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/taskloop_simd_private_codeg...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

426 lines
23 KiB
C++
Raw Normal View History

[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -x c++ -triple x86_64-apple-darwin10 -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -DLAMBDA -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -check-prefix=LAMBDA %s
// RUN: %clang_cc1 -verify -fopenmp -x c++ -fblocks -DBLOCKS -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -check-prefix=BLOCKS %s
// RUN: %clang_cc1 -verify -fopenmp -x c++ -std=c++11 -DARRAY -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -check-prefix=ARRAY %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 -verify -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -std=c++11 -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -std=c++11 -DLAMBDA -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -fblocks -DBLOCKS -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -verify -fopenmp-simd -x c++ -std=c++11 -DARRAY -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// expected-no-diagnostics
#ifndef ARRAY
#ifndef HEADER
#define HEADER
template <class T>
struct S {
T f;
S(T a) : f(a) {}
S() : f() {}
operator T() { return T(); }
~S() {}
};
volatile double g;
[OPENMP] Codegen for reduction clauses in 'taskloop' directives. Adds codegen for taskloop-based directives. llvm-svn: 308174
2017-07-17 21:30:36 +08:00
// CHECK-DAG: [[KMP_TASK_T_TY:%.+]] = type { i8*, i32 (i32, i8*)*, i32, %union{{.+}}, %union{{.+}}, i64, i64, i64, i32, i8* }
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK-DAG: [[S_DOUBLE_TY:%.+]] = type { double }
// CHECK-DAG: [[CAP_MAIN_TY:%.+]] = type { i8 }
// CHECK-DAG: [[PRIVATES_MAIN_TY:%.+]] = type {{.?}}{ [2 x [[S_DOUBLE_TY]]], [[S_DOUBLE_TY]], i32, [2 x i32]
// CHECK-DAG: [[KMP_TASK_MAIN_TY:%.+]] = type { [[KMP_TASK_T_TY]], [[PRIVATES_MAIN_TY]] }
// CHECK-DAG: [[S_INT_TY:%.+]] = type { i32 }
// CHECK-DAG: [[CAP_TMAIN_TY:%.+]] = type { i8 }
// CHECK-DAG: [[PRIVATES_TMAIN_TY:%.+]] = type { i32, [2 x i32], [2 x [[S_INT_TY]]], [[S_INT_TY]], [104 x i8] }
// CHECK-DAG: [[KMP_TASK_TMAIN_TY:%.+]] = type { [[KMP_TASK_T_TY]], [{{[0-9]+}} x i8], [[PRIVATES_TMAIN_TY]] }
template <typename T>
T tmain() {
S<T> test;
T t_var __attribute__((aligned(128))) = T();
T vec[] = {1, 2};
S<T> s_arr[] = {1, 2};
S<T> var(3);
#pragma omp taskloop simd private(t_var, vec, s_arr, s_arr, var, var)
for (int i = 0; i < 10; ++i) {
vec[0] = t_var;
s_arr[0] = var;
}
return T();
}
int main() {
static int sivar;
#ifdef LAMBDA
// LAMBDA: [[G:@.+]] = global double
// LAMBDA-LABEL: @main
// LAMBDA: call{{( x86_thiscallcc)?}} void [[OUTER_LAMBDA:@.+]](
[&]() {
// LAMBDA: define{{.*}} internal{{.*}} void [[OUTER_LAMBDA]](
[OPENMP] Codegen for reduction clauses in 'taskloop' directives. Adds codegen for taskloop-based directives. llvm-svn: 308174
2017-07-17 21:30:36 +08:00
// LAMBDA: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%{{[^ ]+}} @{{[^,]+}}, i32 %{{[^,]+}}, i32 1, i64 96, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %{{[^*]+}}*)* [[TASK_ENTRY:@[^ ]+]] to i32 (i32, i8*)*))
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// LAMBDA: [[PRIVATES:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* %{{.+}}, i{{.+}} 0, i{{.+}} 1
Do not always request an implicit taskgroup region inside the kmpc_taskloop function Summary: For the following code: ``` int i; #pragma omp taskloop for (i = 0; i < 100; ++i) {} #pragma omp taskloop nogroup for (i = 0; i < 100; ++i) {} ``` Clang emits the following LLVM IR: ``` ... call void @__kmpc_taskgroup(%struct.ident_t* @0, i32 %0) %2 = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 %0, i32 1, i64 80, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @.omp_task_entry. to i32 (i32, i8*)*)) ... call void @__kmpc_taskloop(%struct.ident_t* @0, i32 %0, i8* %2, i32 1, i64* %8, i64* %9, i64 %13, i32 0, i32 0, i64 0, i8* null) call void @__kmpc_end_taskgroup(%struct.ident_t* @0, i32 %0) ... %15 = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 %0, i32 1, i64 80, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.1*)* @.omp_task_entry..2 to i32 (i32, i8*)*)) ... call void @__kmpc_taskloop(%struct.ident_t* @0, i32 %0, i8* %15, i32 1, i64* %21, i64* %22, i64 %26, i32 0, i32 0, i64 0, i8* null) ``` The first set of instructions corresponds to the first taskloop construct. It is important to note that the implicit taskgroup region associated with the taskloop construct has been materialized in our IR: the `__kmpc_taskloop` occurs inside a taskgroup region. Note also that this taskgroup region does not exist in our second taskloop because we are using the `nogroup` clause. The issue here is the 4th argument of the kmpc_taskloop call, starting from the end, is always a zero. Checking the LLVM OpenMP RT implementation, we see that this argument corresponds to the nogroup parameter: ``` void __kmpc_taskloop(ident_t *loc, int gtid, kmp_task_t *task, int if_val, kmp_uint64 *lb, kmp_uint64 *ub, kmp_int64 st, int nogroup, int sched, kmp_uint64 grainsize, void *task_dup); ``` So basically we always tell to the RT to do another taskgroup region. For the first taskloop, this means that we create two taskgroup regions. For the second example, it means that despite the fact we had a nogroup clause we are going to have a taskgroup region, so we unnecessary wait until all descendant tasks have been executed. Reviewers: ABataev Reviewed By: ABataev Subscribers: rogfer01, cfe-commits Differential Revision: https://reviews.llvm.org/D53636 llvm-svn: 345180
2018-10-25 03:06:37 +08:00
// LAMBDA: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* null)
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// LAMBDA: ret
#pragma omp taskloop simd private(g, sivar)
for (int i = 0; i < 10; ++i) {
// LAMBDA: define {{.+}} void [[INNER_LAMBDA:@.+]](%{{.+}}* [[ARG_PTR:%.+]])
// LAMBDA: store %{{.+}}* [[ARG_PTR]], %{{.+}}** [[ARG_PTR_REF:%.+]],
// LAMBDA: [[ARG_PTR:%.+]] = load %{{.+}}*, %{{.+}}** [[ARG_PTR_REF]]
// LAMBDA: [[G_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// LAMBDA: [[G_REF:%.+]] = load double*, double** [[G_PTR_REF]]
// LAMBDA: store double 2.0{{.+}}, double* [[G_REF]]
// LAMBDA: [[SIVAR_PTR_REF:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* [[ARG_PTR]], i{{[0-9]+}} 0, i{{[0-9]+}} 1
// LAMBDA: [[SIVAR_REF:%.+]] = load i{{[0-9]+}}*, i{{[0-9]+}}** [[SIVAR_PTR_REF]]
// LAMBDA: store i{{[0-9]+}} 3, i{{[0-9]+}}* [[SIVAR_REF]]
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// LAMBDA: define internal i32 [[TASK_ENTRY]](i32 %0, %{{.+}}* noalias %1)
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
g = 1;
sivar = 2;
// LAMBDA: store double 1.0{{.+}}, double* %{{.+}},
// LAMBDA: store i{{[0-9]+}} 2, i{{[0-9]+}}* %{{.+}},
// LAMBDA: call void [[INNER_LAMBDA]](%
// LAMBDA: ret
[&]() {
g = 2;
sivar = 3;
}();
}
}();
return 0;
#elif defined(BLOCKS)
// BLOCKS: [[G:@.+]] = global double
// BLOCKS-LABEL: @main
// BLOCKS: call void {{%.+}}(i8
^{
// BLOCKS: define{{.*}} internal{{.*}} void {{.+}}(i8*
[OPENMP] Codegen for reduction clauses in 'taskloop' directives. Adds codegen for taskloop-based directives. llvm-svn: 308174
2017-07-17 21:30:36 +08:00
// BLOCKS: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc(%{{[^ ]+}} @{{[^,]+}}, i32 %{{[^,]+}}, i32 1, i64 96, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, %{{[^*]+}}*)* [[TASK_ENTRY:@[^ ]+]] to i32 (i32, i8*)*))
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// BLOCKS: [[PRIVATES:%.+]] = getelementptr inbounds %{{.+}}, %{{.+}}* %{{.+}}, i{{.+}} 0, i{{.+}} 1
Do not always request an implicit taskgroup region inside the kmpc_taskloop function Summary: For the following code: ``` int i; #pragma omp taskloop for (i = 0; i < 100; ++i) {} #pragma omp taskloop nogroup for (i = 0; i < 100; ++i) {} ``` Clang emits the following LLVM IR: ``` ... call void @__kmpc_taskgroup(%struct.ident_t* @0, i32 %0) %2 = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 %0, i32 1, i64 80, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @.omp_task_entry. to i32 (i32, i8*)*)) ... call void @__kmpc_taskloop(%struct.ident_t* @0, i32 %0, i8* %2, i32 1, i64* %8, i64* %9, i64 %13, i32 0, i32 0, i64 0, i8* null) call void @__kmpc_end_taskgroup(%struct.ident_t* @0, i32 %0) ... %15 = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 %0, i32 1, i64 80, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.1*)* @.omp_task_entry..2 to i32 (i32, i8*)*)) ... call void @__kmpc_taskloop(%struct.ident_t* @0, i32 %0, i8* %15, i32 1, i64* %21, i64* %22, i64 %26, i32 0, i32 0, i64 0, i8* null) ``` The first set of instructions corresponds to the first taskloop construct. It is important to note that the implicit taskgroup region associated with the taskloop construct has been materialized in our IR: the `__kmpc_taskloop` occurs inside a taskgroup region. Note also that this taskgroup region does not exist in our second taskloop because we are using the `nogroup` clause. The issue here is the 4th argument of the kmpc_taskloop call, starting from the end, is always a zero. Checking the LLVM OpenMP RT implementation, we see that this argument corresponds to the nogroup parameter: ``` void __kmpc_taskloop(ident_t *loc, int gtid, kmp_task_t *task, int if_val, kmp_uint64 *lb, kmp_uint64 *ub, kmp_int64 st, int nogroup, int sched, kmp_uint64 grainsize, void *task_dup); ``` So basically we always tell to the RT to do another taskgroup region. For the first taskloop, this means that we create two taskgroup regions. For the second example, it means that despite the fact we had a nogroup clause we are going to have a taskgroup region, so we unnecessary wait until all descendant tasks have been executed. Reviewers: ABataev Reviewed By: ABataev Subscribers: rogfer01, cfe-commits Differential Revision: https://reviews.llvm.org/D53636 llvm-svn: 345180
2018-10-25 03:06:37 +08:00
// BLOCKS: call void @__kmpc_taskloop(%{{.+}}* @{{.+}}, i32 %{{.+}}, i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* null)
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// BLOCKS: ret
#pragma omp taskloop simd private(g, sivar)
for (int i = 0; i < 10; ++i) {
// BLOCKS: define {{.+}} void {{@.+}}(i8*
// BLOCKS-NOT: [[G]]{{[[^:word:]]}}
// BLOCKS: store double 2.0{{.+}}, double*
// BLOCKS-NOT: [[G]]{{[[^:word:]]}}
// BLOCKS-NOT: [[SIVAR]]{{[[^:word:]]}}
// BLOCKS: store i{{[0-9]+}} 4, i{{[0-9]+}}*
// BLOCKS-NOT: [[SIVAR]]{{[[^:word:]]}}
// BLOCKS: ret
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// BLOCKS: define internal i32 [[TASK_ENTRY]](i32 %0, %{{.+}}* noalias %1)
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
g = 1;
sivar = 3;
// BLOCKS: store double 1.0{{.+}}, double* %{{.+}},
// BLOCKS-NOT: [[G]]{{[[^:word:]]}}
// BLOCKS: store i{{[0-9]+}} 3, i{{[0-9]+}}* %{{.+}},
// BLOCKS-NOT: [[SIVAR]]{{[[^:word:]]}}
// BLOCKS: call void {{%.+}}(i8
^{
g = 2;
sivar = 4;
}();
}
}();
return 0;
#else
S<double> test;
int t_var = 0;
int vec[] = {1, 2};
S<double> s_arr[] = {1, 2};
S<double> var(3);
#pragma omp taskloop simd private(var, t_var, s_arr, vec, s_arr, var, sivar)
for (int i = 0; i < 10; ++i) {
vec[0] = t_var;
s_arr[0] = var;
sivar = 8;
}
#pragma omp task
g+=1;
return tmain<int>();
#endif
}
// CHECK: define i{{[0-9]+}} @main()
// CHECK: [[TEST:%.+]] = alloca [[S_DOUBLE_TY]],
// CHECK: [[T_VAR_ADDR:%.+]] = alloca i32,
// CHECK: [[VEC_ADDR:%.+]] = alloca [2 x i32],
// CHECK: [[S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]],
// CHECK: [[VAR_ADDR:%.+]] = alloca [[S_DOUBLE_TY]],
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[LOC:%.+]])
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call {{.*}} [[S_DOUBLE_TY_DEF_CONSTR:@.+]]([[S_DOUBLE_TY]]* [[TEST]])
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// Do not store original variables in capture struct.
// CHECK-NOT: getelementptr inbounds [[CAP_MAIN_TY]],
// Allocate task.
// Returns struct kmp_task_t {
// [[KMP_TASK_T_TY]] task_data;
// [[KMP_TASK_MAIN_TY]] privates;
// };
[OPENMP] Codegen for reduction clauses in 'taskloop' directives. Adds codegen for taskloop-based directives. llvm-svn: 308174
2017-07-17 21:30:36 +08:00
// CHECK: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc([[LOC]], i32 [[GTID]], i32 9, i64 120, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_MAIN_TY]]*)* [[TASK_ENTRY:@[^ ]+]] to i32 (i32, i8*)*))
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: [[RES_KMP_TASK:%.+]] = bitcast i8* [[RES]] to [[KMP_TASK_MAIN_TY]]*
// CHECK: [[TASK:%.+]] = getelementptr inbounds [[KMP_TASK_MAIN_TY]], [[KMP_TASK_MAIN_TY]]* [[RES_KMP_TASK]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// Initialize kmp_task_t->privates with default values (no init for simple types, default constructors for classes).
// Also copy address of private copy to the corresponding shareds reference.
// CHECK: [[PRIVATES:%.+]] = getelementptr inbounds [[KMP_TASK_MAIN_TY]], [[KMP_TASK_MAIN_TY]]* [[RES_KMP_TASK]], i{{[0-9]+}} 0, i{{[0-9]+}} 1
// Constructors for s_arr and var.
// a_arr;
// CHECK: [[PRIVATE_S_ARR_REF:%.+]] = getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* [[PRIVATES]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// CHECK: getelementptr inbounds [2 x [[S_DOUBLE_TY]]], [2 x [[S_DOUBLE_TY]]]* [[PRIVATE_S_ARR_REF]], i{{.+}} 0, i{{.+}} 0
// CHECK: getelementptr inbounds [[S_DOUBLE_TY]], [[S_DOUBLE_TY]]* %{{.+}}, i{{.+}} 2
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void [[S_DOUBLE_TY_DEF_CONSTR]]([[S_DOUBLE_TY]]* [[S_ARR_CUR:%.+]])
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: getelementptr inbounds [[S_DOUBLE_TY]], [[S_DOUBLE_TY]]* [[S_ARR_CUR]], i{{.+}} 1
// CHECK: icmp eq
// CHECK: br i1
// var;
// CHECK: [[PRIVATE_VAR_REF:%.+]] = getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 1
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void [[S_DOUBLE_TY_DEF_CONSTR]]([[S_DOUBLE_TY]]* [[PRIVATE_VAR_REF:%.+]])
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// Provide pointer to destructor function, which will destroy private variables at the end of the task.
// CHECK: [[DESTRUCTORS_REF:%.+]] = getelementptr inbounds [[KMP_TASK_T_TY]], [[KMP_TASK_T_TY]]* [[TASK]], i{{.+}} 0, i{{.+}} 3
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[DESTRUCTORS_PTR:%.+]] = bitcast %union{{.+}}* [[DESTRUCTORS_REF]] to i32 (i32, i8*)**
// CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_MAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// Start task.
Do not always request an implicit taskgroup region inside the kmpc_taskloop function Summary: For the following code: ``` int i; #pragma omp taskloop for (i = 0; i < 100; ++i) {} #pragma omp taskloop nogroup for (i = 0; i < 100; ++i) {} ``` Clang emits the following LLVM IR: ``` ... call void @__kmpc_taskgroup(%struct.ident_t* @0, i32 %0) %2 = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 %0, i32 1, i64 80, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @.omp_task_entry. to i32 (i32, i8*)*)) ... call void @__kmpc_taskloop(%struct.ident_t* @0, i32 %0, i8* %2, i32 1, i64* %8, i64* %9, i64 %13, i32 0, i32 0, i64 0, i8* null) call void @__kmpc_end_taskgroup(%struct.ident_t* @0, i32 %0) ... %15 = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 %0, i32 1, i64 80, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.1*)* @.omp_task_entry..2 to i32 (i32, i8*)*)) ... call void @__kmpc_taskloop(%struct.ident_t* @0, i32 %0, i8* %15, i32 1, i64* %21, i64* %22, i64 %26, i32 0, i32 0, i64 0, i8* null) ``` The first set of instructions corresponds to the first taskloop construct. It is important to note that the implicit taskgroup region associated with the taskloop construct has been materialized in our IR: the `__kmpc_taskloop` occurs inside a taskgroup region. Note also that this taskgroup region does not exist in our second taskloop because we are using the `nogroup` clause. The issue here is the 4th argument of the kmpc_taskloop call, starting from the end, is always a zero. Checking the LLVM OpenMP RT implementation, we see that this argument corresponds to the nogroup parameter: ``` void __kmpc_taskloop(ident_t *loc, int gtid, kmp_task_t *task, int if_val, kmp_uint64 *lb, kmp_uint64 *ub, kmp_int64 st, int nogroup, int sched, kmp_uint64 grainsize, void *task_dup); ``` So basically we always tell to the RT to do another taskgroup region. For the first taskloop, this means that we create two taskgroup regions. For the second example, it means that despite the fact we had a nogroup clause we are going to have a taskgroup region, so we unnecessary wait until all descendant tasks have been executed. Reviewers: ABataev Reviewed By: ABataev Subscribers: rogfer01, cfe-commits Differential Revision: https://reviews.llvm.org/D53636 llvm-svn: 345180
2018-10-25 03:06:37 +08:00
// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_MAIN_TY]]*, [[KMP_TASK_MAIN_TY]]*, i32)* [[MAIN_DUP:@.+]] to i8*))
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: call i32 @__kmpc_omp_task([[LOC]], i32 [[GTID]], i8*
// CHECK: = call i{{.+}} [[TMAIN_INT:@.+]]()
// No destructors must be called for private copies of s_arr and var.
// CHECK-NOT: getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 2
// CHECK-NOT: getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 3
// CHECK: call void [[S_DOUBLE_TY_DESTR:@.+]]([[S_DOUBLE_TY]]*
// CHECK-NOT: getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 2
// CHECK-NOT: getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 3
// CHECK: ret
//
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[PRIVATES_MAP_FN:@.+]]([[PRIVATES_MAIN_TY]]* noalias %0, [[S_DOUBLE_TY]]** noalias %1, i32** noalias %2, [2 x [[S_DOUBLE_TY]]]** noalias %3, [2 x i32]** noalias %4, i32** noalias %5)
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: [[PRIVATES:%.+]] = load [[PRIVATES_MAIN_TY]]*, [[PRIVATES_MAIN_TY]]**
// CHECK: [[PRIV_S_VAR:%.+]] = getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* [[PRIVATES]], i32 0, i32 0
// CHECK: [[ARG3:%.+]] = load [2 x [[S_DOUBLE_TY]]]**, [2 x [[S_DOUBLE_TY]]]*** %{{.+}},
// CHECK: store [2 x [[S_DOUBLE_TY]]]* [[PRIV_S_VAR]], [2 x [[S_DOUBLE_TY]]]** [[ARG3]],
// CHECK: [[PRIV_VAR:%.+]] = getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* [[PRIVATES]], i32 0, i32 1
// CHECK: [[ARG1:%.+]] = load [[S_DOUBLE_TY]]**, [[S_DOUBLE_TY]]*** {{.+}},
// CHECK: store [[S_DOUBLE_TY]]* [[PRIV_VAR]], [[S_DOUBLE_TY]]** [[ARG1]],
// CHECK: [[PRIV_T_VAR:%.+]] = getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* [[PRIVATES]], i32 0, i32 2
// CHECK: [[ARG2:%.+]] = load i32**, i32*** %{{.+}},
// CHECK: store i32* [[PRIV_T_VAR]], i32** [[ARG2]],
// CHECK: [[PRIV_VEC:%.+]] = getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* [[PRIVATES]], i32 0, i32 3
// CHECK: [[ARG4:%.+]] = load [2 x i32]**, [2 x i32]*** %{{.+}},
// CHECK: store [2 x i32]* [[PRIV_VEC]], [2 x i32]** [[ARG4]],
// CHECK: ret void
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_MAIN_TY]]* noalias %1)
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_DOUBLE_TY]]*,
// CHECK: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
// CHECK: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_DOUBLE_TY]]]*,
// CHECK: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK: [[PRIV_SIVAR_ADDR:%.+]] = alloca i32*,
// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_MAIN_TY]]*, [[S_DOUBLE_TY]]**, i32**, [2 x [[S_DOUBLE_TY]]]**, [2 x i32]**, i32**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]], i32** [[PRIV_T_VAR_ADDR]], [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], i32** [[PRIV_SIVAR_ADDR]])
// CHECK: [[PRIV_VAR:%.+]] = load [[S_DOUBLE_TY]]*, [[S_DOUBLE_TY]]** [[PRIV_VAR_ADDR]],
// CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
// CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_DOUBLE_TY]]]*, [2 x [[S_DOUBLE_TY]]]** [[PRIV_S_ARR_ADDR]],
// CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],
// CHECK: [[PRIV_SIVAR:%.+]] = load i32*, i32** [[PRIV_SIVAR_ADDR]],
// Privates actually are used.
// CHECK-DAG: [[PRIV_VAR]]
// CHECK-DAG: [[PRIV_T_VAR]]
// CHECK-DAG: [[PRIV_S_ARR]]
// CHECK-DAG: [[PRIV_VEC]]
// CHECK_DAG: [[PRIV_SIVAR]]
// CHECK: ret
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[MAIN_DUP]]([[KMP_TASK_MAIN_TY]]* %0, [[KMP_TASK_MAIN_TY]]* %1, i32 %2)
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: getelementptr inbounds [[KMP_TASK_MAIN_TY]], [[KMP_TASK_MAIN_TY]]* %{{.+}}, i32 0, i32 1
// CHECK: getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* %{{.+}}, i32 0, i32 0
// CHECK: getelementptr inbounds [2 x [[S_DOUBLE_TY]]], [2 x [[S_DOUBLE_TY]]]* %{{.+}}, i32 0, i32 0
// CHECK: getelementptr inbounds [[S_DOUBLE_TY]], [[S_DOUBLE_TY]]* %{{.+}}, i64 2
// CHECK: br label %
// CHECK: phi [[S_DOUBLE_TY]]*
// CHECK: call {{.*}} [[S_DOUBLE_TY_DEF_CONSTR]]([[S_DOUBLE_TY]]*
// CHECK: getelementptr inbounds [[S_DOUBLE_TY]], [[S_DOUBLE_TY]]* %{{.+}}, i64 1
// CHECK: icmp eq [[S_DOUBLE_TY]]* %
// CHECK: br i1 %
// CHECK: getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* %{{.+}}, i32 0, i32 1
// CHECK: call {{.*}} [[S_DOUBLE_TY_DEF_CONSTR]]([[S_DOUBLE_TY]]*
// CHECK: ret void
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal i32 [[DESTRUCTORS]](i32 %0, [[KMP_TASK_MAIN_TY]]* noalias %1)
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: [[PRIVATES:%.+]] = getelementptr inbounds [[KMP_TASK_MAIN_TY]], [[KMP_TASK_MAIN_TY]]* [[RES_KMP_TASK:%.+]], i{{[0-9]+}} 0, i{{[0-9]+}} 1
// CHECK: [[PRIVATE_S_ARR_REF:%.+]] = getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 0
// CHECK: [[PRIVATE_VAR_REF:%.+]] = getelementptr inbounds [[PRIVATES_MAIN_TY]], [[PRIVATES_MAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 1
// CHECK: call void [[S_DOUBLE_TY_DESTR]]([[S_DOUBLE_TY]]* [[PRIVATE_VAR_REF]])
// CHECK: getelementptr inbounds [2 x [[S_DOUBLE_TY]]], [2 x [[S_DOUBLE_TY]]]* [[PRIVATE_S_ARR_REF]], i{{.+}} 0, i{{.+}} 0
// CHECK: getelementptr inbounds [[S_DOUBLE_TY]], [[S_DOUBLE_TY]]* %{{.+}}, i{{.+}} 2
// CHECK: [[PRIVATE_S_ARR_ELEM_REF:%.+]] = getelementptr inbounds [[S_DOUBLE_TY]], [[S_DOUBLE_TY]]* %{{.+}}, i{{.+}} -1
// CHECK: call void [[S_DOUBLE_TY_DESTR]]([[S_DOUBLE_TY]]* [[PRIVATE_S_ARR_ELEM_REF]])
// CHECK: icmp eq
// CHECK: br i1
// CHECK: ret i32
// CHECK: define {{.*}} i{{[0-9]+}} [[TMAIN_INT]]()
// CHECK: [[TEST:%.+]] = alloca [[S_INT_TY]],
// CHECK: [[T_VAR_ADDR:%.+]] = alloca i32,
// CHECK: [[VEC_ADDR:%.+]] = alloca [2 x i32],
// CHECK: [[S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]],
// CHECK: [[VAR_ADDR:%.+]] = alloca [[S_INT_TY]],
// CHECK: [[GTID:%.+]] = call i32 @__kmpc_global_thread_num([[LOC:%.+]])
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call {{.*}} [[S_INT_TY_DEF_CONSTR:@.+]]([[S_INT_TY]]* [[TEST]])
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// Do not store original variables in capture struct.
// CHECK-NOT: getelementptr inbounds [[CAP_TMAIN_TY]],
// Allocate task.
// Returns struct kmp_task_t {
// [[KMP_TASK_T_TY]] task_data;
// [[KMP_TASK_TMAIN_TY]] privates;
// };
[OPENMP 4.0] Fixed codegen for destructors in task-based directives. If private variables require destructors call at the deletion of the task, additional flag in task flags must be set. Patch fixes this problem. llvm-svn: 269039
2016-05-10 18:36:51 +08:00
// CHECK: [[RES:%.+]] = call i8* @__kmpc_omp_task_alloc([[LOC]], i32 [[GTID]], i32 9, i64 256, i64 1, i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_TMAIN_TY]]*)* [[TASK_ENTRY:@[^ ]+]] to i32 (i32, i8*)*))
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: [[RES_KMP_TASK:%.+]] = bitcast i8* [[RES]] to [[KMP_TASK_TMAIN_TY]]*
// CHECK: [[TASK:%.+]] = getelementptr inbounds [[KMP_TASK_TMAIN_TY]], [[KMP_TASK_TMAIN_TY]]* [[RES_KMP_TASK]], i{{[0-9]+}} 0, i{{[0-9]+}} 0
// Initialize kmp_task_t->privates with default values (no init for simple types, default constructors for classes).
// CHECK: [[PRIVATES:%.+]] = getelementptr inbounds [[KMP_TASK_TMAIN_TY]], [[KMP_TASK_TMAIN_TY]]* [[RES_KMP_TASK]], i{{[0-9]+}} 0, i{{[0-9]+}} 2
// Constructors for s_arr and var.
// a_arr;
// CHECK: [[PRIVATE_S_ARR_REF:%.+]] = getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{[0-9]+}} 0, i{{[0-9]+}} 2
// CHECK: getelementptr inbounds [2 x [[S_INT_TY]]], [2 x [[S_INT_TY]]]* [[PRIVATE_S_ARR_REF]], i{{.+}} 0, i{{.+}} 0
// CHECK: getelementptr inbounds [[S_INT_TY]], [[S_INT_TY]]* %{{.+}}, i{{.+}} 2
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void [[S_INT_TY_DEF_CONSTR]]([[S_INT_TY]]* [[S_ARR_CUR:%.+]])
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: getelementptr inbounds [[S_INT_TY]], [[S_INT_TY]]* [[S_ARR_CUR]], i{{.+}} 1
// CHECK: icmp eq
// CHECK: br i1
// var;
// CHECK: [[PRIVATE_VAR_REF:%.+]] = getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 3
Revert "[CodeGenCXX] Treat 'this' as noalias in constructors" This reverts commit https://reviews.llvm.org/rL344150 which causes MachineOutliner related failures on the ppc64le multistage buildbot. llvm-svn: 344526
2018-10-15 23:43:00 +08:00
// CHECK: call void [[S_INT_TY_DEF_CONSTR]]([[S_INT_TY]]* [[PRIVATE_VAR_REF:%.+]])
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// Provide pointer to destructor function, which will destroy private variables at the end of the task.
// CHECK: [[DESTRUCTORS_REF:%.+]] = getelementptr inbounds [[KMP_TASK_T_TY]], [[KMP_TASK_T_TY]]* [[TASK]], i{{.+}} 0, i{{.+}} 3
[OPENMP 4.5] Fixed codegen for 'priority' and destructors in task-based directives. 'kmp_task_t' record type added a new field for 'priority' clause and changed the representation of pointer to destructors for privates used within loop-based directives. Old representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_routine_entry_t destructors; /* pointer to function to invoke deconstructors of firstprivate C++ objects */ /* private vars */ } kmp_task_t; New representation: typedef struct kmp_task { /* GEH: Shouldn't this be aligned somehow? */ void *shareds; /**< pointer to block of pointers to shared vars */ kmp_routine_entry_t routine; /**< pointer to routine to call for executing task */ kmp_int32 part_id; /**< part id for the task */ kmp_cmplrdata_t data1; /* Two known optional additions: destructors and priority */ kmp_cmplrdata_t data2; /* Process destructors first, priority second */ /* future data */ /* private vars */ } kmp_task_t; Also excessive initialization of 'destructors' fields to 'null' was removed from codegen if it is known that no destructors shal be used. Currently a special bit is used in 'kmp_tasking_flags_t' bitfields ('destructors_thunk' bitfield). llvm-svn: 271201
2016-05-30 17:06:50 +08:00
// CHECK: [[DESTRUCTORS_PTR:%.+]] = bitcast %union{{.+}}* [[DESTRUCTORS_REF]] to i32 (i32, i8*)**
// CHECK: store i32 (i32, i8*)* bitcast (i32 (i32, [[KMP_TASK_TMAIN_TY]]*)* [[DESTRUCTORS:@.+]] to i32 (i32, i8*)*), i32 (i32, i8*)** [[DESTRUCTORS_PTR]],
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// Start task.
Do not always request an implicit taskgroup region inside the kmpc_taskloop function Summary: For the following code: ``` int i; #pragma omp taskloop for (i = 0; i < 100; ++i) {} #pragma omp taskloop nogroup for (i = 0; i < 100; ++i) {} ``` Clang emits the following LLVM IR: ``` ... call void @__kmpc_taskgroup(%struct.ident_t* @0, i32 %0) %2 = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 %0, i32 1, i64 80, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @.omp_task_entry. to i32 (i32, i8*)*)) ... call void @__kmpc_taskloop(%struct.ident_t* @0, i32 %0, i8* %2, i32 1, i64* %8, i64* %9, i64 %13, i32 0, i32 0, i64 0, i8* null) call void @__kmpc_end_taskgroup(%struct.ident_t* @0, i32 %0) ... %15 = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @0, i32 %0, i32 1, i64 80, i64 8, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates.1*)* @.omp_task_entry..2 to i32 (i32, i8*)*)) ... call void @__kmpc_taskloop(%struct.ident_t* @0, i32 %0, i8* %15, i32 1, i64* %21, i64* %22, i64 %26, i32 0, i32 0, i64 0, i8* null) ``` The first set of instructions corresponds to the first taskloop construct. It is important to note that the implicit taskgroup region associated with the taskloop construct has been materialized in our IR: the `__kmpc_taskloop` occurs inside a taskgroup region. Note also that this taskgroup region does not exist in our second taskloop because we are using the `nogroup` clause. The issue here is the 4th argument of the kmpc_taskloop call, starting from the end, is always a zero. Checking the LLVM OpenMP RT implementation, we see that this argument corresponds to the nogroup parameter: ``` void __kmpc_taskloop(ident_t *loc, int gtid, kmp_task_t *task, int if_val, kmp_uint64 *lb, kmp_uint64 *ub, kmp_int64 st, int nogroup, int sched, kmp_uint64 grainsize, void *task_dup); ``` So basically we always tell to the RT to do another taskgroup region. For the first taskloop, this means that we create two taskgroup regions. For the second example, it means that despite the fact we had a nogroup clause we are going to have a taskgroup region, so we unnecessary wait until all descendant tasks have been executed. Reviewers: ABataev Reviewed By: ABataev Subscribers: rogfer01, cfe-commits Differential Revision: https://reviews.llvm.org/D53636 llvm-svn: 345180
2018-10-25 03:06:37 +08:00
// CHECK: call void @__kmpc_taskloop([[LOC]], i32 [[GTID]], i8* [[RES]], i32 1, i64* %{{.+}}, i64* %{{.+}}, i64 %{{.+}}, i32 1, i32 0, i64 0, i8* bitcast (void ([[KMP_TASK_TMAIN_TY]]*, [[KMP_TASK_TMAIN_TY]]*, i32)* [[TMAIN_DUP:@.+]] to i8*))
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// No destructors must be called for private copies of s_arr and var.
// CHECK-NOT: getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 2
// CHECK-NOT: getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 3
// CHECK: call void [[S_INT_TY_DESTR:@.+]]([[S_INT_TY]]*
// CHECK-NOT: getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 2
// CHECK-NOT: getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 3
// CHECK: ret
//
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[PRIVATES_MAP_FN:@.+]]([[PRIVATES_TMAIN_TY]]* noalias %0, i32** noalias %1, [2 x i32]** noalias %2, [2 x [[S_INT_TY]]]** noalias %3, [[S_INT_TY]]** noalias %4)
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: [[PRIVATES:%.+]] = load [[PRIVATES_TMAIN_TY]]*, [[PRIVATES_TMAIN_TY]]**
// CHECK: [[PRIV_T_VAR:%.+]] = getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i32 0, i32 0
// CHECK: [[ARG1:%.+]] = load i32**, i32*** %{{.+}},
// CHECK: store i32* [[PRIV_T_VAR]], i32** [[ARG1]],
// CHECK: [[PRIV_VEC:%.+]] = getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i32 0, i32 1
// CHECK: [[ARG2:%.+]] = load [2 x i32]**, [2 x i32]*** %{{.+}},
// CHECK: store [2 x i32]* [[PRIV_VEC]], [2 x i32]** [[ARG2]],
// CHECK: [[PRIV_S_VAR:%.+]] = getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i32 0, i32 2
// CHECK: [[ARG3:%.+]] = load [2 x [[S_INT_TY]]]**, [2 x [[S_INT_TY]]]*** %{{.+}},
// CHECK: store [2 x [[S_INT_TY]]]* [[PRIV_S_VAR]], [2 x [[S_INT_TY]]]** [[ARG3]],
// CHECK: [[PRIV_VAR:%.+]] = getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i32 0, i32 3
// CHECK: [[ARG4:%.+]] = load [[S_INT_TY]]**, [[S_INT_TY]]*** {{.+}},
// CHECK: store [[S_INT_TY]]* [[PRIV_VAR]], [[S_INT_TY]]** [[ARG4]],
// CHECK: ret void
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal i32 [[TASK_ENTRY]](i32 %0, [[KMP_TASK_TMAIN_TY]]* noalias %1)
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: alloca i32*,
// CHECK-DAG: [[PRIV_T_VAR_ADDR:%.+]] = alloca i32*,
// CHECK-DAG: [[PRIV_VEC_ADDR:%.+]] = alloca [2 x i32]*,
// CHECK-DAG: [[PRIV_S_ARR_ADDR:%.+]] = alloca [2 x [[S_INT_TY]]]*,
// CHECK-DAG: [[PRIV_VAR_ADDR:%.+]] = alloca [[S_INT_TY]]*,
// CHECK: store void (i8*, ...)* bitcast (void ([[PRIVATES_TMAIN_TY]]*, i32**, [2 x i32]**, [2 x [[S_INT_TY]]]**, [[S_INT_TY]]**)* [[PRIVATES_MAP_FN]] to void (i8*, ...)*), void (i8*, ...)** [[MAP_FN_ADDR:%.+]],
// CHECK: [[MAP_FN:%.+]] = load void (i8*, ...)*, void (i8*, ...)** [[MAP_FN_ADDR]],
// CHECK: call void (i8*, ...) [[MAP_FN]](i8* %{{.+}}, i32** [[PRIV_T_VAR_ADDR]], [2 x i32]** [[PRIV_VEC_ADDR]], [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]], [[S_INT_TY]]** [[PRIV_VAR_ADDR]])
// CHECK: [[PRIV_T_VAR:%.+]] = load i32*, i32** [[PRIV_T_VAR_ADDR]],
// CHECK: [[PRIV_VEC:%.+]] = load [2 x i32]*, [2 x i32]** [[PRIV_VEC_ADDR]],
// CHECK: [[PRIV_S_ARR:%.+]] = load [2 x [[S_INT_TY]]]*, [2 x [[S_INT_TY]]]** [[PRIV_S_ARR_ADDR]],
// CHECK: [[PRIV_VAR:%.+]] = load [[S_INT_TY]]*, [[S_INT_TY]]** [[PRIV_VAR_ADDR]],
// Privates actually are used.
// CHECK-DAG: [[PRIV_VAR]]
// CHECK-DAG: [[PRIV_T_VAR]]
// CHECK-DAG: [[PRIV_S_ARR]]
// CHECK-DAG: [[PRIV_VEC]]
// CHECK: ret
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal void [[TMAIN_DUP]]([[KMP_TASK_TMAIN_TY]]* %0, [[KMP_TASK_TMAIN_TY]]* %1, i32 %2)
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: getelementptr inbounds [[KMP_TASK_TMAIN_TY]], [[KMP_TASK_TMAIN_TY]]* %{{.+}}, i32 0, i32 2
// CHECK: getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* %{{.+}}, i32 0, i32 2
// CHECK: getelementptr inbounds [2 x [[S_INT_TY]]], [2 x [[S_INT_TY]]]* %{{.+}}, i32 0, i32 0
// CHECK: getelementptr inbounds [[S_INT_TY]], [[S_INT_TY]]* %{{.+}}, i64 2
// CHECK: br label %
// CHECK: phi [[S_INT_TY]]*
// CHECK: call {{.*}} [[S_INT_TY_DEF_CONSTR]]([[S_INT_TY]]*
// CHECK: getelementptr inbounds [[S_INT_TY]], [[S_INT_TY]]* %{{.+}}, i64 1
// CHECK: icmp eq [[S_INT_TY]]* %
// CHECK: br i1 %
// CHECK: getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* %{{.+}}, i32 0, i32 3
// CHECK: call {{.*}} [[S_INT_TY_DEF_CONSTR]]([[S_INT_TY]]*
// CHECK: ret void
IR: print value numbers for unnamed function arguments For consistency with normal instructions and clarity when reading IR, it's best to print the %0, %1, ... names of function arguments in definitions. Also modifies the parser to accept IR in that form for obvious reasons. llvm-svn: 367755
2019-08-03 22:28:34 +08:00
// CHECK: define internal i32 [[DESTRUCTORS]](i32 %0, [[KMP_TASK_TMAIN_TY]]* noalias %1)
[OPENMP 4.5] Tests for 'private|firstprivates' clauses in 'taskloop' directive. Added tests for codegen for private|firstprivate clauses in taskloop-based directives. llvm-svn: 268729
2016-05-06 20:04:14 +08:00
// CHECK: [[PRIVATES:%.+]] = getelementptr inbounds [[KMP_TASK_TMAIN_TY]], [[KMP_TASK_TMAIN_TY]]* [[RES_KMP_TASK:%.+]], i{{[0-9]+}} 0, i{{[0-9]+}} 2
// CHECK: [[PRIVATE_S_ARR_REF:%.+]] = getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 2
// CHECK: [[PRIVATE_VAR_REF:%.+]] = getelementptr inbounds [[PRIVATES_TMAIN_TY]], [[PRIVATES_TMAIN_TY]]* [[PRIVATES]], i{{.+}} 0, i{{.+}} 3
// CHECK: call void [[S_INT_TY_DESTR]]([[S_INT_TY]]* [[PRIVATE_VAR_REF]])
// CHECK: getelementptr inbounds [2 x [[S_INT_TY]]], [2 x [[S_INT_TY]]]* [[PRIVATE_S_ARR_REF]], i{{.+}} 0, i{{.+}} 0
// CHECK: getelementptr inbounds [[S_INT_TY]], [[S_INT_TY]]* %{{.+}}, i{{.+}} 2
// CHECK: [[PRIVATE_S_ARR_ELEM_REF:%.+]] = getelementptr inbounds [[S_INT_TY]], [[S_INT_TY]]* %{{.+}}, i{{.+}} -1
// CHECK: call void [[S_INT_TY_DESTR]]([[S_INT_TY]]* [[PRIVATE_S_ARR_ELEM_REF]])
// CHECK: icmp eq
// CHECK: br i1
// CHECK: ret i32
#endif
#else
// ARRAY-LABEL: array_func
struct St {
int a, b;
St() : a(0), b(0) {}
St &operator=(const St &) { return *this; };
~St() {}
};
void array_func(int n, float a[n], St s[2]) {
// ARRAY: call i8* @__kmpc_omp_task_alloc(
// ARRAY: call void @__kmpc_taskloop(
// ARRAY: store float** %{{.+}}, float*** %{{.+}},
// ARRAY: store %struct.St** %{{.+}}, %struct.St*** %{{.+}},
#pragma omp taskloop simd private(a, s)
for (int i = 0; i < 10; ++i)
;
}
#endif