maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/clang/test/OpenMP/target_map_codegen.cpp

5262 lines
322 KiB
C++
Raw Normal View History

[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
///
/// Implicit maps.
///
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK1 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK1 --check-prefix CK1-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK1 --check-prefix CK1-64
// RUN: %clang_cc1 -DCK1 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK1 --check-prefix CK1-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK1 --check-prefix CK1-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK1 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY0 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -DCK1 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY0 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY0 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK1
[OPENMP] Fix for PR34014: OpenMP 4.5: Target construct in static method of class fails to map class static variable. If the global variable is captured and it has several redeclarations, sometimes it may lead to a compiler crash. Patch fixes this by working only with canonical declarations. llvm-svn: 311479
2017-08-23 01:54:52 +08:00
class B {
public:
static double VAR;
B() {
}
static void modify(int &res) {
#pragma omp target map(tofrom \
: res)
{
res = B::VAR;
}
}
};
double B::VAR = 1.0;
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK1-LABEL: @.__omp_offloading_{{.*}}implicit_maps_integer{{.*}}_l68.region_id = weak constant i8 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK1-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_PRIVATE_VAL | OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK1-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 800]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK1-LABEL: implicit_maps_integer{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_integer (int a){
[OPENMP] Fix for PR34014: OpenMP 4.5: Target construct in static method of class fails to map class static variable. If the global variable is captured and it has several redeclarations, sometimes it may lead to a compiler crash. Patch fixes this by working only with canonical declarations. llvm-svn: 311479
2017-08-23 01:54:52 +08:00
// CK1: call void{{.*}}modify
B::modify(a);
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
int i = a;
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK1-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK1-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK1-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK1-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK1-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK1-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[sz]]*
// CK1-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[sz]]*
// CK1-DAG: store i[[sz]] [[VAL:%[^,]+]], i[[sz]]* [[CBP1]]
// CK1-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK1-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK1-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to i32*
// CK1-64-DAG: store i32 {{.+}}, i32* [[CADDR]],
// CK1: call void [[KERNEL:@.+]](i[[sz]] [[VAL]])
#pragma omp target
{
++i;
}
}
// CK1: define internal void [[KERNEL]](i[[sz]] [[ARG:%.+]])
// CK1: [[ADDR:%.+]] = alloca i[[sz]],
// CK1: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR]],
// CK1-64: [[CADDR:%.+]] = bitcast i64* [[ADDR]] to i32*
// CK1-64: {{.+}} = load i32, i32* [[CADDR]],
// CK1-32: {{.+}} = load i32, i32* [[ADDR]],
#endif
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK2 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK2 --check-prefix CK2-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK2 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK2 --check-prefix CK2-64
// RUN: %clang_cc1 -DCK2 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK2 --check-prefix CK2-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK2 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK2 --check-prefix CK2-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK2 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY1 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK2 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY1 %s
// RUN: %clang_cc1 -DCK2 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY1 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK2 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY1 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY1-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK2
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK2-LABEL: @.__omp_offloading_{{.*}}implicit_maps_reference{{.*}}_l128.region_id = weak constant i8 0
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// CK2: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_PRIVATE_VAL | OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK2: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 800]
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK2-LABEL: @.__omp_offloading_{{.*}}implicit_maps_reference{{.*}}_l147.region_id = weak constant i8 0
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// CK2: [[SIZES2:@.+]] = {{.+}}constant [1 x i[[sz]]] zeroinitializer
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_IS_PTR | OMP_MAP_IMPLICIT = 544
// CK2: [[TYPES2:@.+]] = {{.+}}constant [1 x i64] [i64 544]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK2-LABEL: implicit_maps_reference{{.*}}(
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
void implicit_maps_reference (int a, int *b){
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
int &i = a;
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK2-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK2-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK2-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK2-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK2-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK2-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[sz]]*
// CK2-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[sz]]*
// CK2-DAG: store i[[sz]] [[VAL:%[^,]+]], i[[sz]]* [[CBP1]]
// CK2-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK2-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK2-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to i32*
// CK2-64-DAG: store i32 {{.+}}, i32* [[CADDR]],
// CK2: call void [[KERNEL:@.+]](i[[sz]] [[VAL]])
#pragma omp target
{
++i;
}
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
int *&p = b;
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK2-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES2]]{{.+}}, {{.+}}[[TYPES2]]{{.+}})
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// CK2-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK2-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK2-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK2-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK2-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i32**
// CK2-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK2-DAG: store i32* [[VAL:%[^,]+]], i32** [[CBP1]]
// CK2-DAG: store i32* [[VAL]], i32** [[CP1]]
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// CK2-DAG: [[VAL]] = load i32*, i32** [[ADDR:%.+]],
// CK2-DAG: [[ADDR]] = load i32**, i32*** [[ADDR2:%.+]],
// CK2: call void [[KERNEL2:@.+]](i32* [[VAL]])
#pragma omp target
{
++p;
}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
}
// CK2: define internal void [[KERNEL]](i[[sz]] [[ARG:%.+]])
// CK2: [[ADDR:%.+]] = alloca i[[sz]],
// CK2: [[REF:%.+]] = alloca i32*,
// CK2: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR]],
// CK2-64: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to i32*
// CK2-64: store i32* [[CADDR]], i32** [[REF]],
// CK2-64: [[RVAL:%.+]] = load i32*, i32** [[REF]],
// CK2-64: {{.+}} = load i32, i32* [[RVAL]],
// CK2-32: store i32* [[ADDR]], i32** [[REF]],
// CK2-32: [[RVAL:%.+]] = load i32*, i32** [[REF]],
// CK2-32: {{.+}} = load i32, i32* [[RVAL]],
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// CK2: define internal void [[KERNEL2]](i32* [[ARG:%.+]])
// CK2: [[ADDR:%.+]] = alloca i32*,
// CK2: [[REF:%.+]] = alloca i32**,
// CK2: store i32* [[ARG]], i32** [[ADDR]],
// CK2: store i32** [[ADDR]], i32*** [[REF]],
// CK2: [[T:%.+]] = load i32**, i32*** [[REF]],
// CK2: [[TT:%.+]] = load i32*, i32** [[T]],
// CK2: getelementptr inbounds i32, i32* [[TT]], i32 1
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK3 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK3 --check-prefix CK3-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK3 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK3 --check-prefix CK3-64
// RUN: %clang_cc1 -DCK3 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK3 --check-prefix CK3-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK3 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK3 --check-prefix CK3-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK3 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY2 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK3 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY2 %s
// RUN: %clang_cc1 -DCK3 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY2 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK3 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY2 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY2-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK3
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK3-LABEL: @.__omp_offloading_{{.*}}implicit_maps_parameter{{.*}}_l214.region_id = weak constant i8 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK3-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_PRIVATE_VAL | OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK3-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 800]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK3-LABEL: implicit_maps_parameter{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_parameter (int a){
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK3-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK3-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK3-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK3-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK3-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK3-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[sz]]*
// CK3-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[sz]]*
// CK3-DAG: store i[[sz]] [[VAL:%[^,]+]], i[[sz]]* [[CBP1]]
// CK3-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK3-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK3-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to i32*
// CK3-64-DAG: store i32 {{.+}}, i32* [[CADDR]],
// CK3: call void [[KERNEL:@.+]](i[[sz]] [[VAL]])
#pragma omp target
{
++a;
}
}
// CK3: define internal void [[KERNEL]](i[[sz]] [[ARG:%.+]])
// CK3: [[ADDR:%.+]] = alloca i[[sz]],
// CK3: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR]],
// CK3-64: [[CADDR:%.+]] = bitcast i64* [[ADDR]] to i32*
// CK3-64: {{.+}} = load i32, i32* [[CADDR]],
// CK3-32: {{.+}} = load i32, i32* [[ADDR]],
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK4 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK4 --check-prefix CK4-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK4 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK4 --check-prefix CK4-64
// RUN: %clang_cc1 -DCK4 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK4 --check-prefix CK4-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK4 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK4 --check-prefix CK4-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK4 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY3 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK4 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY3 %s
// RUN: %clang_cc1 -DCK4 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY3 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK4 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY3 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY3-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK4
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK4-LABEL: @.__omp_offloading_{{.*}}implicit_maps_nested_integer{{.*}}_l276.region_id = weak constant i8 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK4-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_PRIVATE_VAL | OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK4-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 800]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK4-LABEL: implicit_maps_nested_integer{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_nested_integer (int a){
int i = a;
// The captures in parallel are by reference. Only the capture in target is by
// copy.
// CK4: call void {{.+}}@__kmpc_fork_call({{.+}} [[KERNELP1:@.+]] to void (i32*, i32*, ...)*), i32* {{.+}})
// CK4: define internal void [[KERNELP1]](i32* {{[^,]+}}, i32* {{[^,]+}}, i32* {{[^,]+}})
#pragma omp parallel
{
[OPENMP]Improve detection of number of teams, threads in target regions. Added more complex analysis for number of teams and number of threads in the target regions, also merged related common code between CGOpenMPRuntime and CGOpenMPRuntimeNVPTX classes. llvm-svn: 358126
2019-04-11 03:11:33 +08:00
// CK4-DAG: call i32 @__tgt_target_teams(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}}, i32 1, i32 0)
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK4-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK4-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK4-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK4-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK4-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[sz]]*
// CK4-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[sz]]*
// CK4-DAG: store i[[sz]] [[VAL:%[^,]+]], i[[sz]]* [[CBP1]]
// CK4-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK4-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK4-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to i32*
// CK4-64-DAG: store i32 {{.+}}, i32* [[CADDR]],
// CK4: call void [[KERNEL:@.+]](i[[sz]] [[VAL]])
#pragma omp target
{
#pragma omp parallel
{
++i;
}
}
}
}
// CK4: define internal void [[KERNEL]](i[[sz]] [[ARG:%.+]])
// CK4: [[ADDR:%.+]] = alloca i[[sz]],
// CK4: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR]],
// CK4-64: [[CADDR:%.+]] = bitcast i64* [[ADDR]] to i32*
// CK4-64: call void {{.+}}@__kmpc_fork_call({{.+}} [[KERNELP2:@.+]] to void (i32*, i32*, ...)*), i32* [[CADDR]])
// CK4-32: call void {{.+}}@__kmpc_fork_call({{.+}} [[KERNELP2:@.+]] to void (i32*, i32*, ...)*), i32* [[ADDR]])
// CK4: define internal void [[KERNELP2]](i32* {{[^,]+}}, i32* {{[^,]+}}, i32* {{[^,]+}})
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK5 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK5 --check-prefix CK5-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK5 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK5 --check-prefix CK5-64
// RUN: %clang_cc1 -DCK5 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK5 --check-prefix CK5-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK5 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK5 --check-prefix CK5-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK5 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY4 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK5 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY4 %s
// RUN: %clang_cc1 -DCK5 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY4 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK5 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY4 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY4-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK5
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK5-LABEL: @.__omp_offloading_{{.*}}implicit_maps_nested_integer_and_enum{{.*}}_l340.region_id = weak constant i8 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK5-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_PRIVATE_VAL | OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK5-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 800]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK5-LABEL: implicit_maps_nested_integer_and_enum{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_nested_integer_and_enum (int a){
enum Bla {
SomeEnum = 0x09
};
// Using an enum should not change the mapping information.
int i = a;
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK5-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK5-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK5-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK5-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK5-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK5-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[sz]]*
// CK5-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[sz]]*
// CK5-DAG: store i[[sz]] [[VAL:%[^,]+]], i[[sz]]* [[CBP1]]
// CK5-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK5-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK5-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to i32*
// CK5-64-DAG: store i32 {{.+}}, i32* [[CADDR]],
// CK5: call void [[KERNEL:@.+]](i[[sz]] [[VAL]])
#pragma omp target
{
++i;
i += SomeEnum;
}
}
// CK5: define internal void [[KERNEL]](i[[sz]] [[ARG:%.+]])
// CK5: [[ADDR:%.+]] = alloca i[[sz]],
// CK5: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR]],
// CK5-64: [[CADDR:%.+]] = bitcast i64* [[ADDR]] to i32*
// CK5-64: {{.+}} = load i32, i32* [[CADDR]],
// CK5-32: {{.+}} = load i32, i32* [[ADDR]],
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK6 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK6 --check-prefix CK6-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK6 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK6 --check-prefix CK6-64
// RUN: %clang_cc1 -DCK6 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK6 --check-prefix CK6-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK6 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK6 --check-prefix CK6-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK6 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY5 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK6 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY5 %s
// RUN: %clang_cc1 -DCK6 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY5 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK6 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY5 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY5-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK6
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK6-LABEL: @.__omp_offloading_{{.*}}implicit_maps_host_global{{.*}}_l397.region_id = weak constant i8 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK6-DAG: [[GBL:@Gi]] = global i32 0
// CK6-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_PRIVATE_VAL | OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK6-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 800]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK6-LABEL: implicit_maps_host_global{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
int Gi;
void implicit_maps_host_global (int a){
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK6-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK6-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK6-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK6-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK6-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK6-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[sz]]*
// CK6-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[sz]]*
// CK6-DAG: store i[[sz]] [[VAL:%[^,]+]], i[[sz]]* [[CBP1]]
// CK6-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK6-64-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK6-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to i32*
// CK6-64-DAG: store i32 [[GBLVAL:%.+]], i32* [[CADDR]],
// CK6-64-DAG: [[GBLVAL]] = load i32, i32* [[GBL]],
// CK6-32-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[GBLVAL:%.+]],
// CK6: call void [[KERNEL:@.+]](i[[sz]] [[VAL]])
#pragma omp target
{
++Gi;
}
}
// CK6: define internal void [[KERNEL]](i[[sz]] [[ARG:%.+]])
// CK6: [[ADDR:%.+]] = alloca i[[sz]],
// CK6: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR]],
// CK6-64: [[CADDR:%.+]] = bitcast i64* [[ADDR]] to i32*
// CK6-64: {{.+}} = load i32, i32* [[CADDR]],
// CK6-32: {{.+}} = load i32, i32* [[ADDR]],
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK7 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK7 --check-prefix CK7-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK7 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK7 --check-prefix CK7-64
// RUN: %clang_cc1 -DCK7 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK7 --check-prefix CK7-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK7 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK7 --check-prefix CK7-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK7 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY6 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK7 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY6 %s
// RUN: %clang_cc1 -DCK7 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY6 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK7 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY6 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY6-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK7
// For a 32-bit targets, the value doesn't fit the size of the pointer,
// therefore it is passed by reference with a map 'to' specification.
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK7-LABEL: @.__omp_offloading_{{.*}}implicit_maps_double{{.*}}_l464.region_id = weak constant i8 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK7-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 8]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_PRIVATE_VAL | OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK7-64-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 800]
// Map types: OMP_MAP_TO | OMP_MAP_PRIVATE | OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 673
// CK7-32-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 673]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK7-LABEL: implicit_maps_double{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_double (int a){
double d = (double)a;
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK7-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK7-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK7-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK7-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK7-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK7-64-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[sz]]*
// CK7-64-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[sz]]*
// CK7-64-DAG: store i[[sz]] [[VAL:%[^,]+]], i[[sz]]* [[CBP1]]
// CK7-64-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK7-64-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK7-64-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to double*
// CK7-64-64-DAG: store double {{.+}}, double* [[CADDR]],
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK7-32-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to double**
// CK7-32-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to double**
// CK7-32-DAG: store double* [[DECL:%[^,]+]], double** [[CBP1]]
// CK7-32-DAG: store double* [[DECL]], double** [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK7-64: call void [[KERNEL:@.+]](i[[sz]] [[VAL]])
// CK7-32: call void [[KERNEL:@.+]](double* [[DECL]])
#pragma omp target
{
d += 1.0;
}
}
// CK7-64: define internal void [[KERNEL]](i[[sz]] [[ARG:%.+]])
// CK7-64: [[ADDR:%.+]] = alloca i[[sz]],
// CK7-64: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR]],
// CK7-64: [[CADDR:%.+]] = bitcast i64* [[ADDR]] to double*
// CK7-64: {{.+}} = load double, double* [[CADDR]],
// CK7-32: define internal void [[KERNEL]](double* {{.+}}[[ARG:%.+]])
// CK7-32: [[ADDR:%.+]] = alloca double*,
// CK7-32: store double* [[ARG]], double** [[ADDR]],
// CK7-32: [[REF:%.+]] = load double*, double** [[ADDR]],
// CK7-32: {{.+}} = load double, double* [[REF]],
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK8 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK8
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK8 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK8
// RUN: %clang_cc1 -DCK8 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK8
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK8 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK8
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK8 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY7 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK8 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY7 %s
// RUN: %clang_cc1 -DCK8 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY7 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK8 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY7 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY7-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK8
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK8-LABEL: @.__omp_offloading_{{.*}}implicit_maps_float{{.*}}_l524.region_id = weak constant i8 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK8-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_PRIVATE_VAL | OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK8-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 800]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK8-LABEL: implicit_maps_float{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_float (int a){
float f = (float)a;
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK8-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK8-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK8-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK8-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK8-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK8-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[sz]]*
// CK8-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[sz]]*
// CK8-DAG: store i[[sz]] [[VAL:%[^,]+]], i[[sz]]* [[CBP1]]
// CK8-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK8-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK8-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to float*
// CK8-DAG: store float {{.+}}, float* [[CADDR]],
// CK8: call void [[KERNEL:@.+]](i[[sz]] [[VAL]])
#pragma omp target
{
f += 1.0;
}
}
// CK8: define internal void [[KERNEL]](i[[sz]] [[ARG:%.+]])
// CK8: [[ADDR:%.+]] = alloca i[[sz]],
// CK8: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR]],
// CK8: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to float*
// CK8: {{.+}} = load float, float* [[CADDR]],
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK9 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK9
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK9 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK9
// RUN: %clang_cc1 -DCK9 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK9
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK9 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK9
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK9 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY8 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK9 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY8 %s
// RUN: %clang_cc1 -DCK9 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY8 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK9 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY8 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY8-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK9
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK9-LABEL: @.__omp_offloading_{{.*}}implicit_maps_array{{.*}}_l575.region_id = weak constant i8 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK9-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 16]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_TO + OMP_MAP_FROM + OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 547
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK9-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 547]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK9-LABEL: implicit_maps_array{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_array (int a){
double darr[2] = {(double)a, (double)a};
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK9-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK9-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK9-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK9-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK9-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK9-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [2 x double]**
// CK9-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to [2 x double]**
// CK9-DAG: store [2 x double]* [[DECL:%[^,]+]], [2 x double]** [[CBP1]]
// CK9-DAG: store [2 x double]* [[DECL]], [2 x double]** [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK9: call void [[KERNEL:@.+]]([2 x double]* [[DECL]])
#pragma omp target
{
darr[0] += 1.0;
darr[1] += 1.0;
}
}
// CK9: define internal void [[KERNEL]]([2 x double]* {{.+}}[[ARG:%.+]])
// CK9: [[ADDR:%.+]] = alloca [2 x double]*,
// CK9: store [2 x double]* [[ARG]], [2 x double]** [[ADDR]],
// CK9: [[REF:%.+]] = load [2 x double]*, [2 x double]** [[ADDR]],
// CK9: {{.+}} = getelementptr inbounds [2 x double], [2 x double]* [[REF]], i[[sz]] 0, i[[sz]] 0
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK10 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK10
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK10 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK10
// RUN: %clang_cc1 -DCK10 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK10
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK10 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK10
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK10 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY9 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK10 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY9 %s
// RUN: %clang_cc1 -DCK10 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY9 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK10 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY9 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY9-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK10
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK10-LABEL: @.__omp_offloading_{{.*}}implicit_maps_pointer{{.*}}_l626.region_id = weak constant i8 0
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK10-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] zeroinitializer
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 544
// CK10-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 544]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK10-LABEL: implicit_maps_pointer{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_pointer (){
double *ddyn;
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK10-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK10-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK10-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK10-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK10-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK10-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to double**
// CK10-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to double**
// CK10-DAG: store double* [[PTR:%[^,]+]], double** [[CBP1]]
// CK10-DAG: store double* [[PTR]], double** [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK10: call void [[KERNEL:@.+]](double* [[PTR]])
#pragma omp target
{
ddyn[0] += 1.0;
ddyn[1] += 1.0;
}
}
// CK10: define internal void [[KERNEL]](double* {{.*}}[[ARG:%.+]])
// CK10: [[ADDR:%.+]] = alloca double*,
// CK10: store double* [[ARG]], double** [[ADDR]],
// CK10: [[REF:%.+]] = load double*, double** [[ADDR]],
// CK10: {{.+}} = getelementptr inbounds double, double* [[REF]], i[[sz]] 0
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK11 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK11
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK11 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK11
// RUN: %clang_cc1 -DCK11 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK11
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK11 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK11
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK11 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY10 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK11 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY10 %s
// RUN: %clang_cc1 -DCK11 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY10 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK11 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY10 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY10-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK11
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK11-LABEL: @.__omp_offloading_{{.*}}implicit_maps_double_complex{{.*}}_l678.region_id = weak constant i8 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK11-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 16]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_TO | OMP_MAP_FROM | OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 547
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK11-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 547]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK11-LABEL: implicit_maps_double_complex{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_double_complex (int a){
double _Complex dc = (double)a;
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK11-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK11-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK11-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK11-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK11-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK11-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to { double, double }**
// CK11-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to { double, double }**
// CK11-DAG: store { double, double }* [[PTR:%[^,]+]], { double, double }** [[CBP1]]
// CK11-DAG: store { double, double }* [[PTR]], { double, double }** [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK11: call void [[KERNEL:@.+]]({ double, double }* [[PTR]])
[OPENMP] Fix mapping|privatization of implicitly captured variables. If the `defaultmap(tofrom:scalar)` clause is specified, the scalars must be mapped with 'tofrom' modifiers, otherwise they must be captured as firstprivates. llvm-svn: 314995
2017-10-06 01:51:39 +08:00
#pragma omp target defaultmap(tofrom:scalar)
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
{
dc *= dc;
}
}
// CK11: define internal void [[KERNEL]]({ double, double }* {{.*}}[[ARG:%.+]])
// CK11: [[ADDR:%.+]] = alloca { double, double }*,
// CK11: store { double, double }* [[ARG]], { double, double }** [[ADDR]],
// CK11: [[REF:%.+]] = load { double, double }*, { double, double }** [[ADDR]],
// CK11: {{.+}} = getelementptr inbounds { double, double }, { double, double }* [[REF]], i32 0, i32 0
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK12 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK12 --check-prefix CK12-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK12 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK12 --check-prefix CK12-64
// RUN: %clang_cc1 -DCK12 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK12 --check-prefix CK12-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK12 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK12 --check-prefix CK12-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK12 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY11 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK12 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY11 %s
// RUN: %clang_cc1 -DCK12 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY11 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK12 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY11 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY11-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK12
// For a 32-bit targets, the value doesn't fit the size of the pointer,
// therefore it is passed by reference with a map 'to' specification.
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK12-LABEL: @.__omp_offloading_{{.*}}implicit_maps_float_complex{{.*}}_l743.region_id = weak constant i8 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK12-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 8]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_PRIVATE_VAL + OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK12-64-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 800]
// Map types: OMP_MAP_TO | OMP_MAP_PRIVATE | OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 673
// CK12-32-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 673]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK12-LABEL: implicit_maps_float_complex{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_float_complex (int a){
float _Complex fc = (float)a;
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK12-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK12-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK12-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK12-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK12-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK12-64-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[sz]]*
// CK12-64-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[sz]]*
// CK12-64-DAG: store i[[sz]] [[VAL:%[^,]+]], i[[sz]]* [[CBP1]]
// CK12-64-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK12-64-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK12-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to { float, float }*
// CK12-64-DAG: store { float, float } {{.+}}, { float, float }* [[CADDR]],
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK12-32-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to { float, float }**
// CK12-32-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to { float, float }**
// CK12-32-DAG: store { float, float }* [[DECL:%[^,]+]], { float, float }** [[CBP1]]
// CK12-32-DAG: store { float, float }* [[DECL]], { float, float }** [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK12-64: call void [[KERNEL:@.+]](i[[sz]] [[VAL]])
// CK12-32: call void [[KERNEL:@.+]]({ float, float }* [[DECL]])
#pragma omp target
{
fc *= fc;
}
}
// CK12-64: define internal void [[KERNEL]](i[[sz]] [[ARG:%.+]])
// CK12-64: [[ADDR:%.+]] = alloca i[[sz]],
// CK12-64: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR]],
// CK12-64: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to { float, float }*
// CK12-64: {{.+}} = getelementptr inbounds { float, float }, { float, float }* [[CADDR]], i32 0, i32 0
// CK12-32: define internal void [[KERNEL]]({ float, float }* {{.+}}[[ARG:%.+]])
// CK12-32: [[ADDR:%.+]] = alloca { float, float }*,
// CK12-32: store { float, float }* [[ARG]], { float, float }** [[ADDR]],
// CK12-32: [[REF:%.+]] = load { float, float }*, { float, float }** [[ADDR]],
// CK12-32: {{.+}} = getelementptr inbounds { float, float }, { float, float }* [[REF]], i32 0, i32 0
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK13 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK13
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK13 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK13
// RUN: %clang_cc1 -DCK13 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK13
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK13 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK13
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK13 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY12 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK13 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY12 %s
// RUN: %clang_cc1 -DCK13 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY12 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK13 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY12 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY12-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK13
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK13-LABEL: @.__omp_offloading_{{.*}}implicit_maps_variable_length_array{{.*}}_l825.region_id = weak constant i8 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// We don't have a constant map size for VLAs.
// Map types:
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// - OMP_MAP_PRIVATE_VAL + OMP_MAP_TARGET_PARAM = 288 (vla size)
// - OMP_MAP_PRIVATE_VAL + OMP_MAP_TARGET_PARAM = 288 (vla size)
// - OMP_MAP_TO + OMP_MAP_FROM + OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 547
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK13-DAG: [[TYPES:@.+]] = {{.+}}constant [3 x i64] [i64 288, i64 288, i64 547]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK13-LABEL: implicit_maps_variable_length_array{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_variable_length_array (int a){
double vla[2][a];
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK13-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 3, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], i[[sz:64|32]]* [[SGEP:%[^,]+]], {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK13-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK13-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK13-DAG: [[SGEP]] = getelementptr inbounds {{.+}}[[SS:%[^,]+]], i32 0, i32 0
// CK13-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK13-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
// CK13-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[SS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK13-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[sz]]*
// CK13-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[sz]]*
// CK13-DAG: store i[[sz]] 2, i[[sz]]* [[CBP0]]
// CK13-DAG: store i[[sz]] 2, i[[sz]]* [[CP0]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK13-DAG: store i[[sz]] {{8|4}}, i[[sz]]* [[S0]],
// CK13-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 1
// CK13-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 1
// CK13-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[SS]], i32 0, i32 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK13-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[sz]]*
// CK13-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[sz]]*
// CK13-DAG: store i[[sz]] [[VAL:%.+]], i[[sz]]* [[CBP1]]
// CK13-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK13-DAG: store i[[sz]] {{8|4}}, i[[sz]]* [[S1]],
// CK13-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 2
// CK13-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 2
// CK13-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[SS]], i32 0, i32 2
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK13-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to double**
// CK13-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to double**
// CK13-DAG: store double* [[DECL:%.+]], double** [[CBP2]]
// CK13-DAG: store double* [[DECL]], double** [[CP2]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK13-DAG: store i[[sz]] [[VALS2:%.+]], i[[sz]]* [[S2]],
// CK13-DAG: [[VALS2]] = mul nuw i[[sz]] %{{.+}}, 8
// CK13: call void [[KERNEL:@.+]](i[[sz]] {{.+}}, i[[sz]] {{.+}}, double* [[DECL]])
#pragma omp target
{
vla[1][3] += 1.0;
}
}
Fix for PR30639: CGDebugInfo Null dereference with OpenMP array access, by Erich Keane OpenMP creates a variable array type with a a null size-expr. The Debug generation failed to due to this. This patch corrects the openmp implementation, updates the tests, and adds a new one for this condition. Differential Revision: https://reviews.llvm.org/D25373 llvm-svn: 284110
2016-10-13 17:52:46 +08:00
// CK13: define internal void [[KERNEL]](i[[sz]] [[VLA0:%.+]], i[[sz]] [[VLA1:%.+]], double* {{.*}}[[ARG:%.+]])
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK13: [[ADDR0:%.+]] = alloca i[[sz]],
// CK13: [[ADDR1:%.+]] = alloca i[[sz]],
// CK13: [[ADDR2:%.+]] = alloca double*,
// CK13: store i[[sz]] [[VLA0]], i[[sz]]* [[ADDR0]],
// CK13: store i[[sz]] [[VLA1]], i[[sz]]* [[ADDR1]],
// CK13: store double* [[ARG]], double** [[ADDR2]],
// CK13: {{.+}} = load i[[sz]], i[[sz]]* [[ADDR0]],
// CK13: {{.+}} = load i[[sz]], i[[sz]]* [[ADDR1]],
// CK13: [[REF:%.+]] = load double*, double** [[ADDR2]],
// CK13: {{.+}} = getelementptr inbounds double, double* [[REF]], i[[sz]] %{{.+}}
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK14 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK14 --check-prefix CK14-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK14 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK14 --check-prefix CK14-64
// RUN: %clang_cc1 -DCK14 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK14 --check-prefix CK14-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK14 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK14 --check-prefix CK14-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK14 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY13 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK14 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY13 %s
// RUN: %clang_cc1 -DCK14 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY13 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK14 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY13 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY13-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK14
// CK14-DAG: [[ST:%.+]] = type { i32, double }
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK14-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l877.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// Map types:
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// - OMP_MAP_TARGET_PARAM = 32
// - OMP_MAP_TO + OMP_MAP_FROM | OMP_MAP_IMPLICIT | OMP_MAP_MEMBER_OF = 281474976711171
// - OMP_MAP_PRIVATE_VAL + OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK14-DAG: [[TYPES:@.+]] = {{.+}}constant [4 x i64] [i64 32, i64 281474976711171, i64 281474976711171, i64 800]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
class SSS {
public:
int a;
double b;
void foo(int c) {
#pragma omp target
{
a += c;
b += (double)c;
}
}
SSS(int a, double b) : a(a), b(b) {}
};
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK14-LABEL: implicit_maps_class{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_class (int a){
SSS sss(a, (double)a);
// CK14: define {{.*}}void @{{.+}}foo{{.+}}([[ST]]* {{[^,]+}}, i32 {{[^,]+}})
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK14-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 4, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], i[[sz:64|32]]* [[SIZES:%[^,]+]], {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK14-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK14-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK14-DAG: [[SIZES]] = getelementptr inbounds {{.+}}[[S:%[^,]+]], i32 0, i32 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK14-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK14-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK14-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK14-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK14-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK14-DAG: store [[ST]]* [[DECL:%.+]], [[ST]]** [[CBP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK14-DAG: store i32* [[A:%.+]], i32** [[CP0]]
// CK14-DAG: store i[[sz]] %{{.+}}, i[[sz]]* [[S0]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK14-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 1
// CK14-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK14-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i32 0, i32 1
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK14-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[ST]]**
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK14-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK14-DAG: store [[ST]]* [[DECL]], [[ST]]** [[CBP1]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK14-DAG: store i32* [[A]], i32** [[CP1]]
// CK14-DAG: store i[[sz]] 4, i[[sz]]* [[S1]]
// CK14-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 2
// CK14-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 2
// CK14-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i32 0, i32 2
// CK14-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [[ST]]**
// CK14-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to double**
// CK14-DAG: store [[ST]]* [[DECL]], [[ST]]** [[CBP2]]
// CK14-DAG: store double* %{{.+}}, double** [[CP2]]
// CK14-DAG: store i[[sz]] 8, i[[sz]]* [[S2]]
// CK14-DAG: [[BP3:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 3
// CK14-DAG: [[P3:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 3
// CK14-DAG: [[S3:%.+]] = getelementptr inbounds {{.+}}[[S]], i32 0, i32 3
// CK14-DAG: [[CBP3:%.+]] = bitcast i8** [[BP3]] to i[[sz]]*
// CK14-DAG: [[CP3:%.+]] = bitcast i8** [[P3]] to i[[sz]]*
// CK14-DAG: store i[[sz]] [[VAL:%.+]], i[[sz]]* [[CBP3]]
// CK14-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP3]]
// CK14-DAG: store i[[sz]] 4, i[[sz]]* [[S3]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK14-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK14-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to i32*
// CK14-64-DAG: store i32 {{.+}}, i32* [[CADDR]],
// CK14: call void [[KERNEL:@.+]]([[ST]]* [[DECL]], i[[sz]] {{.+}})
sss.foo(123);
}
// CK14: define internal void [[KERNEL]]([[ST]]* [[THIS:%.+]], i[[sz]] [[ARG:%.+]])
// CK14: [[ADDR0:%.+]] = alloca [[ST]]*,
// CK14: [[ADDR1:%.+]] = alloca i[[sz]],
// CK14: store [[ST]]* [[THIS]], [[ST]]** [[ADDR0]],
// CK14: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR1]],
// CK14: [[REF0:%.+]] = load [[ST]]*, [[ST]]** [[ADDR0]],
// CK14-64: [[CADDR1:%.+]] = bitcast i[[sz]]* [[ADDR1]] to i32*
// CK14-64: {{.+}} = load i32, i32* [[CADDR1]],
// CK14-32: {{.+}} = load i32, i32* [[ADDR1]],
// CK14: {{.+}} = getelementptr inbounds [[ST]], [[ST]]* [[REF0]], i32 0, i32 0
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK15 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK15 --check-prefix CK15-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK15 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK15 --check-prefix CK15-64
// RUN: %clang_cc1 -DCK15 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK15 --check-prefix CK15-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK15 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK15 --check-prefix CK15-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK15 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY14 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK15 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY14 %s
// RUN: %clang_cc1 -DCK15 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY14 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK15 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY14 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY14-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK15
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15: [[ST:%.+]] = type { i32, double }
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// Map types:
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// - OMP_MAP_TARGET_PARAM = 32
// - OMP_MAP_TO + OMP_MAP_FROM | OMP_MAP_IMPLICIT | OMP_MAP_MEMBER_OF = 281474976711171
// - OMP_MAP_PRIVATE_VAL + OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK15: [[TYPES:@.+]] = {{.+}}constant [4 x i64] [i64 32, i64 281474976711171, i64 281474976711171, i64 800]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// Map types:
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// - OMP_MAP_TARGET_PARAM = 32
// - OMP_MAP_TO + OMP_MAP_FROM | OMP_MAP_IMPLICIT | OMP_MAP_MEMBER_OF = 281474976711171
// - OMP_MAP_PRIVATE_VAL + OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK15: [[TYPES2:@.+]] = {{.+}}constant [4 x i64] [i64 32, i64 281474976711171, i64 281474976711171, i64 800]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
template<int x>
class SSST {
public:
int a;
double b;
void foo(int c) {
#pragma omp target
{
a += c + x;
b += (double)(c + x);
}
}
template<int y>
void bar(int c) {
#pragma omp target
{
a += c + x + y;
b += (double)(c + x + y);
}
}
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
SSST(int a, double b) : a(a), b(b) {}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
};
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-LABEL: implicit_maps_templated_class{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_templated_class (int a){
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
SSST<123> ssst(a, (double)a);
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK15: define {{.*}}void @{{.+}}foo{{.+}}([[ST]]* {{[^,]+}}, i32 {{[^,]+}})
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 4, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], i[[sz:64|32]]* [[SIZES:%[^,]+]], {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK15-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK15-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[SIZES]] = getelementptr inbounds {{.+}}[[S:%[^,]+]], i32 0, i32 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK15-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK15-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK15-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK15-DAG: store [[ST]]* [[DECL:%.+]], [[ST]]** [[CBP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: store i32* [[A:%.+]], i32** [[CP0]]
// CK15-DAG: store i[[sz]] %{{.+}}, i[[sz]]* [[S0]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK15-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 1
// CK15-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i32 0, i32 1
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[ST]]**
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: store [[ST]]* [[DECL]], [[ST]]** [[CBP1]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: store i32* [[A]], i32** [[CP1]]
// CK15-DAG: store i[[sz]] 4, i[[sz]]* [[S1]]
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 2
// CK15-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 2
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i32 0, i32 2
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [[ST]]**
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to double**
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: store [[ST]]* [[DECL]], [[ST]]** [[CBP2]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: store double* %{{.+}}, double** [[CP2]]
// CK15-DAG: store i[[sz]] 8, i[[sz]]* [[S2]]
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: [[BP3:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 3
// CK15-DAG: [[P3:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 3
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[S3:%.+]] = getelementptr inbounds {{.+}}[[S]], i32 0, i32 3
// CK15-DAG: [[CBP3:%.+]] = bitcast i8** [[BP3]] to i[[sz]]*
// CK15-DAG: [[CP3:%.+]] = bitcast i8** [[P3]] to i[[sz]]*
// CK15-DAG: store i[[sz]] [[VAL:%.+]], i[[sz]]* [[CBP3]]
// CK15-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP3]]
// CK15-DAG: store i[[sz]] 4, i[[sz]]* [[S3]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK15-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK15-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to i32*
// CK15-64-DAG: store i32 {{.+}}, i32* [[CADDR]],
// CK15: call void [[KERNEL:@.+]]([[ST]]* [[DECL]], i[[sz]] {{.+}})
ssst.foo(456);
// CK15: define {{.*}}void @{{.+}}bar{{.+}}([[ST]]* {{[^,]+}}, i32 {{[^,]+}})
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 4, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], i[[sz]]* [[SIZES:[^,]+]], {{.+}}[[TYPES2]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK15-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK15-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[SIZES]] = getelementptr inbounds {{.+}}[[S:%[^,]+]], i32 0, i32 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK15-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK15-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK15-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: store [[ST]]* [[DECL:%.+]], [[ST]]** [[CBP0]]
// CK15-DAG: store i32* [[A:%.+]], i32** [[CP0]]
// CK15-DAG: store i[[sz]] %{{.+}}, i[[sz]]* [[S0]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK15-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 1
// CK15-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i32 0, i32 1
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[ST]]**
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: store [[ST]]* [[DECL]], [[ST]]** [[CBP1]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: store i32* [[A]], i32** [[CP1]]
// CK15-DAG: store i[[sz]] 4, i[[sz]]* [[S1]]
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 2
// CK15-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 2
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i32 0, i32 2
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [[ST]]**
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to double**
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: store [[ST]]* [[DECL]], [[ST]]** [[CBP2]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: store double* %{{.+}}, double** [[CP2]]
// CK15-DAG: store i[[sz]] 8, i[[sz]]* [[S2]]
[OPENMP] Generate implicit map|firstprivate clauses for target-based directives. If the variable is used in the target-based region but is not found in any private|mapping clause, then generate implicit firstprivate|map clauses for these implicitly mapped variables. llvm-svn: 314205
2017-09-26 21:47:31 +08:00
// CK15-DAG: [[BP3:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 3
// CK15-DAG: [[P3:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 3
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK15-DAG: [[S3:%.+]] = getelementptr inbounds {{.+}}[[S]], i32 0, i32 3
// CK15-DAG: [[CBP3:%.+]] = bitcast i8** [[BP3]] to i[[sz]]*
// CK15-DAG: [[CP3:%.+]] = bitcast i8** [[P3]] to i[[sz]]*
// CK15-DAG: store i[[sz]] [[VAL:%.+]], i[[sz]]* [[CBP3]]
// CK15-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP3]]
// CK15-DAG: store i[[sz]] 4, i[[sz]]* [[S3]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK15-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK15-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to i32*
// CK15-64-DAG: store i32 {{.+}}, i32* [[CADDR]],
// CK15: call void [[KERNEL2:@.+]]([[ST]]* [[DECL]], i[[sz]] {{.+}})
ssst.bar<210>(789);
}
// CK15: define internal void [[KERNEL]]([[ST]]* [[THIS:%.+]], i[[sz]] [[ARG:%.+]])
// CK15: [[ADDR0:%.+]] = alloca [[ST]]*,
// CK15: [[ADDR1:%.+]] = alloca i[[sz]],
// CK15: store [[ST]]* [[THIS]], [[ST]]** [[ADDR0]],
// CK15: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR1]],
// CK15: [[REF0:%.+]] = load [[ST]]*, [[ST]]** [[ADDR0]],
// CK15-64: [[CADDR1:%.+]] = bitcast i[[sz]]* [[ADDR1]] to i32*
// CK15-64: {{.+}} = load i32, i32* [[CADDR1]],
// CK15-32: {{.+}} = load i32, i32* [[ADDR1]],
// CK15: {{.+}} = getelementptr inbounds [[ST]], [[ST]]* [[REF0]], i32 0, i32 0
// CK15: define internal void [[KERNEL2]]([[ST]]* [[THIS:%.+]], i[[sz]] [[ARG:%.+]])
// CK15: [[ADDR0:%.+]] = alloca [[ST]]*,
// CK15: [[ADDR1:%.+]] = alloca i[[sz]],
// CK15: store [[ST]]* [[THIS]], [[ST]]** [[ADDR0]],
// CK15: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR1]],
// CK15: [[REF0:%.+]] = load [[ST]]*, [[ST]]** [[ADDR0]],
// CK15-64: [[CADDR1:%.+]] = bitcast i[[sz]]* [[ADDR1]] to i32*
// CK15-64: {{.+}} = load i32, i32* [[CADDR1]],
// CK15-32: {{.+}} = load i32, i32* [[ADDR1]],
// CK15: {{.+}} = getelementptr inbounds [[ST]], [[ST]]* [[REF0]], i32 0, i32 0
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK16 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK16 --check-prefix CK16-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK16 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK16 --check-prefix CK16-64
// RUN: %clang_cc1 -DCK16 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK16 --check-prefix CK16-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK16 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK16 --check-prefix CK16-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK16 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY15 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK16 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY15 %s
// RUN: %clang_cc1 -DCK16 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY15 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK16 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY15 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY15-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK16
// CK16-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
// Map types:
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// - OMP_MAP_PRIVATE_VAL + OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK16-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 800]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
template<int y>
int foo(int d) {
int res = d;
#pragma omp target
{
res += y;
}
return res;
}
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK16-LABEL: implicit_maps_templated_function{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_templated_function (int a){
int i = a;
// CK16: define {{.*}}i32 @{{.+}}foo{{.+}}(i32 {{[^,]+}})
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK16-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK16-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK16-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK16-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK16-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK16-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[sz]]*
// CK16-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[sz]]*
// CK16-DAG: store i[[sz]] [[VAL:%.+]], i[[sz]]* [[CBP1]]
// CK16-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK16-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK16-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to i32*
// CK16-64-DAG: store i32 {{.+}}, i32* [[CADDR]],
// CK16: call void [[KERNEL:@.+]](i[[sz]] [[VAL]])
i = foo<543>(i);
}
// CK16: define internal void [[KERNEL]](i[[sz]] [[ARG:%.+]])
// CK16: [[ADDR:%.+]] = alloca i[[sz]],
// CK16: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR]],
// CK16-64: [[CADDR:%.+]] = bitcast i64* [[ADDR]] to i32*
// CK16-64: {{.+}} = load i32, i32* [[CADDR]],
// CK16-32: {{.+}} = load i32, i32* [[ADDR]],
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK17 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK17
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK17 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK17
// RUN: %clang_cc1 -DCK17 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK17
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK17 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK17
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK17 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY16 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK17 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY16 %s
// RUN: %clang_cc1 -DCK17 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY16 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK17 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY16 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY16-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK17
// CK17-DAG: [[ST:%.+]] = type { i32, double }
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK17-LABEL: @.__omp_offloading_{{.*}}implicit_maps_struct{{.*}}_l1236.region_id = weak constant i8 0
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK17-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} {{16|12}}]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// Map types: OMP_MAP_TO + OMP_MAP_FROM + OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 547
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK17-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 547]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
class SSS {
public:
int a;
double b;
};
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK17-LABEL: implicit_maps_struct{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_struct (int a){
SSS s = {a, (double)a};
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK17-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK17-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK17-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK17-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK17-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK17-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[ST]]**
// CK17-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to [[ST]]**
// CK17-DAG: store [[ST]]* [[DECL:%.+]], [[ST]]** [[CBP1]]
// CK17-DAG: store [[ST]]* [[DECL]], [[ST]]** [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK17: call void [[KERNEL:@.+]]([[ST]]* [[DECL]])
#pragma omp target
{
s.a += 1;
s.b += 1.0;
}
}
// CK17: define internal void [[KERNEL]]([[ST]]* {{.+}}[[ARG:%.+]])
// CK17: [[ADDR:%.+]] = alloca [[ST]]*,
// CK17: store [[ST]]* [[ARG]], [[ST]]** [[ADDR]],
// CK17: [[REF:%.+]] = load [[ST]]*, [[ST]]** [[ADDR]],
// CK17: {{.+}} = getelementptr inbounds [[ST]], [[ST]]* [[REF]], i32 0, i32 0
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK18 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK18 --check-prefix CK18-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK18 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK18 --check-prefix CK18-64
// RUN: %clang_cc1 -DCK18 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK18 --check-prefix CK18-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK18 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK18 --check-prefix CK18-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK18 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY17 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK18 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY17 %s
// RUN: %clang_cc1 -DCK18 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY17 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK18 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY17 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY17-NOT: {{__kmpc|__tgt}}
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#ifdef CK18
// CK18-DAG: [[SIZES:@.+]] = {{.+}}constant [1 x i[[sz:64|32]]] [i{{64|32}} 4]
// Map types:
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// - OMP_MAP_PRIVATE_VAL + OMP_MAP_TARGET_PARAM | OMP_MAP_IMPLICIT = 800
// CK18-DAG: [[TYPES:@.+]] = {{.+}}constant [1 x i64] [i64 800]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
template<typename T>
int foo(T d) {
#pragma omp target
{
d += (T)1;
}
return d;
}
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK18-LABEL: implicit_maps_template_type_capture{{.*}}(
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
void implicit_maps_template_type_capture (int a){
int i = a;
// CK18: define {{.*}}i32 @{{.+}}foo{{.+}}(i32 {{[^,]+}})
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK18-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZES]]{{.+}}, {{.+}}[[TYPES]]{{.+}})
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK18-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK18-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK18-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK18-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK18-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[sz]]*
// CK18-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[sz]]*
// CK18-DAG: store i[[sz]] [[VAL:%.+]], i[[sz]]* [[CBP1]]
// CK18-DAG: store i[[sz]] [[VAL]], i[[sz]]* [[CP1]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
// CK18-DAG: [[VAL]] = load i[[sz]], i[[sz]]* [[ADDR:%.+]],
// CK18-64-DAG: [[CADDR:%.+]] = bitcast i[[sz]]* [[ADDR]] to i32*
// CK18-64-DAG: store i32 {{.+}}, i32* [[CADDR]],
// CK18: call void [[KERNEL:@.+]](i[[sz]] [[VAL]])
i = foo(i);
}
// CK18: define internal void [[KERNEL]](i[[sz]] [[ARG:%.+]])
// CK18: [[ADDR:%.+]] = alloca i[[sz]],
// CK18: store i[[sz]] [[ARG]], i[[sz]]* [[ADDR]],
// CK18-64: [[CADDR:%.+]] = bitcast i64* [[ADDR]] to i32*
// CK18-64: {{.+}} = load i32, i32* [[CADDR]],
// CK18-32: {{.+}} = load i32, i32* [[ADDR]],
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK19 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK19 --check-prefix CK19-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK19 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK19 --check-prefix CK19-64
// RUN: %clang_cc1 -DCK19 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK19 --check-prefix CK19-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK19 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK19 --check-prefix CK19-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK19 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY18 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK19 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY18 %s
// RUN: %clang_cc1 -DCK19 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY18 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK19 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY18 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY18-NOT: {{__kmpc|__tgt}}
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
#ifdef CK19
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1510.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE00:@.+]] = private {{.*}}constant [1 x i[[Z:64|32]]] [i[[Z:64|32]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE00:@.+]] = private {{.*}}constant [1 x i64] [i64 32]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1531.region_id = weak constant i8 0
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK19: [[SIZE00n:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE00n:@.+]] = private {{.*}}constant [1 x i64] [i64 32]
[OpenMP] Fix mapping of scalars for combined directives Combined directives like 'target parallel' have two captured statements. Sema has to check the right one from the right direction. Previously, Sema::IsOpenMPCapturedByRef would return false for mapped scalars on combined directives. This results in a wrong signature of the outlined function which triggers an assertion: void llvm::CallInst::init(llvm::FunctionType *, llvm::Value *, ArrayRef<llvm::Value *>, ArrayRef<OperandBundleDef>, const llvm::Twine &): Assertion `(i >= FTy->getNumParams() || FTy->getParamType(i) == Args[i]->getType()) && "Calling a function with a bad signature!"' failed. Fixes PR30975 (and PR31985). New function was taken from clang-ykt. Differential Revision: https://reviews.llvm.org/D34888 llvm-svn: 306956
2017-07-01 18:40:50 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1553.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE01:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 400]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE01:@.+]] = private {{.*}}constant [1 x i64] [i64 33]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1572.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE02:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 240]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE02:@.+]] = private {{.*}}constant [1 x i64] [i64 34]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1591.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE03:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 240]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE03:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1610.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE04:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 400]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE04:@.+]] = private {{.*}}constant [1 x i64] [i64 32]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1629.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE05:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE05:@.+]] = private {{.*}}constant [1 x i64] [i64 33]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1652.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE06:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1675.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE07:@.+]] = private {{.*}}constant [1 x i64] [i64 32]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1694.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE08:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE08:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1715.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE09:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] {{8|4}}]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE09:@.+]] = private {{.*}}constant [1 x i64] [i64 34]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1736.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE10:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 240]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE10:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1757.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE11:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 240]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE11:@.+]] = private {{.*}}constant [1 x i64] [i64 32]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1778.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE12:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE12:@.+]] = private {{.*}}constant [1 x i64] [i64 33]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1803.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE13:@.+]] = private {{.*}}constant [1 x i64] [i64 32]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1828.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE14:@.+]] = private {{.*}}constant [1 x i64] [i64 33]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1849.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE15:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE15:@.+]] = private {{.*}}constant [1 x i64] [i64 34]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1883.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE16:@.+]] = private {{.*}}constant [2 x i64] [i64 288, i64 33]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1909.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE17:@.+]] = private {{.*}}constant [2 x i[[Z]]] [i[[Z]] {{8|4}}, i[[Z]] 240]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE17:@.+]] = private {{.*}}constant [2 x i64] [i64 288, i64 34]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1935.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE18:@.+]] = private {{.*}}constant [2 x i[[Z]]] [i[[Z]] {{8|4}}, i[[Z]] 240]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE18:@.+]] = private {{.*}}constant [2 x i64] [i64 288, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1967.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE19:@.+]] = private {{.*}}constant [2 x i64] [i64 288, i64 32]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l1993.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE20:@.+]] = private {{.*}}constant [2 x i[[Z]]] [i[[Z]] {{8|4}}, i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE20:@.+]] = private {{.*}}constant [2 x i64] [i64 288, i64 33]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2025.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE21:@.+]] = private {{.*}}constant [2 x i64] [i64 288, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2051.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE22:@.+]] = private {{.*}}constant [2 x i[[Z]]] [i[[Z]] {{8|4}}, i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE22:@.+]] = private {{.*}}constant [2 x i64] [i64 288, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2070.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE23:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE23:@.+]] = private {{.*}}constant [1 x i64] [i64 39]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2092.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE24:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 480]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE24:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2113.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE25:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 16]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE25:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2134.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE26:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 24]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE26:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2155.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE27:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE27:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2200.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE28:@.+]] = private {{.*}}constant [3 x i[[Z]]] [i[[Z]] {{8|4}}, i[[Z]] {{8|4}}, i[[Z]] 16]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19: [[MTYPE28:@.+]] = private {{.*}}constant [3 x i64] [i64 35, i64 16, i64 19]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2245.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE29:@.+]] = private {{.*}}constant [3 x i[[Z]]] [i[[Z]] {{8|4}}, i[[Z]] {{8|4}}, i[[Z]] 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19: [[MTYPE29:@.+]] = private {{.*}}constant [3 x i64] [i64 35, i64 16, i64 19]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2301.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE30:@.+]] = private {{.*}}constant [4 x i64] [i64 288, i64 288, i64 288, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2345.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE31:@.+]] = private {{.*}}constant [4 x i[[Z]]] [i[[Z]] {{8|4}}, i[[Z]] {{8|4}}, i[[Z]] {{8|4}}, i[[Z]] 40]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE31:@.+]] = private {{.*}}constant [4 x i64] [i64 288, i64 288, i64 288, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2368.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE32:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 13728]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE32:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2387.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE33:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 13728]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE33:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2406.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE34:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 13728]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE34:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2431.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE35:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2452.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE36:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 208]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE36:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2492.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE37:@.+]] = private {{.*}}constant [3 x i64] [i64 288, i64 288, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2534.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE38:@.+]] = private {{.*}}constant [3 x i64] [i64 288, i64 288, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2576.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE39:@.+]] = private {{.*}}constant [3 x i64] [i64 288, i64 288, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2618.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE40:@.+]] = private {{.*}}constant [3 x i64] [i64 288, i64 288, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2653.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE41:@.+]] = private {{.*}}constant [3 x i[[Z]]] [i[[Z]] {{8|4}}, i[[Z]] {{8|4}}, i[[Z]] 208]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE41:@.+]] = private {{.*}}constant [3 x i64] [i64 288, i64 288, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2698.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: [[SIZE42:@.+]] = private {{.*}}constant [3 x i[[Z]]] [i[[Z]] {{8|4}}, i[[Z]] {{8|4}}, i[[Z]] 104]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19: [[MTYPE42:@.+]] = private {{.*}}constant [3 x i64] [i64 35, i64 16, i64 19]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: @.__omp_offloading_{{.*}}explicit_maps_single{{.*}}_l2723.region_id = weak constant i8 0
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19: [[MTYPE43:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK19-LABEL: explicit_maps_single{{.*}}(
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
void explicit_maps_single (int ii){
// Map of a scalar.
int a = ii;
// Region 00
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE00]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE00]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store i32* [[VAR0:%.+]], i32** [[CBP0]]
// CK19-DAG: store i32* [[VAR0]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: call void [[CALL00:@.+]](i32* {{[^,]+}})
#pragma omp target map(alloc:a)
{
++a;
}
[OpenMP] Fix mapping of scalars for combined directives Combined directives like 'target parallel' have two captured statements. Sema has to check the right one from the right direction. Previously, Sema::IsOpenMPCapturedByRef would return false for mapped scalars on combined directives. This results in a wrong signature of the outlined function which triggers an assertion: void llvm::CallInst::init(llvm::FunctionType *, llvm::Value *, ArrayRef<llvm::Value *>, ArrayRef<OperandBundleDef>, const llvm::Twine &): Assertion `(i >= FTy->getNumParams() || FTy->getParamType(i) == Args[i]->getType()) && "Calling a function with a bad signature!"' failed. Fixes PR30975 (and PR31985). New function was taken from clang-ykt. Differential Revision: https://reviews.llvm.org/D34888 llvm-svn: 306956
2017-07-01 18:40:50 +08:00
// Map of a scalar in nested region.
int b = a;
// Region 00n
[OPENMP]Improve detection of number of teams, threads in target regions. Added more complex analysis for number of teams and number of threads in the target regions, also merged related common code between CGOpenMPRuntime and CGOpenMPRuntimeNVPTX classes. llvm-svn: 358126
2019-04-11 03:11:33 +08:00
// CK19-DAG: call i32 @__tgt_target_teams(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE00n]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE00n]]{{.+}}, i32 1, i32 0)
[OpenMP] Fix mapping of scalars for combined directives Combined directives like 'target parallel' have two captured statements. Sema has to check the right one from the right direction. Previously, Sema::IsOpenMPCapturedByRef would return false for mapped scalars on combined directives. This results in a wrong signature of the outlined function which triggers an assertion: void llvm::CallInst::init(llvm::FunctionType *, llvm::Value *, ArrayRef<llvm::Value *>, ArrayRef<OperandBundleDef>, const llvm::Twine &): Assertion `(i >= FTy->getNumParams() || FTy->getParamType(i) == Args[i]->getType()) && "Calling a function with a bad signature!"' failed. Fixes PR30975 (and PR31985). New function was taken from clang-ykt. Differential Revision: https://reviews.llvm.org/D34888 llvm-svn: 306956
2017-07-01 18:40:50 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store i32* [[VAR0:%.+]], i32** [[CBP0]]
// CK19-DAG: store i32* [[VAR0]], i32** [[CP0]]
// CK19: call void [[CALL00n:@.+]](i32* {{[^,]+}})
#pragma omp target map(alloc:b)
#pragma omp parallel
{
++b;
}
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// Map of an array.
int arra[100];
// Region 01
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE01]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE01]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x i32]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [100 x i32]**
// CK19-DAG: store [100 x i32]* [[VAR0:%.+]], [100 x i32]** [[CBP0]]
// CK19-DAG: store [100 x i32]* [[VAR0]], [100 x i32]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: call void [[CALL01:@.+]]([100 x i32]* {{[^,]+}})
#pragma omp target map(to:arra)
{
arra[50]++;
}
// Region 02
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE02]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE02]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x i32]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store [100 x i32]* [[VAR0:%.+]], [100 x i32]** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%[^,]+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}[100 x i32]* [[VAR0]], i{{.+}} 0, i{{.+}} 20
// CK19: call void [[CALL02:@.+]]([100 x i32]* {{[^,]+}})
#pragma omp target map(from:arra[20:60])
{
arra[50]++;
}
// Region 03
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE03]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE03]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x i32]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store [100 x i32]* [[VAR0:%.+]], [100 x i32]** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%[^,]+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}[100 x i32]* [[VAR0]], i{{.+}} 0, i{{.+}} 0
// CK19: call void [[CALL03:@.+]]([100 x i32]* {{[^,]+}})
#pragma omp target map(tofrom:arra[:60])
{
arra[50]++;
}
// Region 04
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE04]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE04]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x i32]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store [100 x i32]* [[VAR0:%.+]], [100 x i32]** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%[^,]+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}[100 x i32]* [[VAR0]], i{{.+}} 0, i{{.+}} 0
// CK19: call void [[CALL04:@.+]]([100 x i32]* {{[^,]+}})
#pragma omp target map(alloc:arra[:])
{
arra[50]++;
}
// Region 05
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE05]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE05]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x i32]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store [100 x i32]* [[VAR0:%.+]], [100 x i32]** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%[^,]+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}[100 x i32]* [[VAR0]], i{{.+}} 0, i{{.+}} 15
// CK19: call void [[CALL05:@.+]]([100 x i32]* {{[^,]+}})
#pragma omp target map(to:arra[15])
{
arra[15]++;
}
// Region 06
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE06]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x i32]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store [100 x i32]* [[VAR0:%.+]], [100 x i32]** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%[^,]+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i{{.+}} [[CSVAL0:%[^,]+]], i{{.+}}* [[S0]]
// CK19-DAG: [[CSVAL0]] = mul nuw i{{.+}} %{{.*}}, 4
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}[100 x i32]* [[VAR0]], i{{.+}} 0, i{{.+}} %{{.*}}
// CK19: call void [[CALL06:@.+]]([100 x i32]* {{[^,]+}})
#pragma omp target map(tofrom:arra[ii:ii+23])
{
arra[50]++;
}
// Region 07
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE07]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x i32]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store [100 x i32]* [[VAR0:%.+]], [100 x i32]** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%[^,]+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i{{.+}} [[CSVAL0:%[^,]+]], i{{.+}}* [[S0]]
// CK19-DAG: [[CSVAL0]] = mul nuw i{{.+}} %{{.*}}, 4
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}[100 x i32]* [[VAR0]], i{{.+}} 0, i{{.+}} 0
// CK19: call void [[CALL07:@.+]]([100 x i32]* {{[^,]+}})
#pragma omp target map(alloc:arra[:ii])
{
arra[50]++;
}
// Region 08
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE08]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE08]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x i32]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store [100 x i32]* [[VAR0:%.+]], [100 x i32]** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%[^,]+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}[100 x i32]* [[VAR0]], i{{.+}} 0, i{{.+}} %{{.*}}
// CK19: call void [[CALL08:@.+]]([100 x i32]* {{[^,]+}})
#pragma omp target map(tofrom:arra[ii])
{
arra[15]++;
}
// Map of a pointer.
int *pa;
// Region 09
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE09]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE09]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32***
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32***
// CK19-DAG: store i32** [[VAR0:%.+]], i32*** [[CBP0]]
// CK19-DAG: store i32** [[VAR0]], i32*** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: call void [[CALL09:@.+]](i32** {{[^,]+}})
#pragma omp target map(from:pa)
{
pa[50]++;
}
// Region 10
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE10]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE10]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store i32* [[RVAR0:%.+]], i32** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[RVAR0]] = load i32*, i32** [[VAR0:%[^,]+]]
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}i32* [[RVAR00:%.+]], i{{.+}} 20
// CK19-DAG: [[RVAR00]] = load i32*, i32** [[VAR0]]
// CK19: call void [[CALL10:@.+]](i32* {{[^,]+}})
#pragma omp target map(tofrom:pa[20:60])
{
pa[50]++;
}
// Region 11
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE11]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE11]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store i32* [[RVAR0:%.+]], i32** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[RVAR0]] = load i32*, i32** [[VAR0:%[^,]+]]
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}i32* [[RVAR00:%.+]], i{{.+}} 0
// CK19-DAG: [[RVAR00]] = load i32*, i32** [[VAR0]]
// CK19: call void [[CALL11:@.+]](i32* {{[^,]+}})
#pragma omp target map(alloc:pa[:60])
{
pa[50]++;
}
// Region 12
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE12]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE12]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store i32* [[RVAR0:%.+]], i32** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[RVAR0]] = load i32*, i32** [[VAR0:%[^,]+]]
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}i32* [[RVAR00:%.+]], i{{.+}} 15
// CK19-DAG: [[RVAR00]] = load i32*, i32** [[VAR0]]
// CK19: call void [[CALL12:@.+]](i32* {{[^,]+}})
#pragma omp target map(to:pa[15])
{
pa[15]++;
}
// Region 13
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE13]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store i32* [[RVAR0:%.+]], i32** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i{{.+}} [[CSVAL0:%[^,]+]], i{{.+}}* [[S0]]
// CK19-DAG: [[CSVAL0]] = mul nuw i{{.+}} %{{.*}}, 4
// CK19-DAG: [[RVAR0]] = load i32*, i32** [[VAR0:%[^,]+]]
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}i32* [[RVAR00:%.+]], i{{.+}} %{{.*}}
// CK19-DAG: [[RVAR00]] = load i32*, i32** [[VAR0]]
// CK19: call void [[CALL13:@.+]](i32* {{[^,]+}})
#pragma omp target map(alloc:pa[ii-23:ii])
{
pa[50]++;
}
// Region 14
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE14]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store i32* [[RVAR0:%.+]], i32** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i{{.+}} [[CSVAL0:%[^,]+]], i{{.+}}* [[S0]]
// CK19-DAG: [[CSVAL0]] = mul nuw i{{.+}} %{{.*}}, 4
// CK19-DAG: [[RVAR0]] = load i32*, i32** [[VAR0:%[^,]+]]
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}i32* [[RVAR00:%.+]], i{{.+}} 0
// CK19-DAG: [[RVAR00]] = load i32*, i32** [[VAR0]]
// CK19: call void [[CALL14:@.+]](i32* {{[^,]+}})
#pragma omp target map(to:pa[:ii])
{
pa[50]++;
}
// Region 15
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE15]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE15]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store i32* [[RVAR0:%.+]], i32** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[RVAR0]] = load i32*, i32** [[VAR0:%[^,]+]]
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}i32* [[RVAR00:%.+]], i{{.+}} %{{.*}}
// CK19-DAG: [[RVAR00]] = load i32*, i32** [[VAR0]]
// CK19: call void [[CALL15:@.+]](i32* {{[^,]+}})
#pragma omp target map(from:pa[ii+12])
{
pa[15]++;
}
// Map of a variable-size array.
int va[ii];
// Region 16
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE16]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i{{.+}} {{8|4}}, i{{.+}}* [[S0]]
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i32**
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK19-DAG: store i32* [[VAR1:%.+]], i32** [[CBP1]]
// CK19-DAG: store i32* [[VAR1]], i32** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i{{.+}} [[CSVAL1:%[^,]+]], i{{.+}}* [[S1]]
// CK19-DAG: [[CSVAL1]] = mul nuw i{{.+}} %{{.*}}, 4
// CK19: call void [[CALL16:@.+]](i{{.+}} {{[^,]+}}, i32* {{[^,]+}})
#pragma omp target map(to:va)
{
va[50]++;
}
// Region 17
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[SIZE17]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE17]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i32**
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK19-DAG: store i32* [[VAR1:%.+]], i32** [[CBP1]]
// CK19-DAG: store i32* [[SEC1:%.+]], i32** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC1]] = getelementptr {{.*}}i32* [[VAR1]], i{{.+}} 20
// CK19: call void [[CALL17:@.+]](i{{.+}} {{[^,]+}}, i32* {{[^,]+}})
#pragma omp target map(from:va[20:60])
{
va[50]++;
}
// Region 18
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[SIZE18]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE18]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i32**
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK19-DAG: store i32* [[VAR1:%.+]], i32** [[CBP1]]
// CK19-DAG: store i32* [[SEC1:%.+]], i32** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC1]] = getelementptr {{.*}}i32* [[VAR1]], i{{.+}} 0
// CK19: call void [[CALL18:@.+]](i{{.+}} {{[^,]+}}, i32* {{[^,]+}})
#pragma omp target map(tofrom:va[:60])
{
va[50]++;
}
// Region 19
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE19]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i{{.+}} {{8|4}}, i{{.+}}* [[S0]]
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i32**
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK19-DAG: store i32* [[VAR1:%.+]], i32** [[CBP1]]
// CK19-DAG: store i32* [[SEC1:%.+]], i32** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i{{.+}} [[CSVAL1:%[^,]+]], i{{.+}}* [[S1]]
// CK19-DAG: [[CSVAL1]] = mul nuw i{{.+}} %{{.*}}, 4
// CK19-DAG: [[SEC1]] = getelementptr {{.*}}i32* [[VAR1]], i{{.+}} 0
// CK19: call void [[CALL19:@.+]](i{{.+}} {{[^,]+}}, i32* {{[^,]+}})
#pragma omp target map(alloc:va[:])
{
va[50]++;
}
// Region 20
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[SIZE20]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE20]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i32**
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK19-DAG: store i32* [[VAR1:%.+]], i32** [[CBP1]]
// CK19-DAG: store i32* [[SEC1:%.+]], i32** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC1]] = getelementptr {{.*}}i32* [[VAR1]], i{{.+}} 15
// CK19: call void [[CALL20:@.+]](i{{.+}} {{[^,]+}}, i32* {{[^,]+}})
#pragma omp target map(to:va[15])
{
va[15]++;
}
// Region 21
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE21]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i{{.+}} {{8|4}}, i{{.+}}* [[S0]]
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i32**
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK19-DAG: store i32* [[VAR1:%.+]], i32** [[CBP1]]
// CK19-DAG: store i32* [[SEC1:%.+]], i32** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i{{.+}} [[CSVAL1:%[^,]+]], i{{.+}}* [[S1]]
// CK19-DAG: [[CSVAL1]] = mul nuw i{{.+}} %{{.*}}, 4
// CK19-DAG: [[SEC1]] = getelementptr {{.*}}i32* [[VAR1]], i{{.+}} %{{.+}}
// CK19: call void [[CALL21:@.+]](i{{.+}} {{[^,]+}}, i32* {{[^,]+}})
#pragma omp target map(tofrom:va[ii:ii+23])
{
va[50]++;
}
// Region 22
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[SIZE22]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE22]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i32**
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK19-DAG: store i32* [[VAR1:%.+]], i32** [[CBP1]]
// CK19-DAG: store i32* [[SEC1:%.+]], i32** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC1]] = getelementptr {{.*}}i32* [[VAR1]], i{{.+}} %{{.+}}
// CK19: call void [[CALL22:@.+]](i{{.+}} {{[^,]+}}, i32* {{[^,]+}})
#pragma omp target map(tofrom:va[ii])
{
va[15]++;
}
// Always.
// Region 23
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE23]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE23]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store i32* [[VAR0:%.+]], i32** [[CBP0]]
// CK19-DAG: store i32* [[VAR0]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: call void [[CALL23:@.+]](i32* {{[^,]+}})
#pragma omp target map(always, tofrom: a)
{
a++;
}
// Multidimensional arrays.
int marr[4][5][6];
int ***mptr;
// Region 24
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE24]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE24]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [4 x [5 x [6 x i32]]]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [4 x [5 x [6 x i32]]]**
// CK19-DAG: store [4 x [5 x [6 x i32]]]* [[VAR0:%.+]], [4 x [5 x [6 x i32]]]** [[CBP0]]
// CK19-DAG: store [4 x [5 x [6 x i32]]]* [[VAR0]], [4 x [5 x [6 x i32]]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: call void [[CALL24:@.+]]([4 x [5 x [6 x i32]]]* {{[^,]+}})
#pragma omp target map(tofrom: marr)
{
marr[1][2][3]++;
}
// Region 25
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE25]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE25]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [4 x [5 x [6 x i32]]]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store [4 x [5 x [6 x i32]]]* [[VAR0:%.+]], [4 x [5 x [6 x i32]]]** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}[6 x i32]* [[SEC00:[^,]+]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[SEC00]] = getelementptr {{.*}}[5 x [6 x i32]]* [[SEC000:[^,]+]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[SEC000]] = getelementptr {{.*}}[4 x [5 x [6 x i32]]]* [[VAR0]], i{{.+}} 0, i{{.+}} 1
// CK19: call void [[CALL25:@.+]]([4 x [5 x [6 x i32]]]* {{[^,]+}})
#pragma omp target map(tofrom: marr[1][2][2:4])
{
marr[1][2][3]++;
}
// Region 26
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE26]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE26]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [4 x [5 x [6 x i32]]]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store [4 x [5 x [6 x i32]]]* [[VAR0:%.+]], [4 x [5 x [6 x i32]]]** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}[6 x i32]* [[SEC00:[^,]+]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[SEC00]] = getelementptr {{.*}}[5 x [6 x i32]]* [[SEC000:[^,]+]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[SEC000]] = getelementptr {{.*}}[4 x [5 x [6 x i32]]]* [[VAR0]], i{{.+}} 0, i{{.+}} 1
// CK19: call void [[CALL26:@.+]]([4 x [5 x [6 x i32]]]* {{[^,]+}})
#pragma omp target map(tofrom: marr[1][2][:])
{
marr[1][2][3]++;
}
// Region 27
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE27]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE27]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [4 x [5 x [6 x i32]]]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK19-DAG: store [4 x [5 x [6 x i32]]]* [[VAR0:%.+]], [4 x [5 x [6 x i32]]]** [[CBP0]]
// CK19-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}[6 x i32]* [[SEC00:[^,]+]], i{{.+}} 0, i{{.+}} 3
// CK19-DAG: [[SEC00]] = getelementptr {{.*}}[5 x [6 x i32]]* [[SEC000:[^,]+]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[SEC000]] = getelementptr {{.*}}[4 x [5 x [6 x i32]]]* [[VAR0]], i{{.+}} 0, i{{.+}} 1
// CK19: call void [[CALL27:@.+]]([4 x [5 x [6 x i32]]]* {{[^,]+}})
#pragma omp target map(tofrom: marr[1][2][3])
{
marr[1][2][3]++;
}
// Region 28
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[SIZE28]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE28]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32****
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32****
// CK19-DAG: store i32*** [[VAR0:%.+]], i32**** [[CBP0]]
// CK19-DAG: store i32*** [[SEC0:%.+]], i32**** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[VAR0]] = load i32***, i32**** [[PTR:%[^,]+]],
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}i32*** [[SEC00:[^,]+]], i{{.+}} 1
// CK19-DAG: [[SEC00]] = load i32***, i32**** [[PTR]],
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i32****
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32***
// CK19-DAG: store i32*** [[SEC0]], i32**** [[CBP1]]
// CK19-DAG: store i32** [[SEC1:%.+]], i32*** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC1]] = getelementptr {{.*}}i32** [[SEC11:[^,]+]], i{{.+}} 2
// CK19-DAG: [[SEC11]] = load i32**, i32*** [[SEC111:%[^,]+]],
// CK19-DAG: [[SEC111]] = getelementptr {{.*}}i32*** [[SEC1111:[^,]+]], i{{.+}} 1
// CK19-DAG: [[SEC1111]] = load i32***, i32**** [[PTR]],
// CK19-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to i32***
// CK19-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to i32**
// CK19-DAG: store i32** [[SEC1]], i32*** [[CBP2]]
// CK19-DAG: store i32* [[SEC2:%.+]], i32** [[CP2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC2]] = getelementptr {{.*}}i32* [[SEC22:[^,]+]], i{{.+}} 2
// CK19-DAG: [[SEC22]] = load i32*, i32** [[SEC222:%[^,]+]],
// CK19-DAG: [[SEC222]] = getelementptr {{.*}}i32** [[SEC2222:[^,]+]], i{{.+}} 2
// CK19-DAG: [[SEC2222]] = load i32**, i32*** [[SEC22222:%[^,]+]],
// CK19-DAG: [[SEC22222]] = getelementptr {{.*}}i32*** [[SEC222222:[^,]+]], i{{.+}} 1
// CK19-DAG: [[SEC222222]] = load i32***, i32**** [[PTR]],
// CK19: call void [[CALL28:@.+]](i32*** {{[^,]+}})
#pragma omp target map(tofrom: mptr[1][2][2:4])
{
mptr[1][2][3]++;
}
// Region 29
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[SIZE29]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE29]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32****
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32****
// CK19-DAG: store i32*** [[VAR0:%.+]], i32**** [[CBP0]]
// CK19-DAG: store i32*** [[SEC0:%.+]], i32**** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[VAR0]] = load i32***, i32**** [[PTR:%[^,]+]],
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}i32*** [[SEC00:[^,]+]], i{{.+}} 1
// CK19-DAG: [[SEC00]] = load i32***, i32**** [[PTR]],
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i32****
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32***
// CK19-DAG: store i32*** [[SEC0]], i32**** [[CBP1]]
// CK19-DAG: store i32** [[SEC1:%.+]], i32*** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC1]] = getelementptr {{.*}}i32** [[SEC11:[^,]+]], i{{.+}} 2
// CK19-DAG: [[SEC11]] = load i32**, i32*** [[SEC111:%[^,]+]],
// CK19-DAG: [[SEC111]] = getelementptr {{.*}}i32*** [[SEC1111:[^,]+]], i{{.+}} 1
// CK19-DAG: [[SEC1111]] = load i32***, i32**** [[PTR]],
// CK19-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to i32***
// CK19-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to i32**
// CK19-DAG: store i32** [[SEC1]], i32*** [[CBP2]]
// CK19-DAG: store i32* [[SEC2:%.+]], i32** [[CP2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC2]] = getelementptr {{.*}}i32* [[SEC22:[^,]+]], i{{.+}} 3
// CK19-DAG: [[SEC22]] = load i32*, i32** [[SEC222:%[^,]+]],
// CK19-DAG: [[SEC222]] = getelementptr {{.*}}i32** [[SEC2222:[^,]+]], i{{.+}} 2
// CK19-DAG: [[SEC2222]] = load i32**, i32*** [[SEC22222:%[^,]+]],
// CK19-DAG: [[SEC22222]] = getelementptr {{.*}}i32*** [[SEC222222:[^,]+]], i{{.+}} 1
// CK19-DAG: [[SEC222222]] = load i32***, i32**** [[PTR]],
// CK19: call void [[CALL29:@.+]](i32*** {{[^,]+}})
#pragma omp target map(tofrom: mptr[1][2][3])
{
mptr[1][2][3]++;
}
// Multidimensional VLA.
double mva[23][ii][ii+5];
// Region 30
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 4, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[4 x i{{.+}}]* [[MTYPE30]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
//
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] 23, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] 23, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S0]]
//
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[Z]]*
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[Z]]*
// CK19-DAG: store i[[Z]] [[VAR1:%.+]], i[[Z]]* [[CBP1]]
// CK19-DAG: store i[[Z]] [[VAR11:%.+]], i[[Z]]* [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S1]]
// CK19-64-DAG: [[VAR1]] = zext i32 %{{[^,]+}} to i64
// CK19-64-DAG: [[VAR11]] = zext i32 %{{[^,]+}} to i64
//
// CK19-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 2
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to i[[Z]]*
// CK19-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to i[[Z]]*
// CK19-DAG: store i[[Z]] [[VAR2:%.+]], i[[Z]]* [[CBP2]]
// CK19-DAG: store i[[Z]] [[VAR22:%.+]], i[[Z]]* [[CP2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S2]]
// CK19-64-DAG: [[VAR2]] = zext i32 %{{[^,]+}} to i64
// CK19-64-DAG: [[VAR22]] = zext i32 %{{[^,]+}} to i64
//
// CK19-DAG: [[BP3:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 3
// CK19-DAG: [[P3:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 3
// CK19-DAG: [[S3:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 3
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP3:%.+]] = bitcast i8** [[BP3]] to double**
// CK19-DAG: [[CP3:%.+]] = bitcast i8** [[P3]] to double**
// CK19-DAG: store double* [[VAR3:%.+]], double** [[CBP3]]
// CK19-DAG: store double* [[VAR3]], double** [[CP3]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] [[CSVAL3:%[^,]+]], i[[Z]]* [[S3]]
// CK19-DAG: [[CSVAL3]] = mul nuw i[[Z]] %{{[^,]+}}, {{8|4}}
// CK19: call void [[CALL30:@.+]](i[[Z]] 23, i[[Z]] %{{[^,]+}}, i[[Z]] %{{[^,]+}}, double* %{{[^,]+}})
#pragma omp target map(tofrom: mva)
{
mva[1][2][3]++;
}
// Region 31
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 4, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[4 x i{{.+}}]* [[SIZE31]], {{.+}}getelementptr {{.+}}[4 x i{{.+}}]* [[MTYPE31]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
//
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] 23, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] 23, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
//
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[Z]]*
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[Z]]*
// CK19-DAG: store i[[Z]] [[VAR1:%.+]], i[[Z]]* [[CBP1]]
// CK19-DAG: store i[[Z]] [[VAR11:%.+]], i[[Z]]* [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
//
// CK19-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to i[[Z]]*
// CK19-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to i[[Z]]*
// CK19-DAG: store i[[Z]] [[VAR2:%.+]], i[[Z]]* [[CBP2]]
// CK19-DAG: store i[[Z]] [[VAR22:%.+]], i[[Z]]* [[CP2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
//
// CK19-DAG: [[BP3:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 3
// CK19-DAG: [[P3:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 3
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP3:%.+]] = bitcast i8** [[BP3]] to double**
// CK19-DAG: [[CP3:%.+]] = bitcast i8** [[P3]] to double**
// CK19-DAG: store double* [[VAR3:%.+]], double** [[CBP3]]
// CK19-DAG: store double* [[SEC3:%.+]], double** [[CP3]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC3]] = getelementptr {{.*}}double* [[SEC33:%.+]], i[[Z]] 0
// CK19-DAG: [[SEC33]] = getelementptr {{.*}}double* [[SEC333:%.+]], i[[Z]] [[IDX3:%.+]]
// CK19-DAG: [[IDX3]] = mul nsw i[[Z]] %{{[^,]+}}, %{{[^,]+}}
// CK19-DAG: [[SEC333]] = getelementptr {{.*}}double* [[VAR3]], i[[Z]] [[IDX33:%.+]]
// CK19-DAG: [[IDX33]] = mul nsw i[[Z]] 1, %{{[^,]+}}
// CK19: call void [[CALL31:@.+]](i[[Z]] 23, i[[Z]] %{{[^,]+}}, i[[Z]] %{{[^,]+}}, double* %{{[^,]+}})
#pragma omp target map(tofrom: mva[1][ii-2][:5])
{
mva[1][2][3]++;
}
// Multidimensional array sections.
double marras[11][12][13];
double mvlaas[11][ii][13];
double ***mptras;
// Region 32
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE32]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE32]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [11 x [12 x [13 x double]]]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [11 x [12 x [13 x double]]]**
// CK19-DAG: store [11 x [12 x [13 x double]]]* [[VAR0:%.+]], [11 x [12 x [13 x double]]]** [[CBP0]]
// CK19-DAG: store [11 x [12 x [13 x double]]]* [[VAR0]], [11 x [12 x [13 x double]]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19: call void [[CALL32:@.+]]([11 x [12 x [13 x double]]]* {{[^,]+}})
#pragma omp target map(marras)
{
marras[1][2][3]++;
}
// Region 33
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE33]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE33]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [11 x [12 x [13 x double]]]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [12 x [13 x double]]**
// CK19-DAG: store [11 x [12 x [13 x double]]]* [[VAR0:%.+]], [11 x [12 x [13 x double]]]** [[CBP0]]
// CK19-DAG: store [12 x [13 x double]]* [[SEC0:%.+]], [12 x [13 x double]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC0]] = getelementptr {{.+}}[11 x [12 x [13 x double]]]* [[VAR0]], i[[Z]] 0, i[[Z]] 0
// CK19: call void [[CALL33:@.+]]([11 x [12 x [13 x double]]]* {{[^,]+}})
#pragma omp target map(marras[:])
{
marras[1][2][3]++;
}
// Region 34
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE34]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE34]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [11 x [12 x [13 x double]]]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [12 x [13 x double]]**
// CK19-DAG: store [11 x [12 x [13 x double]]]* [[VAR0:%.+]], [11 x [12 x [13 x double]]]** [[CBP0]]
// CK19-DAG: store [12 x [13 x double]]* [[SEC0:%.+]], [12 x [13 x double]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC0]] = getelementptr {{.+}}[11 x [12 x [13 x double]]]* [[VAR0]], i[[Z]] 0, i[[Z]] 0
// CK19: call void [[CALL34:@.+]]([11 x [12 x [13 x double]]]* {{[^,]+}})
#pragma omp target map(marras[:][:][:])
{
marras[1][2][3]++;
}
// Region 35
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE35]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
//
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [11 x [12 x [13 x double]]]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [13 x double]**
// CK19-DAG: store [11 x [12 x [13 x double]]]* [[VAR0:%.+]], [11 x [12 x [13 x double]]]** [[CBP0]]
// CK19-DAG: store [13 x double]* [[SEC0:%.+]], [13 x double]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] [[CSVAL0:%[^,]+]], i[[Z]]* [[S0]]
// CK19-DAG: [[SEC0]] = getelementptr {{.+}}[12 x [13 x double]]* [[SEC00:%[^,]+]], i[[Z]] 0, i[[Z]] 0
// CK19-DAG: [[SEC00]] = getelementptr {{.+}}[11 x [12 x [13 x double]]]* [[VAR0]], i[[Z]] 0, i[[Z]] 1
// CK19-DAG: [[CSVAL0]] = mul nuw i[[Z]] %{{[^,]+}}, 104
// CK19: call void [[CALL35:@.+]]([11 x [12 x [13 x double]]]* {{[^,]+}})
#pragma omp target map(marras[1][:ii][:])
{
marras[1][2][3]++;
}
// Region 36
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE36]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE36]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [11 x [12 x [13 x double]]]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [13 x double]**
// CK19-DAG: store [11 x [12 x [13 x double]]]* [[VAR0:%.+]], [11 x [12 x [13 x double]]]** [[CBP0]]
// CK19-DAG: store [13 x double]* [[SEC0:%.+]], [13 x double]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC0]] = getelementptr {{.+}}[13 x double]* [[SEC00:%[^,]+]], i{{.+}} 0
// CK19-DAG: [[SEC00]] = getelementptr {{.+}}[12 x [13 x double]]* [[SEC000:%[^,]+]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[SEC000]] = getelementptr {{.+}}[11 x [12 x [13 x double]]]* [[VAR0]], i{{.+}} 0, i{{.+}} 0
// CK19: call void [[CALL36:@.+]]([11 x [12 x [13 x double]]]* {{[^,]+}})
#pragma omp target map(marras[:1][:2][:13])
{
marras[1][2][3]++;
}
// Region 37
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE37]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
//
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] 11, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] 11, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S0]]
//
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[Z]]*
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[Z]]*
// CK19-DAG: store i[[Z]] [[VAR1:%.+]], i[[Z]]* [[CBP1]]
// CK19-DAG: store i[[Z]] [[VAR11:%.+]], i[[Z]]* [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S1]]
//
// CK19-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 2
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [13 x double]**
// CK19-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to [13 x double]**
// CK19-DAG: store [13 x double]* [[VAR2:%.+]], [13 x double]** [[CBP2]]
// CK19-DAG: store [13 x double]* [[VAR2]], [13 x double]** [[CP2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] [[CSVAL2:%[^,]+]], i[[Z]]* [[S2]]
// CK19-DAG: [[CSVAL2]] = mul nuw i[[Z]] %{{[^,]+}}, 104
// CK19: call void [[CALL37:@.+]](i[[Z]] 11, i[[Z]] %{{[^,]+}}, [13 x double]* %{{[^,]+}})
#pragma omp target map(mvlaas)
{
mvlaas[1][2][3]++;
}
// Region 38
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE38]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
//
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] 11, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] 11, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S0]]
//
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[Z]]*
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[Z]]*
// CK19-DAG: store i[[Z]] [[VAR1:%.+]], i[[Z]]* [[CBP1]]
// CK19-DAG: store i[[Z]] [[VAR11:%.+]], i[[Z]]* [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S1]]
//
// CK19-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 2
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [13 x double]**
// CK19-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to [13 x double]**
// CK19-DAG: store [13 x double]* [[VAR2:%.+]], [13 x double]** [[CBP2]]
// CK19-DAG: store [13 x double]* [[SEC2:%.+]], [13 x double]** [[CP2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] [[CSVAL2:%[^,]+]], i[[Z]]* [[S2]]
// CK19-DAG: [[SEC2]] = getelementptr {{.+}}[13 x double]* [[VAR2]], i[[Z]] [[SEC22:%[^,]+]]
// CK19-DAG: [[SEC22]] = mul nsw i[[Z]] 0, %{{[^,]+}}
// CK19-DAG: [[CSVAL2]] = mul nuw i[[Z]] %{{[^,]+}}, 104
// CK19: call void [[CALL38:@.+]](i[[Z]] 11, i[[Z]] %{{[^,]+}}, [13 x double]* %{{[^,]+}})
#pragma omp target map(mvlaas[:])
{
mvlaas[1][2][3]++;
}
// Region 39
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE39]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
//
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] 11, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] 11, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S0]]
//
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[Z]]*
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[Z]]*
// CK19-DAG: store i[[Z]] [[VAR1:%.+]], i[[Z]]* [[CBP1]]
// CK19-DAG: store i[[Z]] [[VAR11:%.+]], i[[Z]]* [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S1]]
//
// CK19-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 2
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [13 x double]**
// CK19-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to [13 x double]**
// CK19-DAG: store [13 x double]* [[VAR2:%.+]], [13 x double]** [[CBP2]]
// CK19-DAG: store [13 x double]* [[SEC2:%.+]], [13 x double]** [[CP2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] [[CSVAL2:%[^,]+]], i[[Z]]* [[S2]]
// CK19-DAG: [[SEC2]] = getelementptr {{.+}}[13 x double]* [[VAR2]], i[[Z]] [[SEC22:%[^,]+]]
// CK19-DAG: [[SEC22]] = mul nsw i[[Z]] 0, %{{[^,]+}}
// CK19-DAG: [[CSVAL2]] = mul nuw i[[Z]] %{{[^,]+}}, 104
// CK19: call void [[CALL39:@.+]](i[[Z]] 11, i[[Z]] %{{[^,]+}}, [13 x double]* %{{[^,]+}})
#pragma omp target map(mvlaas[:][:][:])
{
mvlaas[1][2][3]++;
}
// Region 40
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE40]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
//
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] 11, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] 11, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S0]]
//
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[Z]]*
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[Z]]*
// CK19-DAG: store i[[Z]] [[VAR1:%.+]], i[[Z]]* [[CBP1]]
// CK19-DAG: store i[[Z]] [[VAR11:%.+]], i[[Z]]* [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S1]]
//
// CK19-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 2
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [13 x double]**
// CK19-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to [13 x double]**
// CK19-DAG: store [13 x double]* [[VAR2:%.+]], [13 x double]** [[CBP2]]
// CK19-DAG: store [13 x double]* [[SEC2:%.+]], [13 x double]** [[CP2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] [[CSVAL2:%[^,]+]], i[[Z]]* [[S2]]
// CK19-DAG: [[SEC2]] = getelementptr {{.+}}[13 x double]* [[SEC22:%[^,]+]], i[[Z]] 0
// CK19-DAG: [[SEC22]] = getelementptr {{.+}}[13 x double]* [[VAR2]], i[[Z]] [[SEC222:%[^,]+]]
// CK19-DAG: [[SEC222]] = mul nsw i[[Z]] 1, %{{[^,]+}}
// CK19: call void [[CALL40:@.+]](i[[Z]] 11, i[[Z]] %{{[^,]+}}, [13 x double]* %{{[^,]+}})
#pragma omp target map(mvlaas[1][:ii][:])
{
mvlaas[1][2][3]++;
}
// Region 41
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[SIZE41]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE41]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
//
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i[[Z]]*
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i[[Z]]*
// CK19-DAG: store i[[Z]] 11, i[[Z]]* [[CBP0]]
// CK19-DAG: store i[[Z]] 11, i[[Z]]* [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
//
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[Z]]*
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[Z]]*
// CK19-DAG: store i[[Z]] [[VAR1:%.+]], i[[Z]]* [[CBP1]]
// CK19-DAG: store i[[Z]] [[VAR11:%.+]], i[[Z]]* [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
//
// CK19-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [13 x double]**
// CK19-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to [13 x double]**
// CK19-DAG: store [13 x double]* [[VAR2:%.+]], [13 x double]** [[CBP2]]
// CK19-DAG: store [13 x double]* [[SEC2:%.+]], [13 x double]** [[CP2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC2]] = getelementptr {{.+}}[13 x double]* [[SEC22:%[^,]+]], i[[Z]] 0
// CK19-DAG: [[SEC22]] = getelementptr {{.+}}[13 x double]* [[VAR2]], i[[Z]] [[SEC222:%[^,]+]]
// CK19-DAG: [[SEC222]] = mul nsw i[[Z]] 0, %{{[^,]+}}
// CK19: call void [[CALL41:@.+]](i[[Z]] 11, i[[Z]] %{{[^,]+}}, [13 x double]* %{{[^,]+}})
#pragma omp target map(mvlaas[:1][:2][:13])
{
mvlaas[1][2][3]++;
}
// Region 42
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[SIZE42]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE42]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to double****
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to double****
// CK19-DAG: store double*** [[VAR0:%.+]], double**** [[CBP0]]
// CK19-DAG: store double*** [[SEC0:%.+]], double**** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[VAR0]] = load double***, double**** [[PTR:%[^,]+]],
// CK19-DAG: [[SEC0]] = getelementptr {{.*}}double*** [[SEC00:[^,]+]], i{{.+}} 0
// CK19-DAG: [[SEC00]] = load double***, double**** [[PTR]],
// CK19-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK19-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to double****
// CK19-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to double***
// CK19-DAG: store double*** [[SEC0]], double**** [[CBP1]]
// CK19-DAG: store double** [[SEC1:%.+]], double*** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC1]] = getelementptr {{.*}}double** [[SEC11:[^,]+]], i{{.+}} 2
// CK19-DAG: [[SEC11]] = load double**, double*** [[SEC111:%[^,]+]],
// CK19-DAG: [[SEC111]] = getelementptr {{.*}}double*** [[SEC1111:[^,]+]], i{{.+}} 0
// CK19-DAG: [[SEC1111]] = load double***, double**** [[PTR]],
// CK19-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK19-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to double***
// CK19-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to double**
// CK19-DAG: store double** [[SEC1]], double*** [[CBP2]]
// CK19-DAG: store double* [[SEC2:%.+]], double** [[CP2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[SEC2]] = getelementptr {{.*}}double* [[SEC22:[^,]+]], i{{.+}} 0
// CK19-DAG: [[SEC22]] = load double*, double** [[SEC222:%[^,]+]],
// CK19-DAG: [[SEC222]] = getelementptr {{.*}}double** [[SEC2222:[^,]+]], i{{.+}} 2
// CK19-DAG: [[SEC2222]] = load double**, double*** [[SEC22222:%[^,]+]],
// CK19-DAG: [[SEC22222]] = getelementptr {{.*}}double*** [[SEC222222:[^,]+]], i{{.+}} 0
// CK19-DAG: [[SEC222222]] = load double***, double**** [[PTR]],
// CK19: call void [[CALL42:@.+]](double*** {{[^,]+}})
#pragma omp target map(mptras[:1][2][:13])
{
mptras[1][2][3]++;
}
// Region 43 - the memory is not contiguous for this map - will map the whole last dimension.
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK19-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE43]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK19-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK19-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
//
// CK19-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
// CK19-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK19-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [11 x [12 x [13 x double]]]**
// CK19-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [13 x double]**
// CK19-DAG: store [11 x [12 x [13 x double]]]* [[VAR0:%.+]], [11 x [12 x [13 x double]]]** [[CBP0]]
// CK19-DAG: store [13 x double]* [[SEC0:%.+]], [13 x double]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK19-DAG: store i[[Z]] [[CSVAL0:%[^,]+]], i[[Z]]* [[S0]]
// CK19-DAG: [[SEC0]] = getelementptr {{.+}}[12 x [13 x double]]* [[SEC00:%[^,]+]], i[[Z]] 0, i[[Z]] 0
// CK19-DAG: [[SEC00]] = getelementptr {{.+}}[11 x [12 x [13 x double]]]* [[VAR0]], i[[Z]] 0, i[[Z]] 1
// CK19-DAG: [[CSVAL0]] = mul nuw i[[Z]] %{{[^,]+}}, 104
// CK19: call void [[CALL43:@.+]]([11 x [12 x [13 x double]]]* {{[^,]+}})
#pragma omp target map(marras[1][:ii][1:])
{
marras[1][2][3]++;
}
}
// CK19: define {{.+}}[[CALL00]]
// CK19: define {{.+}}[[CALL01]]
// CK19: define {{.+}}[[CALL02]]
// CK19: define {{.+}}[[CALL03]]
// CK19: define {{.+}}[[CALL04]]
// CK19: define {{.+}}[[CALL05]]
// CK19: define {{.+}}[[CALL06]]
// CK19: define {{.+}}[[CALL07]]
// CK19: define {{.+}}[[CALL08]]
// CK19: define {{.+}}[[CALL09]]
// CK19: define {{.+}}[[CALL10]]
// CK19: define {{.+}}[[CALL11]]
// CK19: define {{.+}}[[CALL12]]
// CK19: define {{.+}}[[CALL13]]
// CK19: define {{.+}}[[CALL14]]
// CK19: define {{.+}}[[CALL15]]
// CK19: define {{.+}}[[CALL16]]
// CK19: define {{.+}}[[CALL17]]
// CK19: define {{.+}}[[CALL18]]
// CK19: define {{.+}}[[CALL19]]
// CK19: define {{.+}}[[CALL20]]
// CK19: define {{.+}}[[CALL21]]
// CK19: define {{.+}}[[CALL22]]
// CK19: define {{.+}}[[CALL23]]
// CK19: define {{.+}}[[CALL24]]
// CK19: define {{.+}}[[CALL25]]
// CK19: define {{.+}}[[CALL26]]
// CK19: define {{.+}}[[CALL27]]
// CK19: define {{.+}}[[CALL28]]
// CK19: define {{.+}}[[CALL29]]
// CK19: define {{.+}}[[CALL30]]
// CK19: define {{.+}}[[CALL31]]
// CK19: define {{.+}}[[CALL32]]
// CK19: define {{.+}}[[CALL33]]
// CK19: define {{.+}}[[CALL34]]
// CK19: define {{.+}}[[CALL35]]
// CK19: define {{.+}}[[CALL36]]
// CK19: define {{.+}}[[CALL37]]
// CK19: define {{.+}}[[CALL38]]
// CK19: define {{.+}}[[CALL39]]
// CK19: define {{.+}}[[CALL40]]
// CK19: define {{.+}}[[CALL41]]
// CK19: define {{.+}}[[CALL42]]
// CK19: define {{.+}}[[CALL43]]
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK20 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK20 --check-prefix CK20-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK20 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK20 --check-prefix CK20-64
// RUN: %clang_cc1 -DCK20 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK20 --check-prefix CK20-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK20 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK20 --check-prefix CK20-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK20 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY19 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK20 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY19 %s
// RUN: %clang_cc1 -DCK20 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY19 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK20 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY19 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY19-NOT: {{__kmpc|__tgt}}
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
#ifdef CK20
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK20-LABEL: @.__omp_offloading_{{.*}}explicit_maps_references_and_function_args{{.*}}_l2832.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK20: [[SIZE00:@.+]] = private {{.*}}constant [1 x i[[Z:64|32]]] [i[[Z:64|32]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK20: [[MTYPE00:@.+]] = private {{.*}}constant [1 x i64] [i64 33]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK20-LABEL: @.__omp_offloading_{{.*}}explicit_maps_references_and_function_args{{.*}}_l2853.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK20: [[SIZE01:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 20]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK20: [[MTYPE01:@.+]] = private {{.*}}constant [1 x i64] [i64 33]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK20-LABEL: @.__omp_offloading_{{.*}}explicit_maps_references_and_function_args{{.*}}_l2871.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK20: [[SIZE02:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK20: [[MTYPE02:@.+]] = private {{.*}}constant [1 x i64] [i64 34]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK20-LABEL: @.__omp_offloading_{{.*}}explicit_maps_references_and_function_args{{.*}}_l2892.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK20: [[SIZE03:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 12]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK20: [[MTYPE03:@.+]] = private {{.*}}constant [1 x i64] [i64 34]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK20-LABEL: explicit_maps_references_and_function_args{{.*}}(
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
void explicit_maps_references_and_function_args (int a, float b, int (&c)[10], float *d){
int &aa = a;
float &bb = b;
int (&cc)[10] = c;
float *&dd = d;
// Region 00
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK20-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE00]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE00]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK20-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK20-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK20-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK20-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK20-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK20-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK20-DAG: store i32* [[RVAR0:%.+]], i32** [[CBP0]]
// CK20-DAG: store i32* [[RVAR00:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK20-DAG: [[RVAR0]] = load i32*, i32** [[VAR0:%[^,]+]]
// CK20-DAG: [[RVAR00]] = load i32*, i32** [[VAR0]]
// CK20: call void [[CALL00:@.+]](i32* {{[^,]+}})
#pragma omp target map(to:aa)
{
aa += 1;
}
// Region 01
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK20-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE01]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE01]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK20-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK20-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK20-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK20-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK20-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [10 x i32]**
// CK20-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK20-DAG: store [10 x i32]* [[RVAR0:%.+]], [10 x i32]** [[CBP0]]
// CK20-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK20-DAG: [[SEC0]] = getelementptr {{.*}}[10 x i32]* [[RVAR00:%.+]], i{{.+}} 0, i{{.+}} 0
// CK20-DAG: [[RVAR0]] = load [10 x i32]*, [10 x i32]** [[VAR0:%[^,]+]]
// CK20-DAG: [[RVAR00]] = load [10 x i32]*, [10 x i32]** [[VAR0]]
// CK20: call void [[CALL01:@.+]]([10 x i32]* {{[^,]+}})
#pragma omp target map(to:cc[:5])
{
cc[3] += 1;
}
// Region 02
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK20-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE02]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE02]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK20-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK20-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK20-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK20-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK20-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to float**
// CK20-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to float**
// CK20-DAG: store float* [[VAR0:%.+]], float** [[CBP0]]
// CK20-DAG: store float* [[VAR0]], float** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK20: call void [[CALL02:@.+]](float* {{[^,]+}})
#pragma omp target map(from:b)
{
b += 1.0f;
}
// Region 03
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK20-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE03]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE03]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK20-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK20-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK20-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK20-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK20-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to float**
// CK20-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to float**
// CK20-DAG: store float* [[RVAR0:%.+]], float** [[CBP0]]
// CK20-DAG: store float* [[SEC0:%.+]], float** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK20-DAG: [[RVAR0]] = load float*, float** [[VAR0:%[^,]+]]
// CK20-DAG: [[SEC0]] = getelementptr {{.*}}float* [[RVAR00:%.+]], i{{.+}} 2
// CK20-DAG: [[RVAR00]] = load float*, float** [[VAR0]]
// CK20: call void [[CALL03:@.+]](float* {{[^,]+}})
#pragma omp target map(from:d[2:3])
{
d[2] += 1.0f;
}
}
// CK20: define {{.+}}[[CALL00]]
// CK20: define {{.+}}[[CALL01]]
// CK20: define {{.+}}[[CALL02]]
// CK20: define {{.+}}[[CALL03]]
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK21 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK21 --check-prefix CK21-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK21 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK21 --check-prefix CK21-64
// RUN: %clang_cc1 -DCK21 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK21 --check-prefix CK21-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK21 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK21 --check-prefix CK21-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK21 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY20 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK21 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY20 %s
// RUN: %clang_cc1 -DCK21 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY20 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK21 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY20 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY20-NOT: {{__kmpc|__tgt}}
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
#ifdef CK21
// CK21: [[ST:%.+]] = type { i32, i32, float* }
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK21-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21: [[MTYPE00:@.+]] = private {{.*}}constant [2 x i64] [i64 32, i64 281474976710659]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK21-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21: [[SIZE01:@.+]] = private {{.*}}constant [1 x i[[Z:64|32]]] [i[[Z:64|32]] 492]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK21: [[MTYPE01:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK21-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21: [[MTYPE02:@.+]] = private {{.*}}constant [2 x i64] [i64 32, i64 281474976710674]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK21-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21: [[SIZE03:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 492]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK21: [[MTYPE03:@.+]] = private {{.*}}constant [1 x i64] [i64 34]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK21-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21: [[SIZE04:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK21: [[MTYPE04:@.+]] = private {{.*}}constant [1 x i64] [i64 34]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK21-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21: [[MTYPE05:@.+]] = private {{.*}}constant [3 x i64] [i64 32, i64 281474976710659, i64 281474976710659]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-LABEL: explicit_maps_template_args_and_members{{.*}}(
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
template <int X, typename T>
struct CC {
T A;
int A2;
float *B;
int foo(T arg) {
float la[X];
T *lb;
// Region 00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE00]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK21-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK21-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK21-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
// CK21-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK21-DAG: store [[ST]]* [[VAR0:%.+]], [[ST]]** [[CBP0]]
// CK21-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[SEC0]] = getelementptr {{.*}}[[ST]]* [[VAR0:%.+]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK21-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK21-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK21-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[ST]]**
// CK21-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK21-DAG: store [[ST]]* [[VAR1:%.+]], [[ST]]** [[CBP1]]
// CK21-DAG: store i32* [[SEC1:%.+]], i32** [[CP1]]
// CK21-DAG: store i[[Z]] {{.+}}, i[[Z]]* [[S1]]
// CK21-DAG: [[SEC1]] = getelementptr {{.*}}[[ST]]* [[VAR1:%.+]], i{{.+}} 0, i{{.+}} 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21: call void [[CALL00:@.+]]([[ST]]* {{[^,]+}})
#pragma omp target map(A)
{
A += 1;
}
// Region 01
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK21-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE01]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE01]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK21-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK21-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK21-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK21-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK21-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK21-DAG: store i32* [[RVAR0:%.+]], i32** [[CBP0]]
// CK21-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[RVAR0]] = load i32*, i32** [[VAR0:%[^,]+]]
// CK21-DAG: [[SEC0]] = getelementptr {{.*}}i32* [[RVAR00:%.+]], i{{.+}} 0
// CK21-DAG: [[RVAR00]] = load i32*, i32** [[VAR0]]
// CK21: call void [[CALL01:@.+]](i32* {{[^,]+}})
#pragma omp target map(lb[:X])
{
lb[4] += 1;
}
// Region 02
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE02]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK21-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK21-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK21-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
// CK21-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to float***
// CK21-DAG: store [[ST]]* [[VAR0:%.+]], [[ST]]** [[CBP0]]
// CK21-DAG: store float** [[SEC0:%.+]], float*** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[SEC0]] = getelementptr {{.*}}[[ST]]* [[VAR0]], i{{.+}} 0, i{{.+}} 2
// CK21-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK21-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK21-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to float***
// CK21-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to float**
// CK21-DAG: store float** [[SEC0]], float*** [[CBP1]]
// CK21-DAG: store float* [[SEC1:%.+]], float** [[CP1]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: store i[[Z]] {{.+}}, i[[Z]]* [[S1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[SEC1]] = getelementptr {{.*}}float* [[RVAR1:%[^,]+]], i{{.+}} 123
// CK21-DAG: [[RVAR1]] = load float*, float** [[SEC1_:%[^,]+]]
// CK21-DAG: [[SEC1_]] = getelementptr {{.*}}[[ST]]* [[VAR0]], i{{.+}} 0, i{{.+}} 2
// CK21: call void [[CALL02:@.+]]([[ST]]* {{[^,]+}})
#pragma omp target map(from:B[X:X+2])
{
B[2] += 1.0f;
}
// Region 03
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK21-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE03]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE03]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK21-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK21-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK21-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK21-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [123 x float]**
// CK21-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [123 x float]**
// CK21-DAG: store [123 x float]* [[VAR0:%.+]], [123 x float]** [[CBP0]]
// CK21-DAG: store [123 x float]* [[VAR0]], [123 x float]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21: call void [[CALL03:@.+]]([123 x float]* {{[^,]+}})
#pragma omp target map(from:la)
{
la[3] += 1.0f;
}
// Region 04
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK21-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE04]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE04]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK21-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK21-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK21-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK21-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK21-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK21-DAG: store i32* [[VAR0:%.+]], i32** [[CBP0]]
// CK21-DAG: store i32* [[VAR0]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21: call void [[CALL04:@.+]](i32* {{[^,]+}})
#pragma omp target map(from:arg)
{
arg +=1;
}
// Make sure the extra flag is passed to the second map.
// Region 05
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE05]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK21-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK21-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK21-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
// CK21-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK21-DAG: store [[ST]]* [[VAR0:%.+]], [[ST]]** [[CBP0]]
// CK21-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21-DAG: [[SEC0]] = getelementptr {{.*}}[[ST]]* [[VAR0]], i{{.+}} 0, i{{.+}} 0
// CK21-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK21-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK21-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[ST]]**
// CK21-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK21-DAG: store [[ST]]* [[VAR0]], [[ST]]** [[CBP1]]
// CK21-DAG: store i32* [[SEC0]], i32** [[CP1]]
// CK21-DAG: store i[[Z]] {{.+}}, i[[Z]]* [[S1]]
// CK21-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK21-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
// CK21-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 2
// CK21-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [[ST]]**
// CK21-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to i32**
// CK21-DAG: store [[ST]]* [[VAR2:%.+]], [[ST]]** [[CBP2]]
// CK21-DAG: store i32* [[SEC2:%.+]], i32** [[CP2]]
// CK21-DAG: store i[[Z]] {{.+}}, i[[Z]]* [[S2]]
// CK21-DAG: [[SEC2]] = getelementptr {{.*}}[[ST]]* [[VAR2]], i{{.+}} 0, i{{.+}} 1
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK21: call void [[CALL05:@.+]]([[ST]]* {{[^,]+}})
#pragma omp target map(A, A2)
{
A += 1;
A2 += 1;
}
return A;
}
};
int explicit_maps_template_args_and_members(int a){
CC<123,int> c;
return c.foo(a);
}
// CK21: define {{.+}}[[CALL00]]
// CK21: define {{.+}}[[CALL01]]
// CK21: define {{.+}}[[CALL02]]
// CK21: define {{.+}}[[CALL03]]
// CK21: define {{.+}}[[CALL04]]
// CK21: define {{.+}}[[CALL05]]
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK22 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK22 --check-prefix CK22-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK22 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK22 --check-prefix CK22-64
// RUN: %clang_cc1 -DCK22 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK22 --check-prefix CK22-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK22 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK22 --check-prefix CK22-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK22 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY21 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK22 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY21 %s
// RUN: %clang_cc1 -DCK22 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY21 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK22 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY21 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY21-NOT: {{__kmpc|__tgt}}
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
#ifdef CK22
// CK22-DAG: [[ST:%.+]] = type { float }
// CK22-DAG: [[STT:%.+]] = type { i32 }
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE00:@.+]] = private {{.*}}constant [1 x i[[Z:64|32]]] [i[[Z:64|32]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE00:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE01:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 400]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE01:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE02:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] {{8|4}}]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE02:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE03:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 16]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE03:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE04:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 20]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE04:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE05:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE05:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE06:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 400]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE06:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE07:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] {{8|4}}]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE07:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE08:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 16]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE08:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE09:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 20]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE09:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE10:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE10:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE11:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 400]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE11:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE12:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] {{8|4}}]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE12:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE13:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 16]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE13:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK22-LABEL: @.__omp_offloading_{{.*}}explicit_maps_globals{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: [[SIZE14:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 20]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22: [[MTYPE14:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
int a;
int c[100];
int *d;
struct ST {
float fa;
};
ST sa ;
ST sc[100];
ST *sd;
template<typename T>
struct STT {
T fa;
};
STT<int> sta ;
STT<int> stc[100];
STT<int> *std;
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK22-LABEL: explicit_maps_globals{{.*}}(
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
int explicit_maps_globals(void){
// Region 00
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE00]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE00]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK22-DAG: store i32* @a, i32** [[CBP0]]
// CK22-DAG: store i32* @a, i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: call void [[CALL00:@.+]](i32* {{[^,]+}})
#pragma omp target map(a)
{ a+=1; }
// Region 01
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE01]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE01]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x i32]**
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [100 x i32]**
// CK22-DAG: store [100 x i32]* @c, [100 x i32]** [[CBP0]]
// CK22-DAG: store [100 x i32]* @c, [100 x i32]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: call void [[CALL01:@.+]]([100 x i32]* {{[^,]+}})
#pragma omp target map(c)
{ c[3]+=1; }
// Region 02
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE02]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE02]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32***
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32***
// CK22-DAG: store i32** @d, i32*** [[CBP0]]
// CK22-DAG: store i32** @d, i32*** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: call void [[CALL02:@.+]](i32** {{[^,]+}})
#pragma omp target map(d)
{ d[3]+=1; }
// Region 03
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE03]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE03]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x i32]**
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK22-DAG: store [100 x i32]* @c, [100 x i32]** [[CBP0]]
// CK22-DAG: store i32* getelementptr inbounds ([100 x i32], [100 x i32]* @c, i{{.+}} 0, i{{.+}} 1), i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: call void [[CALL03:@.+]]([100 x i32]* {{[^,]+}})
#pragma omp target map(c[1:4])
{ c[3]+=1; }
// Region 04
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE04]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE04]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK22-DAG: store i32* [[RVAR0:%.+]], i32** [[CBP0]]
// CK22-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[RVAR0]] = load i32*, i32** @d
// CK22-DAG: [[SEC0]] = getelementptr {{.*}}i32* [[RVAR00:%.+]], i{{.+}} 2
// CK22-DAG: [[RVAR00]] = load i32*, i32** @d
// CK22: call void [[CALL04:@.+]](i32* {{[^,]+}})
#pragma omp target map(d[2:5])
{ d[3]+=1; }
// Region 05
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE05]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE05]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[ST]]**
// CK22-DAG: store [[ST]]* @sa, [[ST]]** [[CBP0]]
// CK22-DAG: store [[ST]]* @sa, [[ST]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: call void [[CALL05:@.+]]([[ST]]* {{[^,]+}})
#pragma omp target map(sa)
{ sa.fa+=1; }
// Region 06
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE06]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE06]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x [[ST]]]**
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [100 x [[ST]]]**
// CK22-DAG: store [100 x [[ST]]]* @sc, [100 x [[ST]]]** [[CBP0]]
// CK22-DAG: store [100 x [[ST]]]* @sc, [100 x [[ST]]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: call void [[CALL06:@.+]]([100 x [[ST]]]* {{[^,]+}})
#pragma omp target map(sc)
{ sc[3].fa+=1; }
// Region 07
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE07]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE07]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]***
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[ST]]***
// CK22-DAG: store [[ST]]** @sd, [[ST]]*** [[CBP0]]
// CK22-DAG: store [[ST]]** @sd, [[ST]]*** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: call void [[CALL07:@.+]]([[ST]]** {{[^,]+}})
#pragma omp target map(sd)
{ sd[3].fa+=1; }
// Region 08
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE08]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE08]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x [[ST]]]**
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[ST]]**
// CK22-DAG: store [100 x [[ST]]]* @sc, [100 x [[ST]]]** [[CBP0]]
// CK22-DAG: store [[ST]]* getelementptr inbounds ([100 x [[ST]]], [100 x [[ST]]]* @sc, i{{.+}} 0, i{{.+}} 1), [[ST]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: call void [[CALL08:@.+]]([100 x [[ST]]]* {{[^,]+}})
#pragma omp target map(sc[1:4])
{ sc[3].fa+=1; }
// Region 09
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE09]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE09]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[ST]]**
// CK22-DAG: store [[ST]]* [[RVAR0:%.+]], [[ST]]** [[CBP0]]
// CK22-DAG: store [[ST]]* [[SEC0:%.+]], [[ST]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[RVAR0]] = load [[ST]]*, [[ST]]** @sd
// CK22-DAG: [[SEC0]] = getelementptr {{.*}}[[ST]]* [[RVAR00:%.+]], i{{.+}} 2
// CK22-DAG: [[RVAR00]] = load [[ST]]*, [[ST]]** @sd
// CK22: call void [[CALL09:@.+]]([[ST]]* {{[^,]+}})
#pragma omp target map(sd[2:5])
{ sd[3].fa+=1; }
// Region 10
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE10]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE10]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[STT]]**
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[STT]]**
// CK22-DAG: store [[STT]]* @sta, [[STT]]** [[CBP0]]
// CK22-DAG: store [[STT]]* @sta, [[STT]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: call void [[CALL10:@.+]]([[STT]]* {{[^,]+}})
#pragma omp target map(sta)
{ sta.fa+=1; }
// Region 11
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE11]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE11]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x [[STT]]]**
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [100 x [[STT]]]**
// CK22-DAG: store [100 x [[STT]]]* @stc, [100 x [[STT]]]** [[CBP0]]
// CK22-DAG: store [100 x [[STT]]]* @stc, [100 x [[STT]]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: call void [[CALL11:@.+]]([100 x [[STT]]]* {{[^,]+}})
#pragma omp target map(stc)
{ stc[3].fa+=1; }
// Region 12
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE12]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE12]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[STT]]***
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[STT]]***
// CK22-DAG: store [[STT]]** @std, [[STT]]*** [[CBP0]]
// CK22-DAG: store [[STT]]** @std, [[STT]]*** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: call void [[CALL12:@.+]]([[STT]]** {{[^,]+}})
#pragma omp target map(std)
{ std[3].fa+=1; }
// Region 13
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE13]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE13]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x [[STT]]]**
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[STT]]**
// CK22-DAG: store [100 x [[STT]]]* @stc, [100 x [[STT]]]** [[CBP0]]
// CK22-DAG: store [[STT]]* getelementptr inbounds ([100 x [[STT]]], [100 x [[STT]]]* @stc, i{{.+}} 0, i{{.+}} 1), [[STT]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22: call void [[CALL13:@.+]]([100 x [[STT]]]* {{[^,]+}})
#pragma omp target map(stc[1:4])
{ stc[3].fa+=1; }
// Region 14
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK22-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE14]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE14]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK22-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK22-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK22-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK22-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[STT]]**
// CK22-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[STT]]**
// CK22-DAG: store [[STT]]* [[RVAR0:%.+]], [[STT]]** [[CBP0]]
// CK22-DAG: store [[STT]]* [[SEC0:%.+]], [[STT]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK22-DAG: [[RVAR0]] = load [[STT]]*, [[STT]]** @std
// CK22-DAG: [[SEC0]] = getelementptr {{.*}}[[STT]]* [[RVAR00:%.+]], i{{.+}} 2
// CK22-DAG: [[RVAR00]] = load [[STT]]*, [[STT]]** @std
// CK22: call void [[CALL14:@.+]]([[STT]]* {{[^,]+}})
#pragma omp target map(std[2:5])
{ std[3].fa+=1; }
return 0;
}
// CK22: define {{.+}}[[CALL00]]
// CK22: define {{.+}}[[CALL01]]
// CK22: define {{.+}}[[CALL02]]
// CK22: define {{.+}}[[CALL03]]
// CK22: define {{.+}}[[CALL04]]
// CK22: define {{.+}}[[CALL05]]
// CK22: define {{.+}}[[CALL06]]
// CK22: define {{.+}}[[CALL07]]
// CK22: define {{.+}}[[CALL08]]
// CK22: define {{.+}}[[CALL09]]
// CK22: define {{.+}}[[CALL10]]
// CK22: define {{.+}}[[CALL11]]
// CK22: define {{.+}}[[CALL12]]
// CK22: define {{.+}}[[CALL13]]
// CK22: define {{.+}}[[CALL14]]
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -std=c++11 -DCK23 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK23 --check-prefix CK23-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -std=c++11 -DCK23 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -std=c++11 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK23 --check-prefix CK23-64
// RUN: %clang_cc1 -std=c++11 -DCK23 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK23 --check-prefix CK23-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -std=c++11 -DCK23 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -std=c++11 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK23 --check-prefix CK23-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -std=c++11 -DCK23 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY22 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -std=c++11 -DCK23 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -std=c++11 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY22 %s
// RUN: %clang_cc1 -std=c++11 -DCK23 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY22 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -std=c++11 -DCK23 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -std=c++11 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY22 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY22-NOT: {{__kmpc|__tgt}}
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
#ifdef CK23
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK23-LABEL: @.__omp_offloading_{{.*}}explicit_maps_inside_captured{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23: [[SIZE00:@.+]] = private {{.*}}constant [1 x i[[Z:64|32]]] [i[[Z:64|32]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK23: [[MTYPE00:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK23-LABEL: @.__omp_offloading_{{.*}}explicit_maps_inside_captured{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23: [[SIZE01:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK23: [[MTYPE01:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK23-LABEL: @.__omp_offloading_{{.*}}explicit_maps_inside_captured{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23: [[SIZE02:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 400]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK23: [[MTYPE02:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK23-LABEL: @.__omp_offloading_{{.*}}explicit_maps_inside_captured{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23: [[SIZE03:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] {{8|4}}]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK23: [[MTYPE03:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK23-LABEL: @.__omp_offloading_{{.*}}explicit_maps_inside_captured{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23: [[SIZE04:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 16]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK23: [[MTYPE04:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK23-LABEL: @.__omp_offloading_{{.*}}explicit_maps_inside_captured{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23: [[SIZE05:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 16]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK23: [[MTYPE05:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK23-LABEL: explicit_maps_inside_captured{{.*}}(
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
int explicit_maps_inside_captured(int a){
float b;
float c[100];
float *d;
// CK23: call void @{{.*}}explicit_maps_inside_captured{{.*}}([[SA:%.+]]* {{.*}})
// CK23: define {{.*}}explicit_maps_inside_captured{{.*}}
[&](void){
// Region 00
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK23-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE00]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE00]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK23-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK23-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK23-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK23-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK23-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK23-DAG: store i32* [[VAR0:%.+]], i32** [[CBP0]]
// CK23-DAG: store i32* [[VAR00:%.+]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23-DAG: [[VAR0]] = load i32*, i32** [[CAP0:%[^,]+]]
// CK23-DAG: [[CAP0]] = getelementptr inbounds [[SA]], [[SA]]
// CK23-DAG: [[VAR00]] = load i32*, i32** [[CAP00:%[^,]+]]
// CK23-DAG: [[CAP00]] = getelementptr inbounds [[SA]], [[SA]]
// CK23: call void [[CALL00:@.+]](i32* {{[^,]+}})
#pragma omp target map(a)
{ a+=1; }
// Region 01
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK23-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE01]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE01]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK23-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK23-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK23-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK23-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to float**
// CK23-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to float**
// CK23-DAG: store float* [[VAR0:%.+]], float** [[CBP0]]
// CK23-DAG: store float* [[VAR00:%.+]], float** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23-DAG: [[VAR0]] = load float*, float** [[CAP0:%[^,]+]]
// CK23-DAG: [[CAP0]] = getelementptr inbounds [[SA]], [[SA]]
// CK23-DAG: [[VAR00]] = load float*, float** [[CAP00:%[^,]+]]
// CK23-DAG: [[CAP00]] = getelementptr inbounds [[SA]], [[SA]]
// CK23: call void [[CALL01:@.+]](float* {{[^,]+}})
#pragma omp target map(b)
{ b+=1; }
// Region 02
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK23-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE02]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE02]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK23-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK23-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK23-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK23-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x float]**
// CK23-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [100 x float]**
// CK23-DAG: store [100 x float]* [[VAR0:%.+]], [100 x float]** [[CBP0]]
// CK23-DAG: store [100 x float]* [[VAR00:%.+]], [100 x float]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23-DAG: [[VAR0]] = load [100 x float]*, [100 x float]** [[CAP0:%[^,]+]]
// CK23-DAG: [[CAP0]] = getelementptr inbounds [[SA]], [[SA]]
// CK23-DAG: [[VAR00]] = load [100 x float]*, [100 x float]** [[CAP00:%[^,]+]]
// CK23-DAG: [[CAP00]] = getelementptr inbounds [[SA]], [[SA]]
// CK23: call void [[CALL02:@.+]]([100 x float]* {{[^,]+}})
#pragma omp target map(c)
{ c[3]+=1; }
// Region 03
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK23-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE03]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE03]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK23-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK23-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK23-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK23-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to float***
// CK23-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to float***
// CK23-DAG: store float** [[VAR0:%.+]], float*** [[CBP0]]
// CK23-DAG: store float** [[VAR00:%.+]], float*** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23-DAG: [[VAR0]] = load float**, float*** [[CAP0:%[^,]+]]
// CK23-DAG: [[CAP0]] = getelementptr inbounds [[SA]], [[SA]]
// CK23-DAG: [[VAR00]] = load float**, float*** [[CAP00:%[^,]+]]
// CK23-DAG: [[CAP00]] = getelementptr inbounds [[SA]], [[SA]]
// CK23: call void [[CALL03:@.+]](float** {{[^,]+}})
#pragma omp target map(d)
{ d[3]+=1; }
// Region 04
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK23-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE04]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE04]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK23-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK23-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK23-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK23-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [100 x float]**
// CK23-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to float**
// CK23-DAG: store [100 x float]* [[VAR0:%.+]], [100 x float]** [[CBP0]]
// CK23-DAG: store float* [[SEC0:%.+]], float** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23-DAG: [[SEC0]] = getelementptr {{.*}}[100 x float]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 2
// CK23-DAG: [[VAR0]] = load [100 x float]*, [100 x float]** [[CAP0:%[^,]+]]
// CK23-DAG: [[CAP0]] = getelementptr inbounds [[SA]], [[SA]]
// CK23-DAG: [[VAR00]] = load [100 x float]*, [100 x float]** [[CAP00:%[^,]+]]
// CK23-DAG: [[CAP00]] = getelementptr inbounds [[SA]], [[SA]]
// CK23: call void [[CALL04:@.+]]([100 x float]* {{[^,]+}})
#pragma omp target map(c[2:4])
{ c[3]+=1; }
// Region 05
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK23-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE05]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE05]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK23-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK23-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK23-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK23-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to float**
// CK23-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to float**
// CK23-DAG: store float* [[RVAR0:%.+]], float** [[CBP0]]
// CK23-DAG: store float* [[SEC0:%.+]], float** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK23-DAG: [[RVAR0]] = load float*, float** [[VAR0:%[^,]+]]
// CK23-DAG: [[SEC0]] = getelementptr {{.*}}float* [[RVAR00:%.+]], i{{.+}} 2
// CK23-DAG: [[RVAR00]] = load float*, float** [[VAR00:%[^,]+]]
// CK23-DAG: [[VAR0]] = load float**, float*** [[CAP0:%[^,]+]]
// CK23-DAG: [[CAP0]] = getelementptr inbounds [[SA]], [[SA]]
// CK23-DAG: [[VAR00]] = load float**, float*** [[CAP00:%[^,]+]]
// CK23-DAG: [[CAP00]] = getelementptr inbounds [[SA]], [[SA]]
// CK23: call void [[CALL05:@.+]](float* {{[^,]+}})
#pragma omp target map(d[2:4])
{ d[3]+=1; }
}();
return b;
}
// CK23: define {{.+}}[[CALL00]]
// CK23: define {{.+}}[[CALL01]]
// CK23: define {{.+}}[[CALL02]]
// CK23: define {{.+}}[[CALL03]]
// CK23: define {{.+}}[[CALL04]]
// CK23: define {{.+}}[[CALL05]]
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK24 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK24 --check-prefix CK24-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK24 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK24 --check-prefix CK24-64
// RUN: %clang_cc1 -DCK24 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK24 --check-prefix CK24-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK24 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK24 --check-prefix CK24-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK24 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY23 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK24 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY23 %s
// RUN: %clang_cc1 -DCK24 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY23 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK24 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY23 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY23-NOT: {{__kmpc|__tgt}}
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
#ifdef CK24
// CK24-DAG: [[SC:%.+]] = type { i32, [[SB:%.+]], [[SB:%.+]]*, [10 x i32] }
// CK24-DAG: [[SB]] = type { i32, [[SA:%.+]], [10 x [[SA:%.+]]], [10 x [[SA:%.+]]*], [[SA:%.+]]* }
// CK24-DAG: [[SA]] = type { i32, [[SA]]*, [10 x i32] }
struct SA{
int a;
struct SA *p;
int b[10];
};
struct SB{
int a;
struct SA s;
struct SA sa[10];
struct SA *sp[10];
struct SA *p;
};
struct SC{
int a;
struct SB s;
struct SB *p;
int b[10];
};
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE01:@.+]] = private {{.*}}constant [2 x i64] [i64 32, i64 281474976710659]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE13:@.+]] = private {{.*}}constant [2 x i64] [i64 32, i64 281474976710659]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE14:@.+]] = private {{.*}}constant [2 x i64] [i64 32, i64 281474976710659]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE15:@.+]] = private {{.*}}constant [2 x i64] [i64 32, i64 281474976710659]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE16:@.+]] = private {{.*}}constant [2 x i64] [i64 32, i64 281474976710659]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE17:@.+]] = private {{.*}}constant [2 x i64] [i64 32, i64 281474976710675]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE18:@.+]] = private {{.*}}constant [2 x i64] [i64 32, i64 281474976710659]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE19:@.+]] = private {{.*}}constant [3 x i64] [i64 32, i64 281474976710659, i64 281474976710675]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE20:@.+]] = private {{.*}}constant [2 x i64] [i64 32, i64 281474976710675]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE21:@.+]] = private {{.*}}constant [3 x i64] [i64 32, i64 281474976710659, i64 281474976710675]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE22:@.+]] = private {{.*}}constant [2 x i64] [i64 32, i64 281474976710659]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE23:@.+]] = private {{.*}}constant [3 x i64] [i64 32, i64 281474976710659, i64 281474976710675]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK24-LABEL: @.__omp_offloading_{{.*}}explicit_maps_struct_fields{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24: [[MTYPE24:@.+]] = private {{.*}}constant [4 x i64] [i64 32, i64 281474976710672, i64 16, i64 19]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-LABEL: explicit_maps_struct_fields
int explicit_maps_struct_fields(int a){
SC s;
SC *p;
// Region 01
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE01]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[[SC]]* [[VAR0]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SC]]**
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK24-DAG: store [[SC]]* [[VAR0]], [[SC]]** [[CBP1]]
// CK24-DAG: store i32* [[SEC0]], i32** [[CP1]]
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24: call void [[CALL01:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(s.a)
{ s.a++; }
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
//
// Same thing but starting from a pointer.
//
// Region 13
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE13]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[[SC]]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SC]]**
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK24-DAG: store [[SC]]* [[VAR0]], [[SC]]** [[CBP1]]
// CK24-DAG: store i32* [[SEC0]], i32** [[CP1]]
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[VAR0]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24: call void [[CALL13:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(p->a)
{ p->a++; }
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// Region 14
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE14]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[SA]]**
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store [[SA]]* [[SEC0:%.+]], [[SA]]** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[[SB]]* [[SEC00:%[^,]+]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[SEC00]] = getelementptr {{.*}}[[SC]]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SC]]**
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to [[SA]]**
// CK24-DAG: store [[SC]]* [[VAR0]], [[SC]]** [[CBP1]]
// CK24-DAG: store [[SA]]* [[SEC0]], [[SA]]** [[CP1]]
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[VAR0]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24: call void [[CALL14:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(p->s.s)
{ p->a++; }
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// Region 15
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE15]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[[SA]]* [[SEC00:%[^,]+]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[SEC00]] = getelementptr {{.*}}[[SB]]* [[SEC000:%[^,]+]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[SEC000]] = getelementptr {{.*}}[[SC]]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SC]]**
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK24-DAG: store [[SC]]* [[VAR0]], [[SC]]** [[CBP1]]
// CK24-DAG: store i32* [[SEC0]], i32** [[CP1]]
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[VAR0]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24: call void [[CALL15:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(p->s.s.a)
{ p->a++; }
// Region 16
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE16]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[10 x i32]* [[SEC00:%[^,]+]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[SEC00]] = getelementptr {{.*}}[[SC]]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 3
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SC]]**
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK24-DAG: store [[SC]]* [[VAR0]], [[SC]]** [[CBP1]]
// CK24-DAG: store i32* [[SEC0]], i32** [[CP1]]
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[VAR0]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24: call void [[CALL16:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(p->b[:5])
{ p->a++; }
// Region 17
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE17]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[SB]]***
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store [[SB]]** [[SEC0:%.+]], [[SB]]*** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[[SC]]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SB]]***
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to [[SB]]**
// CK24-DAG: store [[SB]]** [[SEC0]], [[SB]]*** [[CBP1]]
// CK24-DAG: store [[SB]]* [[SEC1:%.+]], [[SB]]** [[CP1]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC1]] = getelementptr {{.*}}[[SB]]* [[SEC11:%[^,]+]], i{{.+}} 0
// CK24-DAG: [[SEC11]] = load [[SB]]*, [[SB]]** [[SEC111:%[^,]+]],
// CK24-DAG: [[SEC111]] = getelementptr {{.*}}[[SC]]* [[VAR000:%.+]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[VAR0]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR000]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24: call void [[CALL17:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(p->p[:5])
{ p->a++; }
// Region 18
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE18]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[[SA]]* [[SEC00:%[^,]+]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[SEC00]] = getelementptr {{.*}}[10 x [[SA]]]* [[SEC000:%[^,]+]], i{{.+}} 0, i{{.+}} 3
// CK24-DAG: [[SEC000]] = getelementptr {{.*}}[[SB]]* [[SEC0000:%[^,]+]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[SEC0000]] = getelementptr {{.*}}[[SC]]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SC]]**
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK24-DAG: store [[SC]]* [[VAR0]], [[SC]]** [[CBP1]]
// CK24-DAG: store i32* [[SEC0]], i32** [[CP1]]
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[VAR0]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24: call void [[CALL18:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(p->s.sa[3].a)
{ p->a++; }
// Region 19
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE19]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[SA]]***
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store [[SA]]** [[SEC0:%.+]], [[SA]]*** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[10 x [[SA]]*]* [[SEC00:%[^,]+]], i{{.+}} 0, i{{.+}} 3
// CK24-DAG: [[SEC00]] = getelementptr {{.*}}[[SB]]* [[SEC000:%[^,]+]], i{{.+}} 0, i{{.+}} 3
// CK24-DAG: [[SEC000]] = getelementptr {{.*}}[[SC]]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SC]]**
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to [[SA]]***
// CK24-DAG: store [[SC]]* [[VAR0]], [[SC]]** [[CBP1]]
// CK24-DAG: store [[SA]]** [[SEC0]], [[SA]]*** [[CP1]]
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S1]]
// CK24-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [[SA]]***
// CK24-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to i32**
// CK24-DAG: store [[SA]]** [[SEC0]], [[SA]]*** [[CBP2]]
// CK24-DAG: store i32* [[SEC1:%.+]], i32** [[CP2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC1]] = getelementptr {{.*}}[[SA]]* [[SEC11:%[^,]+]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[SEC11]] = load [[SA]]*, [[SA]]** [[SEC111:%[^,]+]],
// CK24-DAG: [[SEC111]] = getelementptr {{.*}}[10 x [[SA]]*]* [[SEC1111:%[^,]+]], i{{.+}} 0, i{{.+}} 3
// CK24-DAG: [[SEC1111]] = getelementptr {{.*}}[[SB]]* [[SEC11111:%[^,]+]], i{{.+}} 0, i{{.+}} 3
// CK24-DAG: [[SEC11111]] = getelementptr {{.*}}[[SC]]* [[VAR000:%.+]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[VAR0]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR000]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24: call void [[CALL19:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(p->s.sp[3]->a)
{ p->a++; }
// Region 20
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE20]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[SB]]***
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store [[SB]]** [[SEC0:%.+]], [[SB]]*** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[[SC]]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SB]]***
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK24-DAG: store [[SB]]** [[SEC0]], [[SB]]*** [[CBP1]]
// CK24-DAG: store i32* [[SEC1:%.+]], i32** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC1]] = getelementptr {{.*}}[[SB]]* [[SEC11:%[^,]+]], i{{.+}} 0
// CK24-DAG: [[SEC11]] = load [[SB]]*, [[SB]]** [[SEC111:%[^,]+]],
// CK24-DAG: [[SEC111]] = getelementptr {{.*}}[[SC]]* [[VAR000:%.+]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[VAR0]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR000]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24: call void [[CALL20:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(p->p->a)
{ p->a++; }
// Region 21
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE21]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[SA]]***
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store [[SA]]** [[SEC0:%.+]], [[SA]]*** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[[SB]]* [[SEC00:[^,]+]], i{{.+}} 0, i{{.+}} 4
// CK24-DAG: [[SEC00]] = getelementptr {{.*}}[[SC]]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SC]]**
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to [[SA]]***
// CK24-DAG: store [[SC]]* [[VAR0]], [[SC]]** [[CBP1]]
// CK24-DAG: store [[SA]]** [[SEC0]], [[SA]]*** [[CP1]]
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S1]]
// CK24-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [[SA]]***
// CK24-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to i32**
// CK24-DAG: store [[SA]]** [[SEC0]], [[SA]]*** [[CBP2]]
// CK24-DAG: store i32* [[SEC1:%.+]], i32** [[CP2]]
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC1]] = getelementptr {{.*}}[[SA]]* [[SEC11:%[^,]+]], i{{.+}} 0
// CK24-DAG: [[SEC11]] = load [[SA]]*, [[SA]]** [[SEC111:%[^,]+]],
// CK24-DAG: [[SEC111]] = getelementptr {{.*}}[[SB]]* [[SEC1111:[^,]+]], i{{.+}} 0, i{{.+}} 4
// CK24-DAG: [[SEC1111]] = getelementptr {{.*}}[[SC]]* [[VAR000:%.+]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[VAR0]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR000]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24: call void [[CALL21:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(p->s.p->a)
{ p->a++; }
// Region 22
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE22]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[10 x i32]* [[SEC00:%[^,]+]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[SEC00]] = getelementptr {{.*}}[[SA]]* [[SEC000:%[^,]+]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[SEC000]] = getelementptr {{.*}}[[SB]]* [[SEC0000:%[^,]+]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[SEC0000]] = getelementptr {{.*}}[[SC]]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SC]]**
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK24-DAG: store [[SC]]* [[VAR0]], [[SC]]** [[CBP1]]
// CK24-DAG: store i32* [[SEC0]], i32** [[CP1]]
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[VAR0]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24: call void [[CALL22:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(p->s.s.b[:2])
{ p->a++; }
// Region 23
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE23]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[SA]]***
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store [[SA]]** [[SEC0:%.+]], [[SA]]*** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[[SB]]* [[SEC00:%[^,]+]], i{{.+}} 0, i{{.+}} 4
// CK24-DAG: [[SEC00]] = getelementptr {{.*}}[[SC]]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SC]]**
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to [[SA]]***
// CK24-DAG: store [[SC]]* [[VAR0]], [[SC]]** [[CBP1]]
// CK24-DAG: store [[SA]]** [[SEC0]], [[SA]]*** [[CP1]]
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S1]]
// CK24-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [[SA]]***
// CK24-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to i32**
// CK24-DAG: store [[SA]]** [[SEC0]], [[SA]]*** [[CBP2]]
// CK24-DAG: store i32* [[SEC1:%.+]], i32** [[CP2]]
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC1]] = getelementptr {{.*}}[10 x i32]* [[SEC11:%[^,]+]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[SEC11]] = getelementptr {{.*}}[[SA]]* [[SEC111:%[^,]+]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[SEC111]] = load [[SA]]*, [[SA]]** [[SEC1111:%[^,]+]],
// CK24-DAG: [[SEC1111]] = getelementptr {{.*}}[[SB]]* [[SEC11111:%[^,]+]], i{{.+}} 0, i{{.+}} 4
// CK24-DAG: [[SEC11111]] = getelementptr {{.*}}[[SC]]* [[VAR000:%.+]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[VAR0]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR000]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24: call void [[CALL23:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(p->s.p->b[:2])
{ p->a++; }
// Region 24
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 4, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[sz:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[4 x i{{.+}}]* [[MTYPE24]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK24-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SC]]**
// CK24-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[SB]]***
// CK24-DAG: store [[SC]]* [[VAR0:%.+]], [[SC]]** [[CBP0]]
// CK24-DAG: store [[SB]]** [[SEC0:%.+]], [[SB]]*** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{%.+}}, i[[sz]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC0]] = getelementptr {{.*}}[[SC]]* [[VAR00:%.+]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SB]]***
// CK24-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to [[SA]]***
// CK24-DAG: store [[SB]]** [[SEC0]], [[SB]]*** [[CBP1]]
// CK24-DAG: store [[SA]]** [[SEC1:%.+]], [[SA]]*** [[CP1]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC1]] = getelementptr {{.*}}[[SB]]* [[SEC11:%[^,]+]], i{{.+}} 0, i{{.+}} 4
// CK24-DAG: [[SEC11]] = load [[SB]]*, [[SB]]** [[SEC111:%[^,]+]],
// CK24-DAG: [[SEC111]] = getelementptr {{.*}}[[SC]]* [[VAR000:%.+]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 2
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to [[SA]]***
// CK24-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to [[SA]]***
// CK24-DAG: store [[SA]]** [[SEC1]], [[SA]]*** [[CBP2]]
// CK24-DAG: store [[SA]]** [[SEC2:%.+]], [[SA]]*** [[CP2]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC2]] = getelementptr {{.*}}[[SA]]* [[SEC22:%[^,]+]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[SEC22]] = load [[SA]]*, [[SA]]** [[SEC222:%[^,]+]],
// CK24-DAG: [[SEC222]] = getelementptr {{.*}}[[SB]]* [[SEC2222:%[^,]+]], i{{.+}} 0, i{{.+}} 4
// CK24-DAG: [[SEC2222]] = load [[SB]]*, [[SB]]** [[SEC22222:%[^,]+]],
// CK24-DAG: [[SEC22222]] = getelementptr {{.*}}[[SC]]* [[VAR0000:%.+]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[BP3:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 3
// CK24-DAG: [[P3:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 3
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: [[S3:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 3
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK24-DAG: [[CBP3:%.+]] = bitcast i8** [[BP3]] to [[SA]]***
// CK24-DAG: [[CP3:%.+]] = bitcast i8** [[P3]] to i32**
// CK24-DAG: store [[SA]]** [[SEC2]], [[SA]]*** [[CBP3]]
// CK24-DAG: store i32* [[SEC3:%.+]], i32** [[CP3]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK24-DAG: store i[[sz]] {{.+}}, i[[sz]]* [[S3]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK24-DAG: [[SEC3]] = getelementptr {{.*}}[[SA]]* [[SEC33:%[^,]+]], i{{.+}} 0, i{{.+}} 0
// CK24-DAG: [[SEC33]] = load [[SA]]*, [[SA]]** [[SEC333:%[^,]+]],
// CK24-DAG: [[SEC333]] = getelementptr {{.*}}[[SA]]* [[SEC3333:%[^,]+]], i{{.+}} 0, i{{.+}} 1
// CK24-DAG: [[SEC3333]] = load [[SA]]*, [[SA]]** [[SEC33333:%[^,]+]],
// CK24-DAG: [[SEC33333]] = getelementptr {{.*}}[[SB]]* [[SEC333333:%[^,]+]], i{{.+}} 0, i{{.+}} 4
// CK24-DAG: [[SEC333333]] = load [[SB]]*, [[SB]]** [[SEC3333333:%[^,]+]],
// CK24-DAG: [[SEC3333333]] = getelementptr {{.*}}[[SC]]* [[VAR00000:%.+]], i{{.+}} 0, i{{.+}} 2
// CK24-DAG: [[VAR0]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR000]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR0000]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24-DAG: [[VAR00000]] = load [[SC]]*, [[SC]]** %{{.+}}
// CK24: call void [[CALL24:@.+]]([[SC]]* {{[^,]+}})
#pragma omp target map(p->p->p->p->a)
{ p->a++; }
return s.a;
}
// CK24: define {{.+}}[[CALL01]]
// CK24: define {{.+}}[[CALL13]]
// CK24: define {{.+}}[[CALL14]]
// CK24: define {{.+}}[[CALL15]]
// CK24: define {{.+}}[[CALL16]]
// CK24: define {{.+}}[[CALL17]]
// CK24: define {{.+}}[[CALL18]]
// CK24: define {{.+}}[[CALL19]]
// CK24: define {{.+}}[[CALL20]]
// CK24: define {{.+}}[[CALL21]]
// CK24: define {{.+}}[[CALL22]]
// CK24: define {{.+}}[[CALL23]]
// CK24: define {{.+}}[[CALL24]]
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK25 -std=c++11 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK25 --check-prefix CK25-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK25 -std=c++11 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -std=c++11 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK25 --check-prefix CK25-64
// RUN: %clang_cc1 -DCK25 -std=c++11 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK25 --check-prefix CK25-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK25 -std=c++11 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -std=c++11 -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK25 --check-prefix CK25-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK25 -std=c++11 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY24 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK25 -std=c++11 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -std=c++11 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY24 %s
// RUN: %clang_cc1 -DCK25 -std=c++11 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY24 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK25 -std=c++11 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -std=c++11 -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY24 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY24-NOT: {{__kmpc|__tgt}}
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
#ifdef CK25
// CK25: [[ST:%.+]] = type { i32, float }
// CK25: [[CA00:%.+]] = type { [[ST]]* }
// CK25: [[CA01:%.+]] = type { i32* }
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK25-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK25: [[MTYPE00:@.+]] = private {{.*}}constant [2 x i64] [i64 32, i64 281474976710657]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK25-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK25: [[SIZE01:@.+]] = private {{.*}}constant [1 x i[[Z:64|32]]] [i[[Z:64|32]] 4]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK25: [[MTYPE01:@.+]] = private {{.*}}constant [1 x i64] [i64 33]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK25-LABEL: explicit_maps_with_inner_lambda{{.*}}(
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
template <int X, typename T>
struct CC {
T A;
float B;
int foo(T arg) {
// Region 00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK25-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE00]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK25-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK25-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK25-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK25-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK25-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK25-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK25-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
// CK25-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK25-DAG: store [[ST]]* [[VAR0:%.+]], [[ST]]** [[CBP0]]
// CK25-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK25-DAG: store i[[Z]] {{%.+}}, i[[Z]]* [[S0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK25-DAG: [[SEC0]] = getelementptr {{.*}}[[ST]]* [[VAR0:%.+]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK25-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK25-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
// CK25-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK25-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[ST]]**
// CK25-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK25-DAG: store [[ST]]* [[VAR0]], [[ST]]** [[CBP1]]
// CK25-DAG: store i32* [[SEC0]], i32** [[CP1]]
// CK25-DAG: store i[[Z]] {{.+}}, i[[Z]]* [[S1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK25: call void [[CALL00:@.+]]([[ST]]* {{[^,]+}})
#pragma omp target map(to:A)
{
[&]() {
A += 1;
}();
}
// Region 01
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK25-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE01]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE01]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK25-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK25-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK25-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK25-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK25-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK25-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK25-DAG: store i32* [[VAR0:%.+]], i32** [[CBP0]]
// CK25-DAG: store i32* [[VAR0]], i32** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK25: call void [[CALL01:@.+]](i32* {{[^,]+}})
#pragma omp target map(to:arg)
{
[&]() {
arg += 1;
}();
}
return A+arg;
}
};
int explicit_maps_with_inner_lambda(int a){
CC<123,int> c;
return c.foo(a);
}
// CK25: define {{.+}}[[CALL00]]([[ST]]* [[VAL:%.+]])
// CK25: store [[ST]]* [[VAL]], [[ST]]** [[VALADDR:%[^,]+]],
// CK25: [[VAL1:%.+]] = load [[ST]]*, [[ST]]** [[VALADDR]],
// CK25: [[VALADDR1:%.+]] = getelementptr inbounds [[CA00]], [[CA00]]* [[CA:%[^,]+]], i32 0, i32 0
// CK25: store [[ST]]* [[VAL1]], [[ST]]** [[VALADDR1]],
// CK25: call void {{.*}}[[LAMBDA:@.+]]{{.*}}([[CA00]]* [[CA]])
// CK25: define {{.+}}[[LAMBDA]]
// CK25: define {{.+}}[[CALL01]](i32* {{.*}}[[VAL:%.+]])
// CK25: store i32* [[VAL]], i32** [[VALADDR:%[^,]+]],
// CK25: [[VAL1:%.+]] = load i32*, i32** [[VALADDR]],
// CK25: [[VALADDR1:%.+]] = getelementptr inbounds [[CA01]], [[CA01]]* [[CA:%[^,]+]], i32 0, i32 0
// CK25: store i32* [[VAL1]], i32** [[VALADDR1]],
Fix for PR30632: Name mangling issue. There was a bug in the implementation of captured statements. If it has a lambda expression in it and the same lambda expression is used outside the captured region, clang produced an error: ``` error: definition with same mangled name as another definition ``` Here is an example: ``` struct A { template <typename L> void g(const L&) { } }; template<typename T> void f() { { A().g([](){}); } A().g([](){}); } int main() { f<void>(); } ``` Error report: ``` main.cpp:3:10: error: definition with same mangled name as another definition void g(const L&) { } ^ main.cpp:3:10: note: previous definition is here ``` Patch fixes this bug. llvm-svn: 284229
2016-10-14 20:43:59 +08:00
// CK25: call void {{.*}}[[LAMBDA2:@.+]]{{.*}}([[CA01]]* [[CA]])
// CK25: define {{.+}}[[LAMBDA2]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK26 -std=c++11 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK26 --check-prefix CK26-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK26 -std=c++11 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -std=c++11 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK26 --check-prefix CK26-64
// RUN: %clang_cc1 -DCK26 -std=c++11 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK26 --check-prefix CK26-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK26 -std=c++11 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -std=c++11 -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK26 --check-prefix CK26-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK26 -std=c++11 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY25 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK26 -std=c++11 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -std=c++11 -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY25 %s
// RUN: %clang_cc1 -DCK26 -std=c++11 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY25 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK26 -std=c++11 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -std=c++11 -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY25 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY25-NOT: {{__kmpc|__tgt}}
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
#ifdef CK26
// CK26: [[ST:%.+]] = type { i32, float*, i32, float* }
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK26-LABEL: @.__omp_offloading_{{.*}}CC{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26: [[SIZE00:@.+]] = private {{.*}}constant [2 x i[[Z:64|32]]] [i[[Z:64|32]] {{32|16}}, i[[Z:64|32]] 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK26: [[MTYPE00:@.+]] = private {{.*}}constant [2 x i64] [i64 547, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK26-LABEL: @.__omp_offloading_{{.*}}CC{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26: [[SIZE01:@.+]] = private {{.*}}constant [2 x i[[Z]]] [i[[Z]] {{32|16}}, i[[Z]] 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK26: [[MTYPE01:@.+]] = private {{.*}}constant [2 x i64] [i64 547, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK26-LABEL: @.__omp_offloading_{{.*}}CC{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26: [[SIZE02:@.+]] = private {{.*}}constant [2 x i[[Z]]] [i[[Z]] {{32|16}}, i[[Z]] 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK26: [[MTYPE02:@.+]] = private {{.*}}constant [2 x i64] [i64 547, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK26-LABEL: @.__omp_offloading_{{.*}}CC{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26: [[SIZE03:@.+]] = private {{.*}}constant [2 x i[[Z]]] [i[[Z]] {{32|16}}, i[[Z]] 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK26: [[MTYPE03:@.+]] = private {{.*}}constant [2 x i64] [i64 547, i64 35]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK26-LABEL: explicit_maps_with_private_class_members{{.*}}(
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
struct CC {
int fA;
float &fB;
int pA;
float &pB;
CC(float &B) : fB(B), pB(B) {
// CK26: call {{.*}}@__kmpc_fork_call{{.*}} [[OUTCALL:@.+]] to void (i32*, i32*, ...)*
// define {{.*}}void [[OUTCALL]]
#pragma omp parallel firstprivate(fA,fB) private(pA,pB)
{
// Region 00
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK26-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[SIZE00]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE00]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK26-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK26-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK26-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK26-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
// CK26-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[ST]]**
// CK26-DAG: store [[ST]]* [[VAR0:%.+]], [[ST]]** [[CBP0]]
// CK26-DAG: store [[ST]]* [[VAR0]], [[ST]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK26-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK26-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i32**
// CK26-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK26-DAG: store i32* [[VAR1:%.+]], i32** [[CBP1]]
// CK26-DAG: store i32* [[SEC1:%.+]], i32** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26-DAG: [[VAR1]] = load i32*, i32** [[PVT:%.+]],
// CK26-DAG: [[SEC1]] = load i32*, i32** [[PVT]],
// CK26: call void [[CALL00:@.+]]([[ST]]* {{[^,]+}}, i32* {{[^,]+}})
#pragma omp target map(fA)
{
++fA;
}
// Region 01
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK26-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[SIZE01]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE01]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK26-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK26-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK26-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK26-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
// CK26-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[ST]]**
// CK26-DAG: store [[ST]]* [[VAR0:%.+]], [[ST]]** [[CBP0]]
// CK26-DAG: store [[ST]]* [[VAR0]], [[ST]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK26-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK26-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to float**
// CK26-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to float**
// CK26-DAG: store float* [[VAR1:%.+]], float** [[CBP1]]
// CK26-DAG: store float* [[SEC1:%.+]], float** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26-DAG: [[VAR1]] = load float*, float** [[PVT:%.+]],
// CK26-DAG: [[SEC1]] = load float*, float** [[PVT]],
// CK26: call void [[CALL01:@.+]]([[ST]]* {{[^,]+}}, float* {{[^,]+}})
#pragma omp target map(fB)
{
fB += 1.0;
}
// Region 02
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK26-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[SIZE02]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE02]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK26-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK26-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK26-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK26-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
// CK26-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[ST]]**
// CK26-DAG: store [[ST]]* [[VAR0:%.+]], [[ST]]** [[CBP0]]
// CK26-DAG: store [[ST]]* [[VAR0]], [[ST]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK26-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK26-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i32**
// CK26-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i32**
// CK26-DAG: store i32* [[VAR1:%.+]], i32** [[CBP1]]
// CK26-DAG: store i32* [[SEC1:%.+]], i32** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26-DAG: [[VAR1]] = load i32*, i32** [[PVT:%.+]],
// CK26-DAG: [[SEC1]] = load i32*, i32** [[PVT]],
// CK26: call void [[CALL02:@.+]]([[ST]]* {{[^,]+}}, i32* {{[^,]+}})
#pragma omp target map(pA)
{
++pA;
}
// Region 01
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK26-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 2, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[SIZE03]], {{.+}}getelementptr {{.+}}[2 x i{{.+}}]* [[MTYPE03]]{{.+}})
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK26-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK26-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK26-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK26-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[ST]]**
// CK26-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[ST]]**
// CK26-DAG: store [[ST]]* [[VAR0:%.+]], [[ST]]** [[CBP0]]
// CK26-DAG: store [[ST]]* [[VAR0]], [[ST]]** [[CP0]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK26-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK26-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to float**
// CK26-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to float**
// CK26-DAG: store float* [[VAR1:%.+]], float** [[CBP1]]
// CK26-DAG: store float* [[SEC1:%.+]], float** [[CP1]]
[OpenMP] Map clause codegeneration. Summary: Implement codegen for the map clause. All the new list items in 4.5 specification are supported. Fix bug in the generation of array sections that was exposed by some of the map clause tests: for pointer types the offsets have to be calculated from the pointee not the pointer. Reviewers: hfinkel, kkwli0, carlo.bertolli, arpith-jacob, ABataev Subscribers: ABataev, cfe-commits, caomhin, fraggamuffin Differential Revision: http://reviews.llvm.org/D16749 llvm-svn: 267808
2016-04-28 06:40:57 +08:00
// CK26-DAG: [[VAR1]] = load float*, float** [[PVT:%.+]],
// CK26-DAG: [[SEC1]] = load float*, float** [[PVT]],
// CK26: call void [[CALL03:@.+]]([[ST]]* {{[^,]+}}, float* {{[^,]+}})
#pragma omp target map(pB)
{
pB += 1.0;
}
}
}
int foo() {
return fA + pA;
}
};
// Make sure the private instance is used in all target regions.
// CK26: define {{.+}}[[CALL00]]({{.*}}i32*{{.*}}[[PVTARG:%.+]])
// CK26: store i32* [[PVTARG]], i32** [[PVTADDR:%.+]],
// CK26: [[ADDR:%.+]] = load i32*, i32** [[PVTADDR]],
// CK26: [[VAL:%.+]] = load i32, i32* [[ADDR]],
// CK26: add nsw i32 [[VAL]], 1
// CK26: define {{.+}}[[CALL01]]({{.*}}float*{{.*}}[[PVTARG:%.+]])
// CK26: store float* [[PVTARG]], float** [[PVTADDR:%.+]],
// CK26: [[ADDR:%.+]] = load float*, float** [[PVTADDR]],
// CK26: [[VAL:%.+]] = load float, float* [[ADDR]],
// CK26: [[EXT:%.+]] = fpext float [[VAL]] to double
// CK26: fadd double [[EXT]], 1.000000e+00
// CK26: define {{.+}}[[CALL02]]({{.*}}i32*{{.*}}[[PVTARG:%.+]])
// CK26: store i32* [[PVTARG]], i32** [[PVTADDR:%.+]],
// CK26: [[ADDR:%.+]] = load i32*, i32** [[PVTADDR]],
// CK26: [[VAL:%.+]] = load i32, i32* [[ADDR]],
// CK26: add nsw i32 [[VAL]], 1
// CK26: define {{.+}}[[CALL03]]({{.*}}float*{{.*}}[[PVTARG:%.+]])
// CK26: store float* [[PVTARG]], float** [[PVTADDR:%.+]],
// CK26: [[ADDR:%.+]] = load float*, float** [[PVTADDR]],
// CK26: [[VAL:%.+]] = load float, float* [[ADDR]],
// CK26: [[EXT:%.+]] = fpext float [[VAL]] to double
// CK26: fadd double [[EXT]], 1.000000e+00
int explicit_maps_with_private_class_members(){
float B;
CC c(B);
return c.foo();
}
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
#endif
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK27 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK27 --check-prefix CK27-64
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK27 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK27 --check-prefix CK27-64
// RUN: %clang_cc1 -DCK27 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK27 --check-prefix CK27-32
[OpenMP] Use fopenmp prefix for all options introduced by the offloading implementation. Summary: This patch changes the options used by offloading to start with -fopenmp instead of -fomp. This makes the option naming more consistent and materializes a suggestion by Richard Smith in http://reviews.llvm.org/D9888. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, ABataev Subscribers: kkwli0, cfe-commits, caomhin Differential Revision: http://reviews.llvm.org/D21841 llvm-svn: 274283
2016-07-01 05:22:08 +08:00
// RUN: %clang_cc1 -DCK27 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK27 --check-prefix CK27-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK27 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY26 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK27 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY26 %s
// RUN: %clang_cc1 -DCK27 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY26 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK27 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY26 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY26-NOT: {{__kmpc|__tgt}}
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
#ifdef CK27
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK27-LABEL: @.__omp_offloading_{{.*}}zero_size_section_and_private_maps{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK27: [[SIZE00:@.+]] = private {{.*}}constant [1 x i[[Z:64|32]]] zeroinitializer
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK27: [[MTYPE00:@.+]] = private {{.*}}constant [1 x i64] [i64 544]
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK27-LABEL: @.__omp_offloading_{{.*}}zero_size_section_and_private_maps{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK27: [[SIZE01:@.+]] = private {{.*}}constant [1 x i[[Z]]] zeroinitializer
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27: [[MTYPE01:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK27-LABEL: @.__omp_offloading_{{.*}}zero_size_section_and_private_maps{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK27: [[SIZE02:@.+]] = private {{.*}}constant [1 x i[[Z]]] zeroinitializer
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27: [[MTYPE02:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK27-LABEL: @.__omp_offloading_{{.*}}zero_size_section_and_private_maps{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK27: [[SIZE03:@.+]] = private {{.*}}constant [1 x i[[Z]]] zeroinitializer
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27: [[MTYPE03:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK27-LABEL: @.__omp_offloading_{{.*}}zero_size_section_and_private_maps{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
// CK27-LABEL: @.__omp_offloading_{{.*}}zero_size_section_and_private_maps{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27: [[SIZE05:@.+]] = private {{.*}}constant [1 x i[[Z]]] zeroinitializer
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK27: [[MTYPE05:@.+]] = private {{.*}}constant [1 x i64] [i64 544]
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK27-LABEL: @.__omp_offloading_{{.*}}zero_size_section_and_private_maps{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
// CK27-LABEL: @.__omp_offloading_{{.*}}zero_size_section_and_private_maps{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27: [[SIZE07:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 4]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK27: [[MTYPE07:@.+]] = private {{.*}}constant [1 x i64] [i64 800]
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK27-LABEL: @.__omp_offloading_{{.*}}zero_size_section_and_private_maps{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
// CK27-LABEL: @.__omp_offloading_{{.*}}zero_size_section_and_private_maps{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27: [[SIZE09:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 40]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK27: [[MTYPE09:@.+]] = private {{.*}}constant [1 x i64] [i64 673]
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK27-LABEL: zero_size_section_and_private_maps{{.*}}(
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
void zero_size_section_and_private_maps (int ii){
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// Map of a pointer.
int *pa;
// Region 00
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE00]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE00]]{{.+}})
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK27-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK27-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK27-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK27-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK27-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK27-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK27-DAG: store i32* [[VAR0:%.+]], i32** [[CBP0]]
// CK27-DAG: store i32* [[VAR0]], i32** [[CP0]]
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK27: call void [[CALL00:@.+]](i32* {{[^,]+}})
#pragma omp target
{
pa[50]++;
}
// Region 01
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE01]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE01]]{{.+}})
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK27-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK27-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK27-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK27-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK27-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK27-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK27-DAG: store i32* [[RVAR0:%.+]], i32** [[CBP0]]
// CK27-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK27-DAG: [[RVAR0]] = load i32*, i32** [[VAR0:%[^,]+]]
// CK27-DAG: [[SEC0]] = getelementptr {{.*}}i32* [[RVAR00:%.+]], i{{.+}} 0
// CK27-DAG: [[RVAR00]] = load i32*, i32** [[VAR0]]
// CK27: call void [[CALL01:@.+]](i32* {{[^,]+}})
#pragma omp target map(pa[:0])
{
pa[50]++;
}
// Region 02
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE02]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE02]]{{.+}})
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK27-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK27-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK27-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK27-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK27-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK27-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK27-DAG: store i32* [[RVAR0:%.+]], i32** [[CBP0]]
// CK27-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK27-DAG: [[RVAR0]] = load i32*, i32** [[VAR0:%[^,]+]]
// CK27-DAG: [[SEC0]] = getelementptr {{.*}}i32* [[RVAR00:%.+]], i{{.+}} 0
// CK27-DAG: [[RVAR00]] = load i32*, i32** [[VAR0]]
// CK27: call void [[CALL02:@.+]](i32* {{[^,]+}})
#pragma omp target map(pa[0:0])
{
pa[50]++;
}
// Region 03
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE03]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE03]]{{.+}})
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK27-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK27-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK27-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK27-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK27-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK27-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK27-DAG: store i32* [[RVAR0:%.+]], i32** [[CBP0]]
// CK27-DAG: store i32* [[SEC0:%.+]], i32** [[CP0]]
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
// CK27-DAG: [[RVAR0]] = load i32*, i32** [[VAR0:%[^,]+]]
// CK27-DAG: [[SEC0]] = getelementptr {{.*}}i32* [[RVAR00:%.+]], i{{.+}} %{{.+}}
// CK27-DAG: [[RVAR00]] = load i32*, i32** [[VAR0]]
// CK27: call void [[CALL03:@.+]](i32* {{[^,]+}})
#pragma omp target map(pa[ii:0])
{
pa[50]++;
}
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
int *pvtPtr;
int pvtScl;
int pvtArr[10];
// Region 04
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 0, i8** null, i8** null, i{{64|32}}* null, i64* null)
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27: call void [[CALL04:@.+]]()
#pragma omp target private(pvtPtr)
{
pvtPtr[5]++;
}
// Region 05
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE05]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE05]]{{.+}})
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK27-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK27-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK27-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK27-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK27-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK27-DAG: store i32* [[VAR0:%.+]], i32** [[CBP0]]
// CK27-DAG: store i32* [[VAR0]], i32** [[CP0]]
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27: call void [[CALL05:@.+]](i32* {{[^,]+}})
#pragma omp target firstprivate(pvtPtr)
{
pvtPtr[5]++;
}
// Region 06
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 0, i8** null, i8** null, i{{64|32}}* null, i64* null)
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27: call void [[CALL06:@.+]]()
#pragma omp target private(pvtScl)
{
pvtScl++;
}
// Region 07
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27-DAG: call i32 @__tgt_target(i64 {{.+}}, i8* {{.+}}, i32 1, i8** [[BPGEP:%[0-9]+]], i8** [[PGEP:%[0-9]+]], {{.+}}[[SIZE07]]{{.+}}, {{.+}}[[MTYPE07]]{{.+}})
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27-DAG: [[BPGEP]] = getelementptr inbounds {{.+}}[[BPS:%[^,]+]], i32 0, i32 0
// CK27-DAG: [[PGEP]] = getelementptr inbounds {{.+}}[[PS:%[^,]+]], i32 0, i32 0
// CK27-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BPS]], i32 0, i32 0
// CK27-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[PS]], i32 0, i32 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK27-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to i[[Z]]*
// CK27-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to i[[Z]]*
// CK27-DAG: store i[[Z]] [[VAL:%.+]], i[[Z]]* [[CBP1]]
// CK27-DAG: store i[[Z]] [[VAL]], i[[Z]]* [[CP1]]
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27-DAG: [[VAL]] = load i[[Z]], i[[Z]]* [[ADDR:%.+]],
// CK27-64-DAG: [[CADDR:%.+]] = bitcast i[[Z]]* [[ADDR]] to i32*
// CK27-64-DAG: store i32 {{.+}}, i32* [[CADDR]],
// CK27: call void [[CALL07:@.+]](i[[Z]] [[VAL]])
#pragma omp target firstprivate(pvtScl)
{
pvtScl++;
}
// Region 08
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 0, i8** null, i8** null, i{{64|32}}* null, i64* null)
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27: call void [[CALL08:@.+]]()
#pragma omp target private(pvtArr)
{
pvtArr[5]++;
}
// Region 09
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK27-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE09]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE09]]{{.+}})
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK27-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK27-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK27-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK27-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [10 x i32]**
// CK27-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [10 x i32]**
// CK27-DAG: store [10 x i32]* [[VAR0:%.+]], [10 x i32]** [[CBP0]]
// CK27-DAG: store [10 x i32]* [[VAR0]], [10 x i32]** [[CP0]]
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27: call void [[CALL09:@.+]]([10 x i32]* {{[^,]+}})
#pragma omp target firstprivate(pvtArr)
{
pvtArr[5]++;
}
[OpenMP] Adjust map type bits according to latest spec and use zero size array sections for pointers. Summary: This patch changes the bits used to specify the map types according to the latest version of the libomptarget document and add the support for zero size array section when pointers are being implicitly mapped. This completes the missing new 4.5 map semantics. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20111 llvm-svn: 270868
2016-05-27 00:48:10 +08:00
}
// CK27: define {{.+}}[[CALL00]]
// CK27: define {{.+}}[[CALL01]]
// CK27: define {{.+}}[[CALL02]]
// CK27: define {{.+}}[[CALL03]]
[OpenMP] Add support for the 'private pointer' flag to signal variables captured in target regions and used in first-private clauses. Summary: If a variable is implicitly mapped (doesn't show in a map clause), the runtime library has to be informed if the corresponding capture shows up in first-private clause, so that the storage previously allocated in the device is used. This patch adds the support for that. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: http://reviews.llvm.org/D20112 llvm-svn: 270870
2016-05-27 00:53:38 +08:00
// CK27: define {{.+}}[[CALL04]]
// CK27: define {{.+}}[[CALL05]]
// CK27: define {{.+}}[[CALL06]]
// CK27: define {{.+}}[[CALL07]]
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#endif
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK28 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK28 --check-prefix CK28-64
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// RUN: %clang_cc1 -DCK28 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK28 --check-prefix CK28-64
// RUN: %clang_cc1 -DCK28 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK28 --check-prefix CK28-32
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// RUN: %clang_cc1 -DCK28 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK28 --check-prefix CK28-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK28 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY27 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK28 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY27 %s
// RUN: %clang_cc1 -DCK28 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY27 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK28 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY27 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY27-NOT: {{__kmpc|__tgt}}
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
#ifdef CK28
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK28-LABEL: @.__omp_offloading_{{.*}}explicit_maps_pointer_references{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// CK28: [[SIZE00:@.+]] = private {{.*}}constant [1 x i[[Z:64|32]]] [i[[Z:64|32]] {{8|4}}]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK28: [[MTYPE00:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK28-LABEL: @.__omp_offloading_{{.*}}explicit_maps_pointer_references{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// CK28: [[SIZE01:@.+]] = private {{.*}}constant [1 x i[[Z]]] [i[[Z]] 400]
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK28: [[MTYPE01:@.+]] = private {{.*}}constant [1 x i64] [i64 35]
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK28-LABEL: explicit_maps_pointer_references{{.*}}(
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
void explicit_maps_pointer_references (int *p){
int *&a = p;
// Region 00
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK28-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE00]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE00]]{{.+}})
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// CK28-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK28-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK28-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK28-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK28-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32***
// CK28-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32***
// CK28-DAG: store i32** [[VAR0:%.+]], i32*** [[CBP0]]
// CK28-DAG: store i32** [[VAR1:%.+]], i32*** [[CP0]]
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// CK28-DAG: [[VAR0]] = load i32**, i32*** [[VAR00:%.+]],
// CK28-DAG: [[VAR1]] = load i32**, i32*** [[VAR11:%.+]],
// CK28: call void [[CALL00:@.+]](i32** {{[^,]+}})
#pragma omp target map(a)
{
++a;
}
// Region 01
[Clang][OpenMP] New clang/libomptarget map interface: new function signatures, clang-side This clang patch changes the __tgt_* API function signatures in preparation for the new map interface. Changes are: Device IDs 32bits --> 64bits, Flags 32bits --> 64bits Differential revision: https://reviews.llvm.org/D40281 llvm-svn: 318789
2017-11-22 02:25:12 +08:00
// CK28-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 1, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[SIZE01]], {{.+}}getelementptr {{.+}}[1 x i{{.+}}]* [[MTYPE01]]{{.+}})
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// CK28-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK28-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
// CK28-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK28-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK28-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to i32**
// CK28-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to i32**
// CK28-DAG: store i32* [[VAR0:%.+]], i32** [[CBP0]]
// CK28-DAG: store i32* [[VAR1:%.+]], i32** [[CP0]]
[OpenMP] Add support for mapping array sections through pointer references. Summary: This patch fixes a bug in the map of array sections whose base is a reference to a pointer. The existing mapping support was not prepared to deal with it, causing the compiler to crash. Mapping a reference to a pointer enjoys the same characteristics of a regular pointer, i.e., it is passed by value. Therefore, the reference has to be materialized in the target region. Reviewers: hfinkel, carlo.bertolli, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22690 llvm-svn: 276933
2016-07-28 06:49:49 +08:00
// CK28-DAG: [[VAR0]] = load i32*, i32** [[VAR00:%.+]],
// CK28-DAG: [[VAR00]] = load i32**, i32*** [[VAR000:%.+]],
// CK28-DAG: [[VAR1]] = getelementptr inbounds i32, i32* [[VAR11:%.+]], i{{64|32}} 2
// CK28-DAG: [[VAR11]] = load i32*, i32** [[VAR111:%.+]],
// CK28-DAG: [[VAR111]] = load i32**, i32*** [[VAR1111:%.+]],
// CK28: call void [[CALL01:@.+]](i32* {{[^,]+}})
#pragma omp target map(a[2:100])
{
++a;
}
}
#endif
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
///==========================================================================///
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK29 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK29 --check-prefix CK29-64
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// RUN: %clang_cc1 -DCK29 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK29 --check-prefix CK29-64
// RUN: %clang_cc1 -DCK29 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK29 --check-prefix CK29-32
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// RUN: %clang_cc1 -DCK29 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK29 --check-prefix CK29-32
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -DCK29 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY28 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK29 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY28 %s
// RUN: %clang_cc1 -DCK29 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY28 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// RUN: %clang_cc1 -DCK29 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
[FileCheck] Add -allow-deprecated-dag-overlap to failing clang tests See https://reviews.llvm.org/D47106 for details. Reviewed By: probinson Differential Revision: https://reviews.llvm.org/D47172 llvm-svn: 336844
2018-07-12 04:26:20 +08:00
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY28 %s
[OPENMP] Support for -fopenmp-simd option with compilation of simd loops only. Added support for -fopenmp-simd option that allows compilation of simd-based constructs without emission of OpenMP runtime calls. llvm-svn: 321560
2017-12-30 02:07:07 +08:00
// SIMD-ONLY28-NOT: {{__kmpc|__tgt}}
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
#ifdef CK29
// CK29: [[SSA:%.+]] = type { double*, double** }
// CK29: [[SSB:%.+]] = type { [[SSA]]*, [[SSA]]** }
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK29-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29: [[MTYPE00:@.+]] = private {{.*}}constant [3 x i64] [i64 32, i64 281474976710672, i64 19]
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK29-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29: [[MTYPE01:@.+]] = private {{.*}}constant [3 x i64] [i64 32, i64 281474976710672, i64 19]
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
[OPENMP] Generate unique names for offloading regions id. It is required to emit unique names for offloading regions ids. Required to support compilation and linking of several compilation units. llvm-svn: 331899
2018-05-10 02:02:37 +08:00
// CK29-LABEL: @.__omp_offloading_{{.*}}foo{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29: [[MTYPE02:@.+]] = private {{.*}}constant [3 x i64] [i64 32, i64 281474976710672, i64 19]
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
struct SSA{
double *p;
double *&pr;
SSA(double *&pr) : pr(pr) {}
};
struct SSB{
SSA *p;
SSA *&pr;
SSB(SSA *&pr) : pr(pr) {}
// CK29-LABEL: define {{.+}}foo
void foo() {
// Region 00
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z:64|32]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE00]]{{.+}})
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK29-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK29-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK29-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SSB]]**
// CK29-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[SSA]]**
// CK29-DAG: store [[SSB]]* [[VAR0:%.+]], [[SSB]]** [[CBP0]]
// CK29-DAG: store [[SSA]]** [[VAR00:%.+]], [[SSA]]*** [[CP0]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: store i[[Z]] %{{.+}}, i[[Z]]* [[S0]]
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29-DAG: [[VAR0]] = load [[SSB]]*, [[SSB]]** %
// CK29-DAG: [[VAR00]] = getelementptr inbounds [[SSB]], [[SSB]]* [[VAR0]], i32 0, i32 0
// CK29-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK29-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK29-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SSA]]***
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to double***
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK29-DAG: store [[SSA]]** [[VAR00]], [[SSA]]*** [[CBP1]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: store double** [[VAR1:%.+]], double*** [[CP1]]
// CK29-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S1]]
// CK29-DAG: [[VAR1]] = load double**, double*** [[VAR1_REF:%.+]],
// CK29-DAG: [[VAR1_REF]] = getelementptr inbounds [[SSA]], [[SSA]]* %{{.+}}, i32 0, i32 1
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK29-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 2
// CK29-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to double***
// CK29-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to double**
// CK29-DAG: store double** [[VAR1]], double*** [[CBP2]]
// CK29-DAG: store double* [[VAR2:%.+]], double** [[CP2]]
// CK29-DAG: store i[[Z]] 80, i[[Z]]* [[S2]]
// CK29-DAG: [[VAR2]] = getelementptr inbounds double, double* [[VAR22:%.+]], i{{.+}} 0
// CK29-DAG: [[VAR22]] = load double*, double** %{{.+}},
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29: call void [[CALL00:@.+]]([[SSB]]* {{[^,]+}})
#pragma omp target map(p->pr[:10])
{
p->pr++;
}
// Region 01
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE01]]{{.+}})
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK29-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK29-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK29-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SSB]]**
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[SSA]]**
// CK29-DAG: store [[SSB]]* [[VAR0]], [[SSB]]** [[CBP0]]
// CK29-DAG: store [[SSA]]** [[VAR00:%.+]], [[SSA]]*** [[CP0]]
// CK29-DAG: store i[[Z]] %{{.+}}, i[[Z]]* [[S0]]
// CK29-DAG: [[VAR00]] = load [[SSA]]**, [[SSA]]*** [[VAR000:%.+]],
// CK29-DAG: [[VAR000]] = getelementptr inbounds [[SSB]], [[SSB]]* [[VAR0]], i32 0, i32 1
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK29-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK29-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SSA]]***
// CK29-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to double***
// CK29-DAG: store [[SSA]]** [[VAR00]], [[SSA]]*** [[CBP1]]
// CK29-DAG: store double** [[VAR1:%.+]], double*** [[CP1]]
// CK29-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S1]]
// CK29-DAG: [[VAR1]] = getelementptr inbounds [[SSA]], [[SSA]]* %{{.+}}, i32 0, i32 0
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK29-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 2
// CK29-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to double***
// CK29-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to double**
// CK29-DAG: store double** [[VAR1]], double*** [[CBP2]]
// CK29-DAG: store double* [[VAR2:%.+]], double** [[CP2]]
// CK29-DAG: store i[[Z]] 80, i[[Z]]* [[S2]]
// CK29-DAG: [[VAR2]] = getelementptr inbounds double, double* [[VAR22:%.+]], i{{.+}} 0
// CK29-DAG: [[VAR22]] = load double*, double** %{{.+}},
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29: call void [[CALL00:@.+]]([[SSB]]* {{[^,]+}})
#pragma omp target map(pr->p[:10])
{
pr->p++;
}
// Region 02
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: call i32 @__tgt_target(i64 {{[^,]+}}, i8* {{[^,]+}}, i32 3, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i[[Z]]* [[GEPS:%.+]], {{.+}}getelementptr {{.+}}[3 x i{{.+}}]* [[MTYPE02]]{{.+}})
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29-DAG: [[GEPBP]] = getelementptr inbounds {{.+}}[[BP:%[^,]+]]
// CK29-DAG: [[GEPP]] = getelementptr inbounds {{.+}}[[P:%[^,]+]]
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[GEPS]] = getelementptr inbounds {{.+}}[[S:%[^,]+]]
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29-DAG: [[BP0:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 0
// CK29-DAG: [[P0:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 0
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[S0:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 0
[OPENMP][DEBUG] Generate second function with correct arg types. Currently, if the some of the parameters are captured by value, this argument is converted to uintptr_t type and thus we loosing the debug info about real type of the argument (captured variable): ``` void @.outlined_function.(uintptr %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.outlined_function.(uintptr %a.casted.val) ... ``` To resolve this problem, in debug mode a speciall external wrapper function is generated, that calls the outlined function with the correct parameters types: ``` void @.wrapper.(uintptr %par) { %a = alloca i32 %cast = bitcast i32* %a to uintptr* store uintptr %par, uintptr *%cast %a.val = load i32, i32* %a call void @.outlined_function.(i32 %a) ret void } void @.outlined_function.(i32 %par); ... %a = alloca i32 %a.casted = alloca uintptr %cast = bitcast uintptr* %a.casted to i32* %a.val = load i32, i32 *%a store i32 %a.val, i32 *%cast %a.casted.val = load uintptr, uintptr* %a.casted call void @.wrapper.(uintptr %a.casted.val) ... ``` llvm-svn: 306697
2017-06-30 00:43:05 +08:00
// CK29-DAG: [[CBP0:%.+]] = bitcast i8** [[BP0]] to [[SSB]]**
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[CP0:%.+]] = bitcast i8** [[P0]] to [[SSA]]**
// CK29-DAG: store [[SSB]]* [[VAR0]], [[SSB]]** [[CBP0]]
// CK29-DAG: store [[SSA]]** [[VAR00:%.+]], [[SSA]]*** [[CP0]]
// CK29-DAG: store i[[Z]] %{{.+}}, i[[Z]]* [[S0]]
// CK29-DAG: [[VAR00]] = load [[SSA]]**, [[SSA]]*** [[VAR000:%.+]],
// CK29-DAG: [[VAR000]] = getelementptr inbounds [[SSB]], [[SSB]]* [[VAR0]], i32 0, i32 1
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29-DAG: [[BP1:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 1
// CK29-DAG: [[P1:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 1
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[S1:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 1
// CK29-DAG: [[CBP1:%.+]] = bitcast i8** [[BP1]] to [[SSA]]***
// CK29-DAG: [[CP1:%.+]] = bitcast i8** [[P1]] to double***
// CK29-DAG: store [[SSA]]** [[VAR00]], [[SSA]]*** [[CBP1]]
// CK29-DAG: store double** [[VAR1:%.+]], double*** [[CP1]]
// CK29-DAG: store i[[Z]] {{8|4}}, i[[Z]]* [[S1]]
// CK29-DAG: [[VAR1]] = load double**, double*** [[VAR1_REF:%.+]],
// CK29-DAG: [[VAR1_REF]] = getelementptr inbounds [[SSA]], [[SSA]]* %{{.+}}, i32 0, i32 1
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29-DAG: [[BP2:%.+]] = getelementptr inbounds {{.+}}[[BP]], i{{.+}} 0, i{{.+}} 2
// CK29-DAG: [[P2:%.+]] = getelementptr inbounds {{.+}}[[P]], i{{.+}} 0, i{{.+}} 2
The patch adds support for the new map interface between clang and libomptarget. The changes in the interface are the following: device IDs are now 64-bit integers (as opposed to 32-bit) map flags are 64-bit long (used to be 32-bit) mappings for partially mapped structs are now calculated at compile time and members of partially mapped structs are flagged using the MEMBER_OF field Support for is_device_ptr on struct members was dropped - this functionality is not supported by the OpenMP standard and its implementation is technically infeasible (however, use_device_ptr on struct members works as a non-standard extension of the compiler) llvm-svn: 337468
2018-07-20 00:34:13 +08:00
// CK29-DAG: [[S2:%.+]] = getelementptr inbounds {{.+}}[[S]], i{{.+}} 0, i{{.+}} 2
// CK29-DAG: [[CBP2:%.+]] = bitcast i8** [[BP2]] to double***
// CK29-DAG: [[CP2:%.+]] = bitcast i8** [[P2]] to double**
// CK29-DAG: store double** [[VAR1]], double*** [[CBP2]]
// CK29-DAG: store double* [[VAR2:%.+]], double** [[CP2]]
// CK29-DAG: store i[[Z]] 80, i[[Z]]* [[S2]]
// CK29-DAG: [[VAR2]] = getelementptr inbounds double, double* [[VAR22:%.+]], i{{.+}} 0
// CK29-DAG: [[VAR22]] = load double*, double** %{{.+}},
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
// CK29: call void [[CALL00:@.+]]([[SSB]]* {{[^,]+}})
#pragma omp target map(pr->pr[:10])
{
pr->pr++;
}
}
};
void explicit_maps_member_pointer_references(SSA *sap) {
double *d;
SSA sa(d);
SSB sb(sap);
sb.foo();
}
[OPENMP] Add support for mapping memory pointed by member pointer. Added support for map(s, s.ptr[0:1]) kind of mapping. llvm-svn: 342648
2018-09-20 21:54:02 +08:00
#endif
///==========================================================================///
// RUN: %clang_cc1 -DCK30 -verify -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK30 --check-prefix CK30-64
// RUN: %clang_cc1 -DCK30 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK30 --check-prefix CK30-64
// RUN: %clang_cc1 -DCK30 -verify -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK30 --check-prefix CK30-32
// RUN: %clang_cc1 -DCK30 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix CK30 --check-prefix CK30-32
// RUN: %clang_cc1 -DCK30 -verify -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY30 %s
// RUN: %clang_cc1 -DCK30 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -std=c++11 -triple powerpc64le-unknown-unknown -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=powerpc64le-ibm-linux-gnu -x c++ -triple powerpc64le-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY30 %s
// RUN: %clang_cc1 -DCK30 -verify -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY30 %s
// RUN: %clang_cc1 -DCK30 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -std=c++11 -triple i386-unknown-unknown -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-targets=i386-pc-linux-gnu -x c++ -triple i386-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap --check-prefix SIMD-ONLY30 %s
// SIMD-ONLY30-NOT: {{__kmpc|__tgt}}
#ifdef CK30
// CK30-DAG: [[BASE:%.+]] = type { i32*, i32, i32* }
// CK30-DAG: [[STRUCT:%.+]] = type { [[BASE]], i32*, i32*, i32, i32* }
// CK30-LABEL: @.__omp_offloading_{{.*}}map_with_deep_copy{{.*}}_l{{[0-9]+}}.region_id = weak constant i8 0
// The first element: 0x20 - OMP_MAP_TARGET_PARAM
// 2-4: 0x1000000000003 - OMP_MAP_MEMBER_OF(0) | OMP_MAP_TO | OMP_MAP_FROM - copies all the data in structs excluding deep-copied elements (from &s to &s.ptrBase1, from &s.ptr to &s.ptr1, from &s.ptr1 to end of s).
// 5-6: 0x1000000000013 - OMP_MAP_MEMBER_OF(0) | OMP_MAP_PTR_AND_OBJ | OMP_MAP_TO | OMP_MAP_FROM - deep copy of the pointers + pointee.
// CK30: [[MTYPE00:@.+]] = private {{.*}}constant [6 x i64] [i64 32, i64 281474976710659, i64 281474976710659, i64 281474976710659, i64 281474976710675, i64 281474976710675]
typedef struct {
int *ptrBase;
int valBase;
int *ptrBase1;
} Base;
typedef struct : public Base {
int *ptr;
int *ptr2;
int val;
int *ptr1;
} StructWithPtr;
// CK30-DAG: call i32 @__tgt_target(i64 -1, i8* @.__omp_offloading_{{.*}}map_with_deep_copy{{.*}}_l{{[0-9]+}}.region_id, i32 6, i8** [[GEPBP:%.+]], i8** [[GEPP:%.+]], i{{64|32}}* [[GEPS:%.+]], i64* getelementptr inbounds ([6 x i64], [6 x i64]* [[MTYPE00]], i32 0, i32 0))
// CK30-DAG: [[GEPS]] = getelementptr inbounds [6 x i{{64|32}}], [6 x i{{64|32}}]* [[SIZES:%.+]], i32 0, i32 0
// CK30-DAG: [[GEPP]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[PTRS:%.+]], i32 0, i32 0
// CK30-DAG: [[GEPBP]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BASES:%.+]], i32 0, i32 0
// CK30-DAG: [[BASE_PTR:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BASES]], i32 0, i32 0
// CK30-DAG: [[BC:%.+]] = bitcast i8** [[BASE_PTR]] to [[STRUCT]]**
// CK30-DAG: store [[STRUCT]]* [[S:%.+]], [[STRUCT]]** [[BC]],
// CK30-DAG: [[PTR:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[PTRS]], i32 0, i32 0
// CK30-DAG: [[BC:%.+]] = bitcast i8** [[PTR]] to [[STRUCT]]**
// CK30-DAG: store [[STRUCT]]* [[S]], [[STRUCT]]** [[BC]],
// CK30-DAG: [[SIZE:%.+]] = getelementptr inbounds [6 x i{{64|32}}], [6 x i{{64|32}}]* [[SIZES]], i32 0, i32 0
// CK30-64-DAG: store i64 [[S_ALLOC_SIZE:%.+]], i64* [[SIZE]],
// CK30-32-DAG: store i32 [[S_ALLOC_SIZE32:%.+]], i32* [[SIZE]],
// CK30-32-DAG: [[S_ALLOC_SIZE32]] = trunc i64 [[S_ALLOC_SIZE:%.+]] to i32
// CK30-DAG: [[S_ALLOC_SIZE]] = sdiv exact i64 [[DIFF:%.+]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CK30-DAG: [[DIFF]] = sub i64 [[S_END_BC:%.+]], [[S_BEGIN_BC:%.+]]
// CK30-DAG: [[S_BEGIN_BC]] = ptrtoint i8* [[S_BEGIN:%.+]] to i64
// CK30-DAG: [[S_END_BC]] = ptrtoint i8* [[S_END:%.+]] to i64
// CK30-DAG: [[S_BEGIN]] = bitcast [[STRUCT]]* [[S]] to i8*
// CK30-DAG: [[S_END]] = getelementptr i8, i8* [[S_LAST:%.+]], i32 1
// CK30-DAG: [[S_LAST]] = getelementptr i8, i8* [[S_BC:%.+]], i{{64|32}} {{55|27}}
// CK30-DAG: [[S_BC]] = bitcast [[STRUCT]]* [[S]] to i8*
// CK30-DAG: [[BASE_PTR:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BASES]], i32 0, i32 1
// CK30-DAG: [[BC:%.+]] = bitcast i8** [[BASE_PTR]] to [[STRUCT]]**
// CK30-DAG: store [[STRUCT]]* [[S]], [[STRUCT]]** [[BC]],
// CK30-DAG: [[PTR:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[PTRS]], i32 0, i32 1
// CK30-DAG: [[BC:%.+]] = bitcast i8** [[PTR]] to [[STRUCT]]**
// CK30-DAG: store [[STRUCT]]* [[S]], [[STRUCT]]** [[BC]],
// CK30-DAG: [[SIZE:%.+]] = getelementptr inbounds [6 x i{{64|32}}], [6 x i{{64|32}}]* [[SIZES]], i32 0, i32 1
// CK30-64-DAG: store i64 [[SIZE1:%.+]], i64* [[SIZE]],
// CK30-32-DAG: store i32 [[SIZE1_32:%.+]], i32* [[SIZE]],
// CK30-32-DAG: [[SIZE1_32]] = trunc i64 [[SIZE1:%.+]] to i32
// CK30-DAG: [[SIZE1]] = sdiv exact i64 [[DIFF:%.+]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CK30-DAG: [[DIFF]] = sub i64 [[S_PTRBASE1_BC:%.+]], [[S_BEGIN_BC:%.+]]
// CK30-DAG: [[S_BEGIN_BC]] = ptrtoint i8* [[S_BEGIN:%.+]] to i64
// CK30-DAG: [[S_PTRBASE1_BC]] = ptrtoint i8* [[S_PTRBASE1:%.+]] to i64
// CK30-DAG: [[S_PTRBASE1]] = bitcast i32** [[S_PTRBASE1_REF:%.+]] to i8*
// CK30-DAG: [[S_BEGIN]] = bitcast [[STRUCT]]* [[S]] to i8*
// CK30-DAG: [[S_PTRBASE1_REF]] = getelementptr inbounds [[BASE]], [[BASE]]* [[BASE_ADDR:%.+]], i32 0, i32 2
// CK30-DAG: [[BASE_ADDR]] = bitcast [[STRUCT]]* [[S]] to [[BASE]]*
// CK30-DAG: [[BASE_PTR:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BASES]], i32 0, i32 2
// CK30-DAG: [[BC:%.+]] = bitcast i8** [[BASE_PTR]] to [[STRUCT]]**
// CK30-DAG: store [[STRUCT]]* [[S]], [[STRUCT]]** [[BC]],
// CK30-DAG: [[PTR:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[PTRS]], i32 0, i32 2
// CK30-DAG: [[BC:%.+]] = bitcast i8** [[PTR]] to i32***
// CK30-DAG: store i32** [[PTR1:%.+]], i32*** [[BC]],
// CK30-DAG: [[SIZE:%.+]] = getelementptr inbounds [6 x i{{64|32}}], [6 x i{{64|32}}]* [[SIZES]], i32 0, i32 2
// CK30-64-DAG: store i64 [[SIZE2:%.+]], i64* [[SIZE]],
// CK30-32-DAG: store i32 [[SIZE2_32:%.+]], i32* [[SIZE]],
// CK30-32-DAG: [[SIZE2_32]] = trunc i64 [[SIZE2:%.+]] to i32
// CK30-DAG: [[PTR1]] = getelementptr i32*, i32** [[S_PTRBASE1_REF]], i{{64|32}} 1
// CK30-DAG: [[SIZE2]] = sdiv exact i64 [[DIFF:%.+]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CK30-DAG: [[DIFF]] = sub i64 [[S_PTR1_BC:%.+]], [[S_PTRBASE1_BC:%.+]]
// CK30-DAG: [[S_PTR1_BC]] = ptrtoint i8* [[S_PTR1:%.+]] to i64
// CK30-DAG: [[S_PTRBASE1_BC]] = ptrtoint i8* [[S_PTRBASE1:%.+]] to i64
// CK30-DAG: [[S_PTR1]] = bitcast i32** [[S_PTR1_REF:%.+]] to i8*
// CK30-DAG: [[S_PTRBASE1]] = bitcast i32** [[PTR1]] to i8*
// CK30-DAG: [[S_PTR1_REF]] = getelementptr inbounds [[STRUCT]], [[STRUCT]]* [[S]], i32 0, i32 4
// CK30-DAG: [[BASE_PTR:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BASES]], i32 0, i32 3
// CK30-DAG: [[BC:%.+]] = bitcast i8** [[BASE_PTR]] to [[STRUCT]]**
// CK30-DAG: store [[STRUCT]]* [[S]], [[STRUCT]]** [[BC]],
// CK30-DAG: [[PTR:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[PTRS]], i32 0, i32 3
// CK30-DAG: [[BC:%.+]] = bitcast i8** [[PTR]] to i32***
// CK30-DAG: store i32** [[PTR2:%.+]], i32*** [[BC]],
// CK30-DAG: [[SIZE:%.+]] = getelementptr inbounds [6 x i{{64|32}}], [6 x i{{64|32}}]* [[SIZES]], i32 0, i32 3
// CK30-64-DAG: store i64 [[SIZE3:%.+]], i64* [[SIZE]],
// CK30-32-DAG: store i32 [[SIZE3_32:%.+]], i32* [[SIZE]],
// CK30-32-DAG: [[SIZE3_32]] = trunc i64 [[SIZE3:%.+]] to i32
// CK30-DAG: [[PTR2]] = getelementptr i32*, i32** [[S_PTR1_REF]], i{{64|32}} 1
// CK30-DAG: [[SIZE3]] = sdiv exact i64 [[DIFF:%.+]], ptrtoint (i8* getelementptr (i8, i8* null, i32 1) to i64)
// CK30-DAG: [[DIFF]] = sub i64 [[S_END_BC:%.+]], [[S_PTR1_BC:%.+]]
// CK30-DAG: [[S_PTR1_BC]] = ptrtoint i8* [[S_PTR1:%.+]] to i64
// CK30-DAG: [[S_END_BC]] = ptrtoint i8* [[S_END:%.+]] to i64
// CK30-DAG: [[S_PTR1]] = bitcast i32** [[PTR2]] to i8*
// CK30-DAG: [[S_END]] = getelementptr i8, i8* [[S_LAST]], i{{64|32}} 1
// CK30-DAG: [[BASE_PTR:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BASES]], i32 0, i32 4
// CK30-DAG: [[BC:%.+]] = bitcast i8** [[BASE_PTR]] to i32***
// CK30-DAG: store i32** [[S_PTR1:%.+]], i32*** [[BC]],
// CK30-DAG: [[PTR:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[PTRS]], i32 0, i32 4
// CK30-DAG: [[BC:%.+]] = bitcast i8** [[PTR]] to i32**
// CK30-DAG: store i32* [[S_PTR1_BEGIN:%.+]], i32** [[BC]],
// CK30-DAG: [[SIZE:%.+]] = getelementptr inbounds [6 x i{{64|32}}], [6 x i{{64|32}}]* [[SIZES]], i32 0, i32 4
// CK30-DAG: store i{{64|32}} 4, i{{64|32}}* [[SIZE]],
// CK30-DAG: [[S_PTR1]] = getelementptr inbounds [[STRUCT]], [[STRUCT]]* [[S]], i32 0, i32 4
// CK30-DAG: [[S_PTR1_BEGIN]] = getelementptr inbounds i32, i32* [[S_PTR1_BEGIN_REF:%.+]], i{{64|32}} 0
// CK30-DAG: [[S_PTR1_BEGIN_REF]] = load i32*, i32** [[S_PTR1:%.+]],
// CK30-DAG: [[S_PTR1]] = getelementptr inbounds [[STRUCT]], [[STRUCT]]* [[S]], i32 0, i32 4
// CK30-DAG: [[BASE_PTR:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[BASES]], i32 0, i32 5
// CK30-DAG: [[BC:%.+]] = bitcast i8** [[BASE_PTR]] to i32***
// CK30-DAG: store i32** [[S_PTRBASE1:%.+]], i32*** [[BC]],
// CK30-DAG: [[PTR:%.+]] = getelementptr inbounds [6 x i8*], [6 x i8*]* [[PTRS]], i32 0, i32 5
// CK30-DAG: [[BC:%.+]] = bitcast i8** [[PTR]] to i32**
// CK30-DAG: store i32* [[S_PTRBASE1_BEGIN:%.+]], i32** [[BC]],
// CK30-DAG: [[SIZE:%.+]] = getelementptr inbounds [6 x i{{64|32}}], [6 x i{{64|32}}]* [[SIZES]], i32 0, i32 5
// CK30-DAG: store i{{64|32}} 4, i{{64|32}}* [[SIZE]],
// CK30-DAG: [[S_PTRBASE1]] = getelementptr inbounds [[BASE]], [[BASE]]* [[S_BASE:%.+]], i32 0, i32 2
// CK30-DAG: [[S_BASE]] = bitcast [[STRUCT]]* [[S]] to [[BASE]]*
// CK30-DAG: [[S_PTRBASE1_BEGIN]] = getelementptr inbounds i32, i32* [[S_PTRBASE1_BEGIN_REF:%.+]], i{{64|32}} 0
// CK30-DAG: [[S_PTRBASE1_BEGIN_REF]] = load i32*, i32** [[S_PTRBASE1:%.+]],
// CK30-DAG: [[S_PTRBASE1]] = getelementptr inbounds [[BASE]], [[BASE]]* [[S_BASE:%.+]], i32 0, i32 2
// CK30-DAG: [[S_BASE]] = bitcast [[STRUCT]]* [[S]] to [[BASE]]*
void map_with_deep_copy() {
StructWithPtr s;
#pragma omp target map(s, s.ptr1 [0:1], s.ptrBase1 [0:1])
{
s.val++;
s.ptr1[0]++;
s.ptrBase1[0] = 10001;
}
}
[OpenMP] Add support to map member expressions with references to pointers. Summary: This patch add support to map pointers through references in class members. Although a reference does not have storage that a user can access, it still has to be mapped in order to get the deep copy right and the dereferencing code work properly. Reviewers: hfinkel, carlo.bertolli, arpith-jacob, kkwli0, ABataev Subscribers: caomhin, cfe-commits Differential Revision: https://reviews.llvm.org/D22787 llvm-svn: 276934
2016-07-28 06:52:16 +08:00
#endif
[OpenMP] Update target directive codegen to use 4.5 implicit data mappings. Summary: This patch implements the 4.5 specification for the implicit data maps. OpenMP 4.5 specification changes the default way data is captured into a target region. All the non-aggregate kinds are passed by value by default. This required activating the capturing by value during SEMA for the target region. All the non-aggregate values that can be encoded in the size of a pointer are properly casted and forwarded to the runtime library. On top of fixing the previous weird behavior for mapping pointers in nested data regions (an explicit map was always required), this also improves performance as the number of allocations/transactions to the device per non-aggregate map are reduced from two to only one - instead of passing a reference and the value, only the value passed. Explicit maps will be added later on once firstprivate, private, and map clauses' SEMA and parsing are available. Reviewers: hfinkel, rjmccall, ABataev Subscribers: cfe-commits, carlo.bertolli Differential Revision: http://reviews.llvm.org/D14940 llvm-svn: 254521
2015-12-03 01:44:43 +08:00
#endif