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/sections_reduction_codegen.cpp

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

2162 lines
151 KiB
C++
Raw Normal View History

[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --include-generated-funcs --replace-value-regex "__omp_offloading_[0-9a-z]+_[0-9a-z]+" "reduction_size[.].+[.]" "pl_cond[.].+[.|,]" --prefix-filecheck-ir-name _
[OpaquePtrs][Clang] Add -no-opaque-pointers to tests (NFC) This adds -no-opaque-pointers to clang tests whose output will change when opaque pointers are enabled by default. This is intended to be part of the migration approach described in https://discourse.llvm.org/t/enabling-opaque-pointers-by-default/61322/9. The patch has been produced by replacing %clang_cc1 with %clang_cc1 -no-opaque-pointers for tests that fail with opaque pointers enabled. Worth noting that this doesn't cover all tests, there's a remaining ~40 tests not using %clang_cc1 that will need a followup change. Differential Revision: https://reviews.llvm.org/D123115
2022-04-07 18:03:55 +08:00
// RUN: %clang_cc1 -no-opaque-pointers -verify -fopenmp -x c++ -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK1
// RUN: %clang_cc1 -no-opaque-pointers -fopenmp -x c++ -std=c++11 -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -no-opaque-pointers -fopenmp -x c++ -triple x86_64-apple-darwin10 -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK2
// RUN: %clang_cc1 -no-opaque-pointers -verify -fopenmp -x c++ -std=c++11 -DLAMBDA -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK3
// RUN: %clang_cc1 -no-opaque-pointers -verify -fopenmp -x c++ -fblocks -DBLOCKS -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck -allow-deprecated-dag-overlap %s --check-prefix=CHECK4
// RUN: %clang_cc1 -no-opaque-pointers -verify -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -no-opaque-pointers -fopenmp-simd -x c++ -std=c++11 -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -no-opaque-pointers -fopenmp-simd -x c++ -triple x86_64-apple-darwin10 -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -no-opaque-pointers -verify -fopenmp-simd -x c++ -std=c++11 -DLAMBDA -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
// RUN: %clang_cc1 -no-opaque-pointers -verify -fopenmp-simd -x c++ -fblocks -DBLOCKS -triple x86_64-apple-darwin10 -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
[OPENMP] Codegen for 'reduction' clause in 'sections' directive. Emit a code for reduction clause. Next code should be emitted for reductions: static kmp_critical_name lock = { 0 }; void reduce_func(void *lhs[<n>], void *rhs[<n>]) { *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]); ... *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1], *(Type<n>-1*)rhs[<n>-1]); } ... void *RedList[<n>] = {&<RHSExprs>[0], ..., &<RHSExprs>[<n>-1]}; switch (__kmpc_reduce{_nowait}(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>)) { case 1: <LHSExprs>[0] = ReductionOperation0(*<LHSExprs>[0], *<RHSExprs>[0]); ... <LHSExprs>[<n>-1] = ReductionOperation<n>-1(*<LHSExprs>[<n>-1], *<RHSExprs>[<n>-1]); __kmpc_end_reduce{_nowait}(<loc>, <gtid>, &<lock>); break; case 2: Atomic(<LHSExprs>[0] = ReductionOperation0(*<LHSExprs>[0], *<RHSExprs>[0])); ... Atomic(<LHSExprs>[<n>-1] = ReductionOperation<n>-1(*<LHSExprs>[<n>-1], *<RHSExprs>[<n>-1])); break; default:; } Reduction variables are a kind of a private variables, they have private copies, but initial values are chosen in accordance with the reduction operation. If sections directive has only single section, then original shared variables are used instead with barrier at the end of the directive. Differential Revision: http://reviews.llvm.org/D9242 llvm-svn: 235835
2015-04-27 13:04:13 +08:00
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
volatile double g;
template <class T>
struct S {
T f;
S(T a) : f(a + g) {}
S() : f(g) {}
operator T() { return T(); }
S &operator&(const S &) { return *this; }
~S() {}
};
template <typename T>
T tmain() {
T t;
S<T> test;
T t_var = T(), t_var1;
T vec[] = {1, 2};
S<T> s_arr[] = {1, 2};
S<T> var(3), var1;
#pragma omp parallel
#pragma omp sections reduction(+:t_var) reduction(&:var) reduction(&& : var1) reduction(min: t_var1) nowait
{
vec[0] = t_var;
#pragma omp section
s_arr[0] = var;
}
return T();
}
int main() {
#ifdef LAMBDA
[&]() {
#pragma omp parallel
#pragma omp sections reduction(+:g)
{
// Reduction list for runtime.
g = 1;
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
[OPENMP] Codegen for 'reduction' clause in 'sections' directive. Emit a code for reduction clause. Next code should be emitted for reductions: static kmp_critical_name lock = { 0 }; void reduce_func(void *lhs[<n>], void *rhs[<n>]) { *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]); ... *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1], *(Type<n>-1*)rhs[<n>-1]); } ... void *RedList[<n>] = {&<RHSExprs>[0], ..., &<RHSExprs>[<n>-1]}; switch (__kmpc_reduce{_nowait}(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>)) { case 1: <LHSExprs>[0] = ReductionOperation0(*<LHSExprs>[0], *<RHSExprs>[0]); ... <LHSExprs>[<n>-1] = ReductionOperation<n>-1(*<LHSExprs>[<n>-1], *<RHSExprs>[<n>-1]); __kmpc_end_reduce{_nowait}(<loc>, <gtid>, &<lock>); break; case 2: Atomic(<LHSExprs>[0] = ReductionOperation0(*<LHSExprs>[0], *<RHSExprs>[0])); ... Atomic(<LHSExprs>[<n>-1] = ReductionOperation<n>-1(*<LHSExprs>[<n>-1], *<RHSExprs>[<n>-1])); break; default:; } Reduction variables are a kind of a private variables, they have private copies, but initial values are chosen in accordance with the reduction operation. If sections directive has only single section, then original shared variables are used instead with barrier at the end of the directive. Differential Revision: http://reviews.llvm.org/D9242 llvm-svn: 235835
2015-04-27 13:04:13 +08:00
#pragma omp section
[&]() {
g = 2;
}();
}
}();
return 0;
#elif defined(BLOCKS)
^{
#pragma omp parallel
#pragma omp sections reduction(-:g)
{
// Reduction list for runtime.
g = 1;
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
[OPENMP] Codegen for 'reduction' clause in 'sections' directive. Emit a code for reduction clause. Next code should be emitted for reductions: static kmp_critical_name lock = { 0 }; void reduce_func(void *lhs[<n>], void *rhs[<n>]) { *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]); ... *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1], *(Type<n>-1*)rhs[<n>-1]); } ... void *RedList[<n>] = {&<RHSExprs>[0], ..., &<RHSExprs>[<n>-1]}; switch (__kmpc_reduce{_nowait}(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>)) { case 1: <LHSExprs>[0] = ReductionOperation0(*<LHSExprs>[0], *<RHSExprs>[0]); ... <LHSExprs>[<n>-1] = ReductionOperation<n>-1(*<LHSExprs>[<n>-1], *<RHSExprs>[<n>-1]); __kmpc_end_reduce{_nowait}(<loc>, <gtid>, &<lock>); break; case 2: Atomic(<LHSExprs>[0] = ReductionOperation0(*<LHSExprs>[0], *<RHSExprs>[0])); ... Atomic(<LHSExprs>[<n>-1] = ReductionOperation<n>-1(*<LHSExprs>[<n>-1], *<RHSExprs>[<n>-1])); break; default:; } Reduction variables are a kind of a private variables, they have private copies, but initial values are chosen in accordance with the reduction operation. If sections directive has only single section, then original shared variables are used instead with barrier at the end of the directive. Differential Revision: http://reviews.llvm.org/D9242 llvm-svn: 235835
2015-04-27 13:04:13 +08:00
#pragma omp section
^{
g = 2;
}();
}
}();
return 0;
#else
S<float> test;
float t_var = 0, t_var1;
int vec[] = {1, 2};
S<float> s_arr[] = {1, 2};
S<float> var(3), var1;
#pragma omp parallel
#pragma omp sections reduction(+:t_var) reduction(&:var) reduction(&& : var1) reduction(min: t_var1)
{
{
vec[0] = t_var;
s_arr[0] = var;
vec[1] = t_var1;
s_arr[1] = var1;
}
}
return tmain<int>();
#endif
}
// Reduction list for runtime.
[OPENMP] Outlined function for parallel and other regions with list of captured variables. Currently all variables used in OpenMP regions are captured into a record and passed to outlined functions in this record. It may result in some poor performance because of too complex analysis later in optimization passes. Patch makes to emit outlined functions for parallel-based regions with a list of captured variables. It reduces code for 2*n GEPs, stores and loads at least. Codegen for task-based regions remains unchanged because runtime requires that all captured variables are passed in captured record. llvm-svn: 247251
2015-09-10 16:12:02 +08:00
[OPENMP] Codegen for 'reduction' clause in 'sections' directive. Emit a code for reduction clause. Next code should be emitted for reductions: static kmp_critical_name lock = { 0 }; void reduce_func(void *lhs[<n>], void *rhs[<n>]) { *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]); ... *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1], *(Type<n>-1*)rhs[<n>-1]); } ... void *RedList[<n>] = {&<RHSExprs>[0], ..., &<RHSExprs>[<n>-1]}; switch (__kmpc_reduce{_nowait}(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>)) { case 1: <LHSExprs>[0] = ReductionOperation0(*<LHSExprs>[0], *<RHSExprs>[0]); ... <LHSExprs>[<n>-1] = ReductionOperation<n>-1(*<LHSExprs>[<n>-1], *<RHSExprs>[<n>-1]); __kmpc_end_reduce{_nowait}(<loc>, <gtid>, &<lock>); break; case 2: Atomic(<LHSExprs>[0] = ReductionOperation0(*<LHSExprs>[0], *<RHSExprs>[0])); ... Atomic(<LHSExprs>[<n>-1] = ReductionOperation<n>-1(*<LHSExprs>[<n>-1], *<RHSExprs>[<n>-1])); break; default:; } Reduction variables are a kind of a private variables, they have private copies, but initial values are chosen in accordance with the reduction operation. If sections directive has only single section, then original shared variables are used instead with barrier at the end of the directive. Differential Revision: http://reviews.llvm.org/D9242 llvm-svn: 235835
2015-04-27 13:04:13 +08:00
// For + reduction operation initial value of private variable is 0.
// For & reduction operation initial value of private variable is ones in all bits.
// For && reduction operation initial value of private variable is 1.0.
// For min reduction operation initial value of private variable is largest repesentable value.
// Skip checks for internal operations.
// void *RedList[<n>] = {<ReductionVars>[0], ..., <ReductionVars>[<n>-1]};
// res = __kmpc_reduce_nowait(<loc>, <gtid>, <n>, sizeof(RedList), RedList, reduce_func, &<lock>);
// switch(res)
// case 1:
// t_var += t_var_reduction;
// var = var.operator &(var_reduction);
// var1 = var1.operator &&(var1_reduction);
// t_var1 = min(t_var1, t_var1_reduction);
// __kmpc_end_reduce_nowait(<loc>, <gtid>, &<lock>);
// break;
// case 2:
// t_var += t_var_reduction;
// var = var.operator &(var_reduction);
// var1 = var1.operator &&(var1_reduction);
// t_var1 = min(t_var1, t_var1_reduction);
// break;
// void reduce_func(void *lhs[<n>], void *rhs[<n>]) {
// *(Type0*)lhs[0] = ReductionOperation0(*(Type0*)lhs[0], *(Type0*)rhs[0]);
// ...
// *(Type<n>-1*)lhs[<n>-1] = ReductionOperation<n>-1(*(Type<n>-1*)lhs[<n>-1],
// *(Type<n>-1*)rhs[<n>-1]);
// }
// t_var_lhs = (i{{[0-9]+}}*)lhs[0];
// t_var_rhs = (i{{[0-9]+}}*)rhs[0];
// var_lhs = (S<i{{[0-9]+}}>*)lhs[1];
// var_rhs = (S<i{{[0-9]+}}>*)rhs[1];
// var1_lhs = (S<i{{[0-9]+}}>*)lhs[2];
// var1_rhs = (S<i{{[0-9]+}}>*)rhs[2];
// t_var1_lhs = (i{{[0-9]+}}*)lhs[3];
// t_var1_rhs = (i{{[0-9]+}}*)rhs[3];
// t_var_lhs += t_var_rhs;
// var_lhs = var_lhs.operator &(var_rhs);
// var1_lhs = var1_lhs.operator &&(var1_rhs);
// t_var1_lhs = min(t_var1_lhs, t_var1_rhs);
#endif
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-LABEL: define {{[^@]+}}@main
// CHECK1-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[TEST:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK1-NEXT: [[T_VAR:%.*]] = alloca float, align 4
// CHECK1-NEXT: [[T_VAR1:%.*]] = alloca float, align 4
// CHECK1-NEXT: [[VEC:%.*]] = alloca [2 x i32], align 4
// CHECK1-NEXT: [[S_ARR:%.*]] = alloca [2 x %struct.S], align 4
// CHECK1-NEXT: [[VAR:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK1-NEXT: [[VAR1:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK1-NEXT: store i32 0, i32* [[RETVAL]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TEST]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: store float 0.000000e+00, float* [[T_VAR]], align 4
// CHECK1-NEXT: [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const.main.vec to i8*), i64 8, i1 false)
// CHECK1-NEXT: [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i64 0, i64 0
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], float noundef 1.000000e+00)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYINIT_BEGIN]], i64 1
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], float noundef 2.000000e+00)
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR]], float noundef 3.000000e+00)
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR1]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3:[0-9]+]], i32 6, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, float*, %struct.S*, %struct.S*, float*, [2 x i32]*, [2 x %struct.S]*)* @.omp_outlined. to void (i32*, i32*, ...)*), float* [[T_VAR]], %struct.S* [[VAR]], %struct.S* [[VAR1]], float* [[T_VAR1]], [2 x i32]* [[VEC]], [2 x %struct.S]* [[S_ARR]])
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK1-NEXT: [[CALL:%.*]] = call noundef i32 @_Z5tmainIiET_v()
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: store i32 [[CALL]], i32* [[RETVAL]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR1]]) #[[ATTR4:[0-9]+]]
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i32 0, i32 0
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 2
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK1: arraydestroy.body:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP1]], [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN]]
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK1: arraydestroy.done1:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP2:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK1-NEXT: ret i32 [[TMP2]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfEC2Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS1]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ef
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]], float noundef [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfEC2Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS1]], float noundef [[TMP0]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined.
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK1-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], float* noundef nonnull align 4 dereferenceable(4) [[T_VAR:%.*]], %struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR:%.*]], %struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR1:%.*]], float* noundef nonnull align 4 dereferenceable(4) [[T_VAR1:%.*]], [2 x i32]* noundef nonnull align 4 dereferenceable(8) [[VEC:%.*]], [2 x %struct.S]* noundef nonnull align 4 dereferenceable(8) [[S_ARR:%.*]]) #[[ATTR3:[0-9]+]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[T_VAR_ADDR:%.*]] = alloca float*, align 8
// CHECK1-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: [[VAR1_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: [[T_VAR1_ADDR:%.*]] = alloca float*, align 8
// CHECK1-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 8
// CHECK1-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S]*, align 8
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[DOTOMP_SECTIONS_LB_:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_SECTIONS_UB_:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_SECTIONS_ST_:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_SECTIONS_IL_:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_SECTIONS_IV_:%.*]] = alloca i32, align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[T_VAR2:%.*]] = alloca float, align 4
// CHECK1-NEXT: [[VAR3:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK1-NEXT: [[VAR14:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK1-NEXT: [[T_VAR15:%.*]] = alloca float, align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [4 x i8*], align 8
// CHECK1-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK1-NEXT: [[ATOMIC_TEMP:%.*]] = alloca float, align 4
// CHECK1-NEXT: [[TMP:%.*]] = alloca float, align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[REF_TMP17:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK1-NEXT: [[ATOMIC_TEMP27:%.*]] = alloca float, align 4
// CHECK1-NEXT: [[_TMP28:%.*]] = alloca float, align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: store float* [[T_VAR]], float** [[T_VAR_ADDR]], align 8
// CHECK1-NEXT: store %struct.S* [[VAR]], %struct.S** [[VAR_ADDR]], align 8
// CHECK1-NEXT: store %struct.S* [[VAR1]], %struct.S** [[VAR1_ADDR]], align 8
// CHECK1-NEXT: store float* [[T_VAR1]], float** [[T_VAR1_ADDR]], align 8
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 8
// CHECK1-NEXT: store [2 x %struct.S]* [[S_ARR]], [2 x %struct.S]** [[S_ARR_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load float*, float** [[T_VAR_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load %struct.S*, %struct.S** [[VAR_ADDR]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load %struct.S*, %struct.S** [[VAR1_ADDR]], align 8
// CHECK1-NEXT: [[TMP3:%.*]] = load float*, float** [[T_VAR1_ADDR]], align 8
// CHECK1-NEXT: [[TMP4:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 8
// CHECK1-NEXT: [[TMP5:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[S_ARR_ADDR]], align 8
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_LB_]], align 4
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_SECTIONS_ST_]], align 4
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_IL_]], align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: store float 0.000000e+00, float* [[T_VAR2]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR3]])
// CHECK1-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR14]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: store float 0x47EFFFFFE0000000, float* [[T_VAR15]], align 4
// CHECK1-NEXT: [[TMP6:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP7:%.*]] = load i32, i32* [[TMP6]], align 4
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP7]], i32 34, i32* [[DOTOMP_SECTIONS_IL_]], i32* [[DOTOMP_SECTIONS_LB_]], i32* [[DOTOMP_SECTIONS_UB_]], i32* [[DOTOMP_SECTIONS_ST_]], i32 1, i32 1)
// CHECK1-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK1-NEXT: [[TMP9:%.*]] = icmp slt i32 [[TMP8]], 0
// CHECK1-NEXT: [[TMP10:%.*]] = select i1 [[TMP9]], i32 [[TMP8]], i32 0
// CHECK1-NEXT: store i32 [[TMP10]], i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK1-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_LB_]], align 4
// CHECK1-NEXT: store i32 [[TMP11]], i32* [[DOTOMP_SECTIONS_IV_]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK1: omp.inner.for.cond:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK1-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK1-NEXT: [[CMP:%.*]] = icmp sle i32 [[TMP12]], [[TMP13]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br i1 [[CMP]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
// CHECK1: omp.inner.for.body:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK1-NEXT: switch i32 [[TMP14]], label [[DOTOMP_SECTIONS_EXIT:%.*]] [
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: i32 0, label [[DOTOMP_SECTIONS_CASE:%.*]]
// CHECK1-NEXT: ]
// CHECK1: .omp.sections.case:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP15:%.*]] = load float, float* [[T_VAR2]], align 4
// CHECK1-NEXT: [[CONV:%.*]] = fptosi float [[TMP15]] to i32
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP4]], i64 0, i64 0
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: store i32 [[CONV]], i32* [[ARRAYIDX]], align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[TMP5]], i64 0, i64 0
// CHECK1-NEXT: [[TMP16:%.*]] = bitcast %struct.S* [[ARRAYIDX6]] to i8*
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast %struct.S* [[VAR3]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP16]], i8* align 4 [[TMP17]], i64 4, i1 false)
// CHECK1-NEXT: [[TMP18:%.*]] = load float, float* [[T_VAR15]], align 4
// CHECK1-NEXT: [[CONV7:%.*]] = fptosi float [[TMP18]] to i32
// CHECK1-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP4]], i64 0, i64 1
// CHECK1-NEXT: store i32 [[CONV7]], i32* [[ARRAYIDX8]], align 4
// CHECK1-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[TMP5]], i64 0, i64 1
// CHECK1-NEXT: [[TMP19:%.*]] = bitcast %struct.S* [[ARRAYIDX9]] to i8*
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast %struct.S* [[VAR14]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP19]], i8* align 4 [[TMP20]], i64 4, i1 false)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[DOTOMP_SECTIONS_EXIT]]
// CHECK1: .omp.sections.exit:
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK1: omp.inner.for.inc:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK1-NEXT: [[INC:%.*]] = add nsw i32 [[TMP21]], 1
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: store i32 [[INC]], i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK1: omp.inner.for.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP7]])
// CHECK1-NEXT: [[TMP22:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
// CHECK1-NEXT: [[TMP23:%.*]] = bitcast float* [[T_VAR2]] to i8*
// CHECK1-NEXT: store i8* [[TMP23]], i8** [[TMP22]], align 8
// CHECK1-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
// CHECK1-NEXT: [[TMP25:%.*]] = bitcast %struct.S* [[VAR3]] to i8*
// CHECK1-NEXT: store i8* [[TMP25]], i8** [[TMP24]], align 8
// CHECK1-NEXT: [[TMP26:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
// CHECK1-NEXT: [[TMP27:%.*]] = bitcast %struct.S* [[VAR14]] to i8*
// CHECK1-NEXT: store i8* [[TMP27]], i8** [[TMP26]], align 8
// CHECK1-NEXT: [[TMP28:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 3
// CHECK1-NEXT: [[TMP29:%.*]] = bitcast float* [[T_VAR15]] to i8*
// CHECK1-NEXT: store i8* [[TMP29]], i8** [[TMP28]], align 8
// CHECK1-NEXT: [[TMP30:%.*]] = bitcast [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
// CHECK1-NEXT: [[TMP31:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP7]], i32 4, i64 32, i8* [[TMP30]], void (i8*, i8*)* @.omp.reduction.reduction_func, [8 x i32]* @.gomp_critical_user_.reduction.var)
// CHECK1-NEXT: switch i32 [[TMP31]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
// CHECK1-NEXT: ]
// CHECK1: .omp.reduction.case1:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP32:%.*]] = load float, float* [[TMP0]], align 4
// CHECK1-NEXT: [[TMP33:%.*]] = load float, float* [[T_VAR2]], align 4
// CHECK1-NEXT: [[ADD:%.*]] = fadd float [[TMP32]], [[TMP33]]
// CHECK1-NEXT: store float [[ADD]], float* [[TMP0]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL:%.*]] = call noundef nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP1]], %struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR3]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[TMP1]] to i8*
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[CALL]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP34]], i8* align 4 [[TMP35]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL10:%.*]] = call noundef float @_ZN1SIfEcvfEv(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP2]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TOBOOL:%.*]] = fcmp une float [[CALL10]], 0.000000e+00
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
// CHECK1: land.rhs:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL11:%.*]] = call noundef float @_ZN1SIfEcvfEv(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR14]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TOBOOL12:%.*]] = fcmp une float [[CALL11]], 0.000000e+00
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[LAND_END]]
// CHECK1: land.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP36:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE1]] ], [ [[TOBOOL12]], [[LAND_RHS]] ]
// CHECK1-NEXT: [[CONV13:%.*]] = uitofp i1 [[TMP36]] to float
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]], float noundef [[CONV13]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP37:%.*]] = bitcast %struct.S* [[TMP2]] to i8*
// CHECK1-NEXT: [[TMP38:%.*]] = bitcast %struct.S* [[REF_TMP]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP37]], i8* align 4 [[TMP38]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP39:%.*]] = load float, float* [[TMP3]], align 4
// CHECK1-NEXT: [[TMP40:%.*]] = load float, float* [[T_VAR15]], align 4
// CHECK1-NEXT: [[CMP14:%.*]] = fcmp olt float [[TMP39]], [[TMP40]]
// CHECK1-NEXT: br i1 [[CMP14]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1: cond.true:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP41:%.*]] = load float, float* [[TMP3]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[COND_END:%.*]]
// CHECK1: cond.false:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP42:%.*]] = load float, float* [[T_VAR15]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[COND_END]]
// CHECK1: cond.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[COND:%.*]] = phi float [ [[TMP41]], [[COND_TRUE]] ], [ [[TMP42]], [[COND_FALSE]] ]
// CHECK1-NEXT: store float [[COND]], float* [[TMP3]], align 4
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.reduction.var)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK1: .omp.reduction.case2:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP43:%.*]] = load float, float* [[T_VAR2]], align 4
// CHECK1-NEXT: [[TMP44:%.*]] = bitcast float* [[TMP0]] to i32*
// CHECK1-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i32, i32* [[TMP44]] monotonic, align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[ATOMIC_CONT:%.*]]
// CHECK1: atomic_cont:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP45:%.*]] = phi i32 [ [[ATOMIC_LOAD]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[TMP53:%.*]], [[ATOMIC_CONT]] ]
// CHECK1-NEXT: [[TMP46:%.*]] = bitcast float* [[ATOMIC_TEMP]] to i32*
// CHECK1-NEXT: [[TMP47:%.*]] = bitcast i32 [[TMP45]] to float
// CHECK1-NEXT: store float [[TMP47]], float* [[TMP]], align 4
// CHECK1-NEXT: [[TMP48:%.*]] = load float, float* [[TMP]], align 4
// CHECK1-NEXT: [[TMP49:%.*]] = load float, float* [[T_VAR2]], align 4
// CHECK1-NEXT: [[ADD15:%.*]] = fadd float [[TMP48]], [[TMP49]]
// CHECK1-NEXT: store float [[ADD15]], float* [[ATOMIC_TEMP]], align 4
// CHECK1-NEXT: [[TMP50:%.*]] = load i32, i32* [[TMP46]], align 4
// CHECK1-NEXT: [[TMP51:%.*]] = bitcast float* [[TMP0]] to i32*
// CHECK1-NEXT: [[TMP52:%.*]] = cmpxchg i32* [[TMP51]], i32 [[TMP45]], i32 [[TMP50]] monotonic monotonic, align 4
// CHECK1-NEXT: [[TMP53]] = extractvalue { i32, i1 } [[TMP52]], 0
// CHECK1-NEXT: [[TMP54:%.*]] = extractvalue { i32, i1 } [[TMP52]], 1
// CHECK1-NEXT: br i1 [[TMP54]], label [[ATOMIC_EXIT:%.*]], label [[ATOMIC_CONT]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1: atomic_exit:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL16:%.*]] = call noundef nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP1]], %struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR3]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP55:%.*]] = bitcast %struct.S* [[TMP1]] to i8*
// CHECK1-NEXT: [[TMP56:%.*]] = bitcast %struct.S* [[CALL16]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP55]], i8* align 4 [[TMP56]], i64 4, i1 false)
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL18:%.*]] = call noundef float @_ZN1SIfEcvfEv(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP2]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TOBOOL19:%.*]] = fcmp une float [[CALL18]], 0.000000e+00
// CHECK1-NEXT: br i1 [[TOBOOL19]], label [[LAND_RHS20:%.*]], label [[LAND_END23:%.*]]
// CHECK1: land.rhs20:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL21:%.*]] = call noundef float @_ZN1SIfEcvfEv(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR14]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TOBOOL22:%.*]] = fcmp une float [[CALL21]], 0.000000e+00
// CHECK1-NEXT: br label [[LAND_END23]]
// CHECK1: land.end23:
// CHECK1-NEXT: [[TMP57:%.*]] = phi i1 [ false, [[ATOMIC_EXIT]] ], [ [[TOBOOL22]], [[LAND_RHS20]] ]
// CHECK1-NEXT: [[CONV24:%.*]] = uitofp i1 [[TMP57]] to float
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[REF_TMP17]], float noundef [[CONV24]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP58:%.*]] = bitcast %struct.S* [[TMP2]] to i8*
// CHECK1-NEXT: [[TMP59:%.*]] = bitcast %struct.S* [[REF_TMP17]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP58]], i8* align 4 [[TMP59]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[REF_TMP17]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
// CHECK1-NEXT: [[TMP60:%.*]] = load float, float* [[T_VAR15]], align 4
// CHECK1-NEXT: [[TMP61:%.*]] = bitcast float* [[TMP3]] to i32*
// CHECK1-NEXT: [[ATOMIC_LOAD25:%.*]] = load atomic i32, i32* [[TMP61]] monotonic, align 4
// CHECK1-NEXT: br label [[ATOMIC_CONT26:%.*]]
// CHECK1: atomic_cont26:
// CHECK1-NEXT: [[TMP62:%.*]] = phi i32 [ [[ATOMIC_LOAD25]], [[LAND_END23]] ], [ [[TMP72:%.*]], [[COND_END32:%.*]] ]
// CHECK1-NEXT: [[TMP63:%.*]] = bitcast float* [[ATOMIC_TEMP27]] to i32*
// CHECK1-NEXT: [[TMP64:%.*]] = bitcast i32 [[TMP62]] to float
// CHECK1-NEXT: store float [[TMP64]], float* [[_TMP28]], align 4
// CHECK1-NEXT: [[TMP65:%.*]] = load float, float* [[_TMP28]], align 4
// CHECK1-NEXT: [[TMP66:%.*]] = load float, float* [[T_VAR15]], align 4
// CHECK1-NEXT: [[CMP29:%.*]] = fcmp olt float [[TMP65]], [[TMP66]]
// CHECK1-NEXT: br i1 [[CMP29]], label [[COND_TRUE30:%.*]], label [[COND_FALSE31:%.*]]
// CHECK1: cond.true30:
// CHECK1-NEXT: [[TMP67:%.*]] = load float, float* [[_TMP28]], align 4
// CHECK1-NEXT: br label [[COND_END32]]
// CHECK1: cond.false31:
// CHECK1-NEXT: [[TMP68:%.*]] = load float, float* [[T_VAR15]], align 4
// CHECK1-NEXT: br label [[COND_END32]]
// CHECK1: cond.end32:
// CHECK1-NEXT: [[COND33:%.*]] = phi float [ [[TMP67]], [[COND_TRUE30]] ], [ [[TMP68]], [[COND_FALSE31]] ]
// CHECK1-NEXT: store float [[COND33]], float* [[ATOMIC_TEMP27]], align 4
// CHECK1-NEXT: [[TMP69:%.*]] = load i32, i32* [[TMP63]], align 4
// CHECK1-NEXT: [[TMP70:%.*]] = bitcast float* [[TMP3]] to i32*
// CHECK1-NEXT: [[TMP71:%.*]] = cmpxchg i32* [[TMP70]], i32 [[TMP62]], i32 [[TMP69]] monotonic monotonic, align 4
// CHECK1-NEXT: [[TMP72]] = extractvalue { i32, i1 } [[TMP71]], 0
// CHECK1-NEXT: [[TMP73:%.*]] = extractvalue { i32, i1 } [[TMP71]], 1
// CHECK1-NEXT: br i1 [[TMP73]], label [[ATOMIC_EXIT34:%.*]], label [[ATOMIC_CONT26]]
// CHECK1: atomic_exit34:
// CHECK1-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.reduction.var)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK1: .omp.reduction.default:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR14]]) #[[ATTR4]]
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR3]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4:[0-9]+]], i32 [[TMP7]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK1-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR5:[0-9]+]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [4 x i8*]*
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [4 x i8*]*
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 0
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to float*
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 0
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to float*
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 1
// CHECK1-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast i8* [[TMP13]] to %struct.S*
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 1
// CHECK1-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to %struct.S*
// CHECK1-NEXT: [[TMP18:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 2
// CHECK1-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to %struct.S*
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 2
// CHECK1-NEXT: [[TMP22:%.*]] = load i8*, i8** [[TMP21]], align 8
// CHECK1-NEXT: [[TMP23:%.*]] = bitcast i8* [[TMP22]] to %struct.S*
// CHECK1-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 3
// CHECK1-NEXT: [[TMP25:%.*]] = load i8*, i8** [[TMP24]], align 8
// CHECK1-NEXT: [[TMP26:%.*]] = bitcast i8* [[TMP25]] to float*
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 3
// CHECK1-NEXT: [[TMP28:%.*]] = load i8*, i8** [[TMP27]], align 8
// CHECK1-NEXT: [[TMP29:%.*]] = bitcast i8* [[TMP28]] to float*
// CHECK1-NEXT: [[TMP30:%.*]] = load float, float* [[TMP11]], align 4
// CHECK1-NEXT: [[TMP31:%.*]] = load float, float* [[TMP8]], align 4
// CHECK1-NEXT: [[ADD:%.*]] = fadd float [[TMP30]], [[TMP31]]
// CHECK1-NEXT: store float [[ADD]], float* [[TMP11]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL:%.*]] = call noundef nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP17]], %struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP14]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TMP32:%.*]] = bitcast %struct.S* [[TMP17]] to i8*
// CHECK1-NEXT: [[TMP33:%.*]] = bitcast %struct.S* [[CALL]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP32]], i8* align 4 [[TMP33]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL2:%.*]] = call noundef float @_ZN1SIfEcvfEv(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP23]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TOBOOL:%.*]] = fcmp une float [[CALL2]], 0.000000e+00
// CHECK1-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
// CHECK1: land.rhs:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL3:%.*]] = call noundef float @_ZN1SIfEcvfEv(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP20]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TOBOOL4:%.*]] = fcmp une float [[CALL3]], 0.000000e+00
// CHECK1-NEXT: br label [[LAND_END]]
// CHECK1: land.end:
// CHECK1-NEXT: [[TMP34:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[TOBOOL4]], [[LAND_RHS]] ]
// CHECK1-NEXT: [[CONV:%.*]] = uitofp i1 [[TMP34]] to float
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]], float noundef [[CONV]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[TMP23]] to i8*
// CHECK1-NEXT: [[TMP36:%.*]] = bitcast %struct.S* [[REF_TMP]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP35]], i8* align 4 [[TMP36]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TMP37:%.*]] = load float, float* [[TMP29]], align 4
// CHECK1-NEXT: [[TMP38:%.*]] = load float, float* [[TMP26]], align 4
// CHECK1-NEXT: [[CMP:%.*]] = fcmp olt float [[TMP37]], [[TMP38]]
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK1: cond.true:
// CHECK1-NEXT: [[TMP39:%.*]] = load float, float* [[TMP29]], align 4
// CHECK1-NEXT: br label [[COND_END:%.*]]
// CHECK1: cond.false:
// CHECK1-NEXT: [[TMP40:%.*]] = load float, float* [[TMP26]], align 4
// CHECK1-NEXT: br label [[COND_END]]
// CHECK1: cond.end:
// CHECK1-NEXT: [[COND:%.*]] = phi float [ [[TMP39]], [[COND_TRUE]] ], [ [[TMP40]], [[COND_FALSE]] ]
// CHECK1-NEXT: store float [[COND]], float* [[TMP29]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEanERKS0_
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP0:%.*]]) #[[ATTR6:[0-9]+]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store %struct.S* [[TMP0]], %struct.S** [[DOTADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: ret %struct.S* [[THIS1]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEcvfEv
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) #[[ATTR6]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: ret float 0.000000e+00
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfED1Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIfED2Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z5tmainIiET_v
// CHECK1-SAME: () #[[ATTR6]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[T:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[TEST:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK1-NEXT: [[T_VAR:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[T_VAR1:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[VEC:%.*]] = alloca [2 x i32], align 4
// CHECK1-NEXT: [[S_ARR:%.*]] = alloca [2 x %struct.S.0], align 4
// CHECK1-NEXT: [[VAR:%.*]] = alloca [[STRUCT_S_0]], align 4
// CHECK1-NEXT: [[VAR1:%.*]] = alloca [[STRUCT_S_0]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TEST]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: store i32 0, i32* [[T_VAR]], align 4
// CHECK1-NEXT: [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const._Z5tmainIiET_v.vec to i8*), i64 8, i1 false)
// CHECK1-NEXT: [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i64 0, i64 0
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], i32 noundef 1)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYINIT_BEGIN]], i64 1
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], i32 noundef 2)
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR]], i32 noundef 3)
// CHECK1-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR1]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 6, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*, %struct.S.0*, %struct.S.0*, i32*, [2 x i32]*, [2 x %struct.S.0]*)* @.omp_outlined..1 to void (i32*, i32*, ...)*), i32* [[T_VAR]], %struct.S.0* [[VAR]], %struct.S.0* [[VAR1]], i32* [[T_VAR1]], [2 x i32]* [[VEC]], [2 x %struct.S.0]* [[S_ARR]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: store i32 0, i32* [[RETVAL]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR1]]) #[[ATTR4]]
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i64 2
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK1: arraydestroy.body:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP1]], [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN]]
// CHECK1-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK1: arraydestroy.done1:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP2:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK1-NEXT: ret i32 [[TMP2]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT: [[TMP0:%.*]] = load volatile double, double* @g, align 8
// CHECK1-NEXT: [[CONV:%.*]] = fptrunc double [[TMP0]] to float
// CHECK1-NEXT: store float [[CONV]], float* [[F]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ef
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]], float noundef [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK1-NEXT: [[CONV:%.*]] = fpext float [[TMP0]] to double
// CHECK1-NEXT: [[TMP1:%.*]] = load volatile double, double* @g, align 8
// CHECK1-NEXT: [[ADD:%.*]] = fadd double [[CONV]], [[TMP1]]
// CHECK1-NEXT: [[CONV2:%.*]] = fptrunc double [[ADD]] to float
// CHECK1-NEXT: store float [[CONV2]], float* [[F]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIfED2Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiEC2Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS1]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ei
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 noundef [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiEC2Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS1]], i32 noundef [[TMP0]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined..1
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK1-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], i32* noundef nonnull align 4 dereferenceable(4) [[T_VAR:%.*]], %struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR:%.*]], %struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR1:%.*]], i32* noundef nonnull align 4 dereferenceable(4) [[T_VAR1:%.*]], [2 x i32]* noundef nonnull align 4 dereferenceable(8) [[VEC:%.*]], [2 x %struct.S.0]* noundef nonnull align 4 dereferenceable(8) [[S_ARR:%.*]]) #[[ATTR3]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[T_VAR_ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[VAR1_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[T_VAR1_ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 8
// CHECK1-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S.0]*, align 8
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[DOTOMP_SECTIONS_LB_:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_SECTIONS_UB_:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_SECTIONS_ST_:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_SECTIONS_IL_:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[DOTOMP_SECTIONS_IV_:%.*]] = alloca i32, align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[T_VAR2:%.*]] = alloca i32, align 4
// CHECK1-NEXT: [[VAR3:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK1-NEXT: [[VAR14:%.*]] = alloca [[STRUCT_S_0]], align 4
// CHECK1-NEXT: [[T_VAR15:%.*]] = alloca i32, align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [4 x i8*], align 8
// CHECK1-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S_0]], align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[REF_TMP13:%.*]] = alloca [[STRUCT_S_0]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: store i32* [[T_VAR]], i32** [[T_VAR_ADDR]], align 8
// CHECK1-NEXT: store %struct.S.0* [[VAR]], %struct.S.0** [[VAR_ADDR]], align 8
// CHECK1-NEXT: store %struct.S.0* [[VAR1]], %struct.S.0** [[VAR1_ADDR]], align 8
// CHECK1-NEXT: store i32* [[T_VAR1]], i32** [[T_VAR1_ADDR]], align 8
// CHECK1-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 8
// CHECK1-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[S_ARR_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i32*, i32** [[T_VAR_ADDR]], align 8
// CHECK1-NEXT: [[TMP1:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR_ADDR]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR1_ADDR]], align 8
// CHECK1-NEXT: [[TMP3:%.*]] = load i32*, i32** [[T_VAR1_ADDR]], align 8
// CHECK1-NEXT: [[TMP4:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 8
// CHECK1-NEXT: [[TMP5:%.*]] = load [2 x %struct.S.0]*, [2 x %struct.S.0]** [[S_ARR_ADDR]], align 8
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_LB_]], align 4
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_SECTIONS_ST_]], align 4
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_IL_]], align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: store i32 0, i32* [[T_VAR2]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR3]])
// CHECK1-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR14]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: store i32 2147483647, i32* [[T_VAR15]], align 4
// CHECK1-NEXT: [[TMP6:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: [[TMP7:%.*]] = load i32, i32* [[TMP6]], align 4
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP7]], i32 34, i32* [[DOTOMP_SECTIONS_IL_]], i32* [[DOTOMP_SECTIONS_LB_]], i32* [[DOTOMP_SECTIONS_UB_]], i32* [[DOTOMP_SECTIONS_ST_]], i32 1, i32 1)
// CHECK1-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK1-NEXT: [[TMP9:%.*]] = icmp slt i32 [[TMP8]], 1
// CHECK1-NEXT: [[TMP10:%.*]] = select i1 [[TMP9]], i32 [[TMP8]], i32 1
// CHECK1-NEXT: store i32 [[TMP10]], i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK1-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_LB_]], align 4
// CHECK1-NEXT: store i32 [[TMP11]], i32* [[DOTOMP_SECTIONS_IV_]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK1: omp.inner.for.cond:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK1-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK1-NEXT: [[CMP:%.*]] = icmp sle i32 [[TMP12]], [[TMP13]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br i1 [[CMP]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
// CHECK1: omp.inner.for.body:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK1-NEXT: switch i32 [[TMP14]], label [[DOTOMP_SECTIONS_EXIT:%.*]] [
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: i32 0, label [[DOTOMP_SECTIONS_CASE:%.*]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: i32 1, label [[DOTOMP_SECTIONS_CASE6:%.*]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: ]
// CHECK1: .omp.sections.case:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP15:%.*]] = load i32, i32* [[T_VAR2]], align 4
// CHECK1-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP4]], i64 0, i64 0
// CHECK1-NEXT: store i32 [[TMP15]], i32* [[ARRAYIDX]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[DOTOMP_SECTIONS_EXIT]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1: .omp.sections.case6:
// CHECK1-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[TMP5]], i64 0, i64 0
// CHECK1-NEXT: [[TMP16:%.*]] = bitcast %struct.S.0* [[ARRAYIDX7]] to i8*
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast %struct.S.0* [[VAR3]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP16]], i8* align 4 [[TMP17]], i64 4, i1 false)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[DOTOMP_SECTIONS_EXIT]]
// CHECK1: .omp.sections.exit:
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK1: omp.inner.for.inc:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK1-NEXT: [[INC:%.*]] = add nsw i32 [[TMP18]], 1
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: store i32 [[INC]], i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK1: omp.inner.for.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP7]])
// CHECK1-NEXT: [[TMP19:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast i32* [[T_VAR2]] to i8*
// CHECK1-NEXT: store i8* [[TMP20]], i8** [[TMP19]], align 8
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
// CHECK1-NEXT: [[TMP22:%.*]] = bitcast %struct.S.0* [[VAR3]] to i8*
// CHECK1-NEXT: store i8* [[TMP22]], i8** [[TMP21]], align 8
// CHECK1-NEXT: [[TMP23:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
// CHECK1-NEXT: [[TMP24:%.*]] = bitcast %struct.S.0* [[VAR14]] to i8*
// CHECK1-NEXT: store i8* [[TMP24]], i8** [[TMP23]], align 8
// CHECK1-NEXT: [[TMP25:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 3
// CHECK1-NEXT: [[TMP26:%.*]] = bitcast i32* [[T_VAR15]] to i8*
// CHECK1-NEXT: store i8* [[TMP26]], i8** [[TMP25]], align 8
// CHECK1-NEXT: [[TMP27:%.*]] = bitcast [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
// CHECK1-NEXT: [[TMP28:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP7]], i32 4, i64 32, i8* [[TMP27]], void (i8*, i8*)* @.omp.reduction.reduction_func.2, [8 x i32]* @.gomp_critical_user_.reduction.var)
// CHECK1-NEXT: switch i32 [[TMP28]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
// CHECK1-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
// CHECK1-NEXT: ]
// CHECK1: .omp.reduction.case1:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP29:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK1-NEXT: [[TMP30:%.*]] = load i32, i32* [[T_VAR2]], align 4
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP29]], [[TMP30]]
// CHECK1-NEXT: store i32 [[ADD]], i32* [[TMP0]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL:%.*]] = call noundef nonnull align 4 dereferenceable(4) %struct.S.0* @_ZN1SIiEanERKS0_(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP1]], %struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR3]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP31:%.*]] = bitcast %struct.S.0* [[TMP1]] to i8*
// CHECK1-NEXT: [[TMP32:%.*]] = bitcast %struct.S.0* [[CALL]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP31]], i8* align 4 [[TMP32]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL8:%.*]] = call noundef i32 @_ZN1SIiEcviEv(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP2]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[CALL8]], 0
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
// CHECK1: land.rhs:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL9:%.*]] = call noundef i32 @_ZN1SIiEcviEv(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR14]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TOBOOL10:%.*]] = icmp ne i32 [[CALL9]], 0
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[LAND_END]]
// CHECK1: land.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP33:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE1]] ], [ [[TOBOOL10]], [[LAND_RHS]] ]
// CHECK1-NEXT: [[CONV:%.*]] = zext i1 [[TMP33]] to i32
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]], i32 noundef [[CONV]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP34:%.*]] = bitcast %struct.S.0* [[TMP2]] to i8*
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S.0* [[REF_TMP]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP34]], i8* align 4 [[TMP35]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP36:%.*]] = load i32, i32* [[TMP3]], align 4
// CHECK1-NEXT: [[TMP37:%.*]] = load i32, i32* [[T_VAR15]], align 4
// CHECK1-NEXT: [[CMP11:%.*]] = icmp slt i32 [[TMP36]], [[TMP37]]
// CHECK1-NEXT: br i1 [[CMP11]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1: cond.true:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP3]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[COND_END:%.*]]
// CHECK1: cond.false:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP39:%.*]] = load i32, i32* [[T_VAR15]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[COND_END]]
// CHECK1: cond.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ [[TMP38]], [[COND_TRUE]] ], [ [[TMP39]], [[COND_FALSE]] ]
// CHECK1-NEXT: store i32 [[COND]], i32* [[TMP3]], align 4
// CHECK1-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.reduction.var)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK1: .omp.reduction.case2:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP40:%.*]] = load i32, i32* [[T_VAR2]], align 4
// CHECK1-NEXT: [[TMP41:%.*]] = atomicrmw add i32* [[TMP0]], i32 [[TMP40]] monotonic, align 4
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL12:%.*]] = call noundef nonnull align 4 dereferenceable(4) %struct.S.0* @_ZN1SIiEanERKS0_(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP1]], %struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR3]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP42:%.*]] = bitcast %struct.S.0* [[TMP1]] to i8*
// CHECK1-NEXT: [[TMP43:%.*]] = bitcast %struct.S.0* [[CALL12]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP42]], i8* align 4 [[TMP43]], i64 4, i1 false)
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
// CHECK1-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL14:%.*]] = call noundef i32 @_ZN1SIiEcviEv(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP2]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TOBOOL15:%.*]] = icmp ne i32 [[CALL14]], 0
// CHECK1-NEXT: br i1 [[TOBOOL15]], label [[LAND_RHS16:%.*]], label [[LAND_END19:%.*]]
// CHECK1: land.rhs16:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL17:%.*]] = call noundef i32 @_ZN1SIiEcviEv(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR14]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TOBOOL18:%.*]] = icmp ne i32 [[CALL17]], 0
// CHECK1-NEXT: br label [[LAND_END19]]
// CHECK1: land.end19:
// CHECK1-NEXT: [[TMP44:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE2]] ], [ [[TOBOOL18]], [[LAND_RHS16]] ]
// CHECK1-NEXT: [[CONV20:%.*]] = zext i1 [[TMP44]] to i32
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[REF_TMP13]], i32 noundef [[CONV20]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: [[TMP45:%.*]] = bitcast %struct.S.0* [[TMP2]] to i8*
// CHECK1-NEXT: [[TMP46:%.*]] = bitcast %struct.S.0* [[REF_TMP13]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP45]], i8* align 4 [[TMP46]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[REF_TMP13]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK1-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
// CHECK1-NEXT: [[TMP47:%.*]] = load i32, i32* [[T_VAR15]], align 4
// CHECK1-NEXT: [[TMP48:%.*]] = atomicrmw min i32* [[TMP3]], i32 [[TMP47]] monotonic, align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK1: .omp.reduction.default:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR14]]) #[[ATTR4]]
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR3]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.2
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK1-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR5]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK1-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK1-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK1-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK1-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [4 x i8*]*
// CHECK1-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
// CHECK1-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [4 x i8*]*
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 0
// CHECK1-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK1-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
// CHECK1-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 0
// CHECK1-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
// CHECK1-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
// CHECK1-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 1
// CHECK1-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
// CHECK1-NEXT: [[TMP14:%.*]] = bitcast i8* [[TMP13]] to %struct.S.0*
// CHECK1-NEXT: [[TMP15:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 1
// CHECK1-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
// CHECK1-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to %struct.S.0*
// CHECK1-NEXT: [[TMP18:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 2
// CHECK1-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
// CHECK1-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to %struct.S.0*
// CHECK1-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 2
// CHECK1-NEXT: [[TMP22:%.*]] = load i8*, i8** [[TMP21]], align 8
// CHECK1-NEXT: [[TMP23:%.*]] = bitcast i8* [[TMP22]] to %struct.S.0*
// CHECK1-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 3
// CHECK1-NEXT: [[TMP25:%.*]] = load i8*, i8** [[TMP24]], align 8
// CHECK1-NEXT: [[TMP26:%.*]] = bitcast i8* [[TMP25]] to i32*
// CHECK1-NEXT: [[TMP27:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 3
// CHECK1-NEXT: [[TMP28:%.*]] = load i8*, i8** [[TMP27]], align 8
// CHECK1-NEXT: [[TMP29:%.*]] = bitcast i8* [[TMP28]] to i32*
// CHECK1-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK1-NEXT: [[TMP31:%.*]] = load i32, i32* [[TMP8]], align 4
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP30]], [[TMP31]]
// CHECK1-NEXT: store i32 [[ADD]], i32* [[TMP11]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL:%.*]] = call noundef nonnull align 4 dereferenceable(4) %struct.S.0* @_ZN1SIiEanERKS0_(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP17]], %struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP14]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TMP32:%.*]] = bitcast %struct.S.0* [[TMP17]] to i8*
// CHECK1-NEXT: [[TMP33:%.*]] = bitcast %struct.S.0* [[CALL]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP32]], i8* align 4 [[TMP33]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL2:%.*]] = call noundef i32 @_ZN1SIiEcviEv(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP23]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[CALL2]], 0
// CHECK1-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
// CHECK1: land.rhs:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: [[CALL3:%.*]] = call noundef i32 @_ZN1SIiEcviEv(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP20]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TOBOOL4:%.*]] = icmp ne i32 [[CALL3]], 0
// CHECK1-NEXT: br label [[LAND_END]]
// CHECK1: land.end:
// CHECK1-NEXT: [[TMP34:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[TOBOOL4]], [[LAND_RHS]] ]
// CHECK1-NEXT: [[CONV:%.*]] = zext i1 [[TMP34]] to i32
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]], i32 noundef [[CONV]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TMP35:%.*]] = bitcast %struct.S.0* [[TMP23]] to i8*
// CHECK1-NEXT: [[TMP36:%.*]] = bitcast %struct.S.0* [[REF_TMP]] to i8*
// CHECK1-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP35]], i8* align 4 [[TMP36]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: [[TMP37:%.*]] = load i32, i32* [[TMP29]], align 4
// CHECK1-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP26]], align 4
// CHECK1-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP37]], [[TMP38]]
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK1: cond.true:
// CHECK1-NEXT: [[TMP39:%.*]] = load i32, i32* [[TMP29]], align 4
// CHECK1-NEXT: br label [[COND_END:%.*]]
// CHECK1: cond.false:
// CHECK1-NEXT: [[TMP40:%.*]] = load i32, i32* [[TMP26]], align 4
// CHECK1-NEXT: br label [[COND_END]]
// CHECK1: cond.end:
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ [[TMP39]], [[COND_TRUE]] ], [ [[TMP40]], [[COND_FALSE]] ]
// CHECK1-NEXT: store i32 [[COND]], i32* [[TMP29]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEanERKS0_
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP0:%.*]]) #[[ATTR6]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store %struct.S.0* [[TMP0]], %struct.S.0** [[DOTADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: ret %struct.S.0* [[THIS1]]
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEcviEv
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) #[[ATTR6]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: ret i32 0
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiED1Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-NEXT: call void @_ZN1SIiED2Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT: [[TMP0:%.*]] = load volatile double, double* @g, align 8
// CHECK1-NEXT: [[CONV:%.*]] = fptosi double [[TMP0]] to i32
// CHECK1-NEXT: store i32 [[CONV]], i32* [[F]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ei
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 noundef [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK1-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK1-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to double
// CHECK1-NEXT: [[TMP1:%.*]] = load volatile double, double* @g, align 8
// CHECK1-NEXT: [[ADD:%.*]] = fadd double [[CONV]], [[TMP1]]
// CHECK1-NEXT: [[CONV2:%.*]] = fptosi double [[ADD]] to i32
// CHECK1-NEXT: store i32 [[CONV2]], i32* [[F]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN1SIiED2Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK1-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK1-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK1-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@main
// CHECK2-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[TEST:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK2-NEXT: [[T_VAR:%.*]] = alloca float, align 4
// CHECK2-NEXT: [[T_VAR1:%.*]] = alloca float, align 4
// CHECK2-NEXT: [[VEC:%.*]] = alloca [2 x i32], align 4
// CHECK2-NEXT: [[S_ARR:%.*]] = alloca [2 x %struct.S], align 4
// CHECK2-NEXT: [[VAR:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK2-NEXT: [[VAR1:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK2-NEXT: store i32 0, i32* [[RETVAL]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TEST]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: store float 0.000000e+00, float* [[T_VAR]], align 4
// CHECK2-NEXT: [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const.main.vec to i8*), i64 8, i1 false)
// CHECK2-NEXT: [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i64 0, i64 0
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], float noundef 1.000000e+00)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYINIT_BEGIN]], i64 1
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], float noundef 2.000000e+00)
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR]], float noundef 3.000000e+00)
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR1]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3:[0-9]+]], i32 6, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, float*, %struct.S*, %struct.S*, float*, [2 x i32]*, [2 x %struct.S]*)* @.omp_outlined. to void (i32*, i32*, ...)*), float* [[T_VAR]], %struct.S* [[VAR]], %struct.S* [[VAR1]], float* [[T_VAR1]], [2 x i32]* [[VEC]], [2 x %struct.S]* [[S_ARR]])
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK2-NEXT: [[CALL:%.*]] = call noundef i32 @_Z5tmainIiET_v()
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: store i32 [[CALL]], i32* [[RETVAL]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR1]]) #[[ATTR4:[0-9]+]]
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[S_ARR]], i32 0, i32 0
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAY_BEGIN]], i64 2
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK2: arraydestroy.body:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S* [ [[TMP1]], [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S]], %struct.S* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN]]
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK2: arraydestroy.done1:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK2-NEXT: ret i32 [[TMP2]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1:[0-9]+]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfEC2Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS1]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC1Ef
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]], float noundef [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfEC2Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS1]], float noundef [[TMP0]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined.
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK2-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], float* noundef nonnull align 4 dereferenceable(4) [[T_VAR:%.*]], %struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR:%.*]], %struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR1:%.*]], float* noundef nonnull align 4 dereferenceable(4) [[T_VAR1:%.*]], [2 x i32]* noundef nonnull align 4 dereferenceable(8) [[VEC:%.*]], [2 x %struct.S]* noundef nonnull align 4 dereferenceable(8) [[S_ARR:%.*]]) #[[ATTR3:[0-9]+]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[T_VAR_ADDR:%.*]] = alloca float*, align 8
// CHECK2-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: [[VAR1_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: [[T_VAR1_ADDR:%.*]] = alloca float*, align 8
// CHECK2-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 8
// CHECK2-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S]*, align 8
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[DOTOMP_SECTIONS_LB_:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_SECTIONS_UB_:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_SECTIONS_ST_:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_SECTIONS_IL_:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_SECTIONS_IV_:%.*]] = alloca i32, align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[T_VAR2:%.*]] = alloca float, align 4
// CHECK2-NEXT: [[VAR3:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK2-NEXT: [[VAR14:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK2-NEXT: [[T_VAR15:%.*]] = alloca float, align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [4 x i8*], align 8
// CHECK2-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK2-NEXT: [[ATOMIC_TEMP:%.*]] = alloca float, align 4
// CHECK2-NEXT: [[TMP:%.*]] = alloca float, align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[REF_TMP17:%.*]] = alloca [[STRUCT_S]], align 4
// CHECK2-NEXT: [[ATOMIC_TEMP27:%.*]] = alloca float, align 4
// CHECK2-NEXT: [[_TMP28:%.*]] = alloca float, align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: store float* [[T_VAR]], float** [[T_VAR_ADDR]], align 8
// CHECK2-NEXT: store %struct.S* [[VAR]], %struct.S** [[VAR_ADDR]], align 8
// CHECK2-NEXT: store %struct.S* [[VAR1]], %struct.S** [[VAR1_ADDR]], align 8
// CHECK2-NEXT: store float* [[T_VAR1]], float** [[T_VAR1_ADDR]], align 8
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 8
// CHECK2-NEXT: store [2 x %struct.S]* [[S_ARR]], [2 x %struct.S]** [[S_ARR_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load float*, float** [[T_VAR_ADDR]], align 8
// CHECK2-NEXT: [[TMP1:%.*]] = load %struct.S*, %struct.S** [[VAR_ADDR]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load %struct.S*, %struct.S** [[VAR1_ADDR]], align 8
// CHECK2-NEXT: [[TMP3:%.*]] = load float*, float** [[T_VAR1_ADDR]], align 8
// CHECK2-NEXT: [[TMP4:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 8
// CHECK2-NEXT: [[TMP5:%.*]] = load [2 x %struct.S]*, [2 x %struct.S]** [[S_ARR_ADDR]], align 8
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_LB_]], align 4
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_SECTIONS_ST_]], align 4
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_IL_]], align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: store float 0.000000e+00, float* [[T_VAR2]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR3]])
// CHECK2-NEXT: call void @_ZN1SIfEC1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR14]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: store float 0x47EFFFFFE0000000, float* [[T_VAR15]], align 4
// CHECK2-NEXT: [[TMP6:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: [[TMP7:%.*]] = load i32, i32* [[TMP6]], align 4
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP7]], i32 34, i32* [[DOTOMP_SECTIONS_IL_]], i32* [[DOTOMP_SECTIONS_LB_]], i32* [[DOTOMP_SECTIONS_UB_]], i32* [[DOTOMP_SECTIONS_ST_]], i32 1, i32 1)
// CHECK2-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK2-NEXT: [[TMP9:%.*]] = icmp slt i32 [[TMP8]], 0
// CHECK2-NEXT: [[TMP10:%.*]] = select i1 [[TMP9]], i32 [[TMP8]], i32 0
// CHECK2-NEXT: store i32 [[TMP10]], i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK2-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_LB_]], align 4
// CHECK2-NEXT: store i32 [[TMP11]], i32* [[DOTOMP_SECTIONS_IV_]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK2: omp.inner.for.cond:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK2-NEXT: [[CMP:%.*]] = icmp sle i32 [[TMP12]], [[TMP13]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br i1 [[CMP]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
// CHECK2: omp.inner.for.body:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK2-NEXT: switch i32 [[TMP14]], label [[DOTOMP_SECTIONS_EXIT:%.*]] [
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: i32 0, label [[DOTOMP_SECTIONS_CASE:%.*]]
// CHECK2-NEXT: ]
// CHECK2: .omp.sections.case:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP15:%.*]] = load float, float* [[T_VAR2]], align 4
// CHECK2-NEXT: [[CONV:%.*]] = fptosi float [[TMP15]] to i32
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP4]], i64 0, i64 0
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: store i32 [[CONV]], i32* [[ARRAYIDX]], align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[TMP5]], i64 0, i64 0
// CHECK2-NEXT: [[TMP16:%.*]] = bitcast %struct.S* [[ARRAYIDX6]] to i8*
// CHECK2-NEXT: [[TMP17:%.*]] = bitcast %struct.S* [[VAR3]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP16]], i8* align 4 [[TMP17]], i64 4, i1 false)
// CHECK2-NEXT: [[TMP18:%.*]] = load float, float* [[T_VAR15]], align 4
// CHECK2-NEXT: [[CONV7:%.*]] = fptosi float [[TMP18]] to i32
// CHECK2-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP4]], i64 0, i64 1
// CHECK2-NEXT: store i32 [[CONV7]], i32* [[ARRAYIDX8]], align 4
// CHECK2-NEXT: [[ARRAYIDX9:%.*]] = getelementptr inbounds [2 x %struct.S], [2 x %struct.S]* [[TMP5]], i64 0, i64 1
// CHECK2-NEXT: [[TMP19:%.*]] = bitcast %struct.S* [[ARRAYIDX9]] to i8*
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast %struct.S* [[VAR14]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP19]], i8* align 4 [[TMP20]], i64 4, i1 false)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[DOTOMP_SECTIONS_EXIT]]
// CHECK2: .omp.sections.exit:
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK2: omp.inner.for.inc:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP21:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK2-NEXT: [[INC:%.*]] = add nsw i32 [[TMP21]], 1
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: store i32 [[INC]], i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK2: omp.inner.for.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP7]])
// CHECK2-NEXT: [[TMP22:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
// CHECK2-NEXT: [[TMP23:%.*]] = bitcast float* [[T_VAR2]] to i8*
// CHECK2-NEXT: store i8* [[TMP23]], i8** [[TMP22]], align 8
// CHECK2-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
// CHECK2-NEXT: [[TMP25:%.*]] = bitcast %struct.S* [[VAR3]] to i8*
// CHECK2-NEXT: store i8* [[TMP25]], i8** [[TMP24]], align 8
// CHECK2-NEXT: [[TMP26:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
// CHECK2-NEXT: [[TMP27:%.*]] = bitcast %struct.S* [[VAR14]] to i8*
// CHECK2-NEXT: store i8* [[TMP27]], i8** [[TMP26]], align 8
// CHECK2-NEXT: [[TMP28:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 3
// CHECK2-NEXT: [[TMP29:%.*]] = bitcast float* [[T_VAR15]] to i8*
// CHECK2-NEXT: store i8* [[TMP29]], i8** [[TMP28]], align 8
// CHECK2-NEXT: [[TMP30:%.*]] = bitcast [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
// CHECK2-NEXT: [[TMP31:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP7]], i32 4, i64 32, i8* [[TMP30]], void (i8*, i8*)* @.omp.reduction.reduction_func, [8 x i32]* @.gomp_critical_user_.reduction.var)
// CHECK2-NEXT: switch i32 [[TMP31]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
// CHECK2-NEXT: ]
// CHECK2: .omp.reduction.case1:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP32:%.*]] = load float, float* [[TMP0]], align 4
// CHECK2-NEXT: [[TMP33:%.*]] = load float, float* [[T_VAR2]], align 4
// CHECK2-NEXT: [[ADD:%.*]] = fadd float [[TMP32]], [[TMP33]]
// CHECK2-NEXT: store float [[ADD]], float* [[TMP0]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL:%.*]] = call noundef nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP1]], %struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR3]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP34:%.*]] = bitcast %struct.S* [[TMP1]] to i8*
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[CALL]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP34]], i8* align 4 [[TMP35]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL10:%.*]] = call noundef float @_ZN1SIfEcvfEv(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP2]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TOBOOL:%.*]] = fcmp une float [[CALL10]], 0.000000e+00
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
// CHECK2: land.rhs:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL11:%.*]] = call noundef float @_ZN1SIfEcvfEv(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR14]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TOBOOL12:%.*]] = fcmp une float [[CALL11]], 0.000000e+00
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[LAND_END]]
// CHECK2: land.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP36:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE1]] ], [ [[TOBOOL12]], [[LAND_RHS]] ]
// CHECK2-NEXT: [[CONV13:%.*]] = uitofp i1 [[TMP36]] to float
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]], float noundef [[CONV13]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP37:%.*]] = bitcast %struct.S* [[TMP2]] to i8*
// CHECK2-NEXT: [[TMP38:%.*]] = bitcast %struct.S* [[REF_TMP]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP37]], i8* align 4 [[TMP38]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP39:%.*]] = load float, float* [[TMP3]], align 4
// CHECK2-NEXT: [[TMP40:%.*]] = load float, float* [[T_VAR15]], align 4
// CHECK2-NEXT: [[CMP14:%.*]] = fcmp olt float [[TMP39]], [[TMP40]]
// CHECK2-NEXT: br i1 [[CMP14]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2: cond.true:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP41:%.*]] = load float, float* [[TMP3]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[COND_END:%.*]]
// CHECK2: cond.false:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP42:%.*]] = load float, float* [[T_VAR15]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[COND_END]]
// CHECK2: cond.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[COND:%.*]] = phi float [ [[TMP41]], [[COND_TRUE]] ], [ [[TMP42]], [[COND_FALSE]] ]
// CHECK2-NEXT: store float [[COND]], float* [[TMP3]], align 4
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.reduction.var)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK2: .omp.reduction.case2:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP43:%.*]] = load float, float* [[T_VAR2]], align 4
// CHECK2-NEXT: [[TMP44:%.*]] = bitcast float* [[TMP0]] to i32*
// CHECK2-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i32, i32* [[TMP44]] monotonic, align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[ATOMIC_CONT:%.*]]
// CHECK2: atomic_cont:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP45:%.*]] = phi i32 [ [[ATOMIC_LOAD]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[TMP53:%.*]], [[ATOMIC_CONT]] ]
// CHECK2-NEXT: [[TMP46:%.*]] = bitcast float* [[ATOMIC_TEMP]] to i32*
// CHECK2-NEXT: [[TMP47:%.*]] = bitcast i32 [[TMP45]] to float
// CHECK2-NEXT: store float [[TMP47]], float* [[TMP]], align 4
// CHECK2-NEXT: [[TMP48:%.*]] = load float, float* [[TMP]], align 4
// CHECK2-NEXT: [[TMP49:%.*]] = load float, float* [[T_VAR2]], align 4
// CHECK2-NEXT: [[ADD15:%.*]] = fadd float [[TMP48]], [[TMP49]]
// CHECK2-NEXT: store float [[ADD15]], float* [[ATOMIC_TEMP]], align 4
// CHECK2-NEXT: [[TMP50:%.*]] = load i32, i32* [[TMP46]], align 4
// CHECK2-NEXT: [[TMP51:%.*]] = bitcast float* [[TMP0]] to i32*
// CHECK2-NEXT: [[TMP52:%.*]] = cmpxchg i32* [[TMP51]], i32 [[TMP45]], i32 [[TMP50]] monotonic monotonic, align 4
// CHECK2-NEXT: [[TMP53]] = extractvalue { i32, i1 } [[TMP52]], 0
// CHECK2-NEXT: [[TMP54:%.*]] = extractvalue { i32, i1 } [[TMP52]], 1
// CHECK2-NEXT: br i1 [[TMP54]], label [[ATOMIC_EXIT:%.*]], label [[ATOMIC_CONT]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2: atomic_exit:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL16:%.*]] = call noundef nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP1]], %struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR3]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP55:%.*]] = bitcast %struct.S* [[TMP1]] to i8*
// CHECK2-NEXT: [[TMP56:%.*]] = bitcast %struct.S* [[CALL16]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP55]], i8* align 4 [[TMP56]], i64 4, i1 false)
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL18:%.*]] = call noundef float @_ZN1SIfEcvfEv(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP2]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TOBOOL19:%.*]] = fcmp une float [[CALL18]], 0.000000e+00
// CHECK2-NEXT: br i1 [[TOBOOL19]], label [[LAND_RHS20:%.*]], label [[LAND_END23:%.*]]
// CHECK2: land.rhs20:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL21:%.*]] = call noundef float @_ZN1SIfEcvfEv(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR14]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TOBOOL22:%.*]] = fcmp une float [[CALL21]], 0.000000e+00
// CHECK2-NEXT: br label [[LAND_END23]]
// CHECK2: land.end23:
// CHECK2-NEXT: [[TMP57:%.*]] = phi i1 [ false, [[ATOMIC_EXIT]] ], [ [[TOBOOL22]], [[LAND_RHS20]] ]
// CHECK2-NEXT: [[CONV24:%.*]] = uitofp i1 [[TMP57]] to float
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[REF_TMP17]], float noundef [[CONV24]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP58:%.*]] = bitcast %struct.S* [[TMP2]] to i8*
// CHECK2-NEXT: [[TMP59:%.*]] = bitcast %struct.S* [[REF_TMP17]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP58]], i8* align 4 [[TMP59]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[REF_TMP17]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
// CHECK2-NEXT: [[TMP60:%.*]] = load float, float* [[T_VAR15]], align 4
// CHECK2-NEXT: [[TMP61:%.*]] = bitcast float* [[TMP3]] to i32*
// CHECK2-NEXT: [[ATOMIC_LOAD25:%.*]] = load atomic i32, i32* [[TMP61]] monotonic, align 4
// CHECK2-NEXT: br label [[ATOMIC_CONT26:%.*]]
// CHECK2: atomic_cont26:
// CHECK2-NEXT: [[TMP62:%.*]] = phi i32 [ [[ATOMIC_LOAD25]], [[LAND_END23]] ], [ [[TMP72:%.*]], [[COND_END32:%.*]] ]
// CHECK2-NEXT: [[TMP63:%.*]] = bitcast float* [[ATOMIC_TEMP27]] to i32*
// CHECK2-NEXT: [[TMP64:%.*]] = bitcast i32 [[TMP62]] to float
// CHECK2-NEXT: store float [[TMP64]], float* [[_TMP28]], align 4
// CHECK2-NEXT: [[TMP65:%.*]] = load float, float* [[_TMP28]], align 4
// CHECK2-NEXT: [[TMP66:%.*]] = load float, float* [[T_VAR15]], align 4
// CHECK2-NEXT: [[CMP29:%.*]] = fcmp olt float [[TMP65]], [[TMP66]]
// CHECK2-NEXT: br i1 [[CMP29]], label [[COND_TRUE30:%.*]], label [[COND_FALSE31:%.*]]
// CHECK2: cond.true30:
// CHECK2-NEXT: [[TMP67:%.*]] = load float, float* [[_TMP28]], align 4
// CHECK2-NEXT: br label [[COND_END32]]
// CHECK2: cond.false31:
// CHECK2-NEXT: [[TMP68:%.*]] = load float, float* [[T_VAR15]], align 4
// CHECK2-NEXT: br label [[COND_END32]]
// CHECK2: cond.end32:
// CHECK2-NEXT: [[COND33:%.*]] = phi float [ [[TMP67]], [[COND_TRUE30]] ], [ [[TMP68]], [[COND_FALSE31]] ]
// CHECK2-NEXT: store float [[COND33]], float* [[ATOMIC_TEMP27]], align 4
// CHECK2-NEXT: [[TMP69:%.*]] = load i32, i32* [[TMP63]], align 4
// CHECK2-NEXT: [[TMP70:%.*]] = bitcast float* [[TMP3]] to i32*
// CHECK2-NEXT: [[TMP71:%.*]] = cmpxchg i32* [[TMP70]], i32 [[TMP62]], i32 [[TMP69]] monotonic monotonic, align 4
// CHECK2-NEXT: [[TMP72]] = extractvalue { i32, i1 } [[TMP71]], 0
// CHECK2-NEXT: [[TMP73:%.*]] = extractvalue { i32, i1 } [[TMP71]], 1
// CHECK2-NEXT: br i1 [[TMP73]], label [[ATOMIC_EXIT34:%.*]], label [[ATOMIC_CONT26]]
// CHECK2: atomic_exit34:
// CHECK2-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.reduction.var)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK2: .omp.reduction.default:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR14]]) #[[ATTR4]]
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[VAR3]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB4:[0-9]+]], i32 [[TMP7]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK2-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR5:[0-9]+]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S:%.*]], align 4
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [4 x i8*]*
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [4 x i8*]*
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 0
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to float*
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 0
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to float*
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 1
// CHECK2-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast i8* [[TMP13]] to %struct.S*
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 1
// CHECK2-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
// CHECK2-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to %struct.S*
// CHECK2-NEXT: [[TMP18:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 2
// CHECK2-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to %struct.S*
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 2
// CHECK2-NEXT: [[TMP22:%.*]] = load i8*, i8** [[TMP21]], align 8
// CHECK2-NEXT: [[TMP23:%.*]] = bitcast i8* [[TMP22]] to %struct.S*
// CHECK2-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 3
// CHECK2-NEXT: [[TMP25:%.*]] = load i8*, i8** [[TMP24]], align 8
// CHECK2-NEXT: [[TMP26:%.*]] = bitcast i8* [[TMP25]] to float*
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 3
// CHECK2-NEXT: [[TMP28:%.*]] = load i8*, i8** [[TMP27]], align 8
// CHECK2-NEXT: [[TMP29:%.*]] = bitcast i8* [[TMP28]] to float*
// CHECK2-NEXT: [[TMP30:%.*]] = load float, float* [[TMP11]], align 4
// CHECK2-NEXT: [[TMP31:%.*]] = load float, float* [[TMP8]], align 4
// CHECK2-NEXT: [[ADD:%.*]] = fadd float [[TMP30]], [[TMP31]]
// CHECK2-NEXT: store float [[ADD]], float* [[TMP11]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL:%.*]] = call noundef nonnull align 4 dereferenceable(4) %struct.S* @_ZN1SIfEanERKS0_(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP17]], %struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP14]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TMP32:%.*]] = bitcast %struct.S* [[TMP17]] to i8*
// CHECK2-NEXT: [[TMP33:%.*]] = bitcast %struct.S* [[CALL]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP32]], i8* align 4 [[TMP33]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL2:%.*]] = call noundef float @_ZN1SIfEcvfEv(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP23]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TOBOOL:%.*]] = fcmp une float [[CALL2]], 0.000000e+00
// CHECK2-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
// CHECK2: land.rhs:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL3:%.*]] = call noundef float @_ZN1SIfEcvfEv(%struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP20]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TOBOOL4:%.*]] = fcmp une float [[CALL3]], 0.000000e+00
// CHECK2-NEXT: br label [[LAND_END]]
// CHECK2: land.end:
// CHECK2-NEXT: [[TMP34:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[TOBOOL4]], [[LAND_RHS]] ]
// CHECK2-NEXT: [[CONV:%.*]] = uitofp i1 [[TMP34]] to float
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfEC1Ef(%struct.S* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]], float noundef [[CONV]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S* [[TMP23]] to i8*
// CHECK2-NEXT: [[TMP36:%.*]] = bitcast %struct.S* [[REF_TMP]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP35]], i8* align 4 [[TMP36]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfED1Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TMP37:%.*]] = load float, float* [[TMP29]], align 4
// CHECK2-NEXT: [[TMP38:%.*]] = load float, float* [[TMP26]], align 4
// CHECK2-NEXT: [[CMP:%.*]] = fcmp olt float [[TMP37]], [[TMP38]]
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK2: cond.true:
// CHECK2-NEXT: [[TMP39:%.*]] = load float, float* [[TMP29]], align 4
// CHECK2-NEXT: br label [[COND_END:%.*]]
// CHECK2: cond.false:
// CHECK2-NEXT: [[TMP40:%.*]] = load float, float* [[TMP26]], align 4
// CHECK2-NEXT: br label [[COND_END]]
// CHECK2: cond.end:
// CHECK2-NEXT: [[COND:%.*]] = phi float [ [[TMP39]], [[COND_TRUE]] ], [ [[TMP40]], [[COND_FALSE]] ]
// CHECK2-NEXT: store float [[COND]], float* [[TMP29]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEanERKS0_
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S* noundef nonnull align 4 dereferenceable(4) [[TMP0:%.*]]) #[[ATTR6:[0-9]+]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store %struct.S* [[TMP0]], %struct.S** [[DOTADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: ret %struct.S* [[THIS1]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEcvfEv
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) #[[ATTR6]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: ret float 0.000000e+00
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfED1Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIfED2Ev(%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z5tmainIiET_v
// CHECK2-SAME: () #[[ATTR6]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[T:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[TEST:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK2-NEXT: [[T_VAR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[T_VAR1:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[VEC:%.*]] = alloca [2 x i32], align 4
// CHECK2-NEXT: [[S_ARR:%.*]] = alloca [2 x %struct.S.0], align 4
// CHECK2-NEXT: [[VAR:%.*]] = alloca [[STRUCT_S_0]], align 4
// CHECK2-NEXT: [[VAR1:%.*]] = alloca [[STRUCT_S_0]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TEST]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: store i32 0, i32* [[T_VAR]], align 4
// CHECK2-NEXT: [[TMP0:%.*]] = bitcast [2 x i32]* [[VEC]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP0]], i8* align 4 bitcast ([2 x i32]* @__const._Z5tmainIiET_v.vec to i8*), i64 8, i1 false)
// CHECK2-NEXT: [[ARRAYINIT_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i64 0, i64 0
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[ARRAYINIT_BEGIN]], i32 noundef 1)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[ARRAYINIT_ELEMENT:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYINIT_BEGIN]], i64 1
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[ARRAYINIT_ELEMENT]], i32 noundef 2)
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR]], i32 noundef 3)
// CHECK2-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR1]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB3]], i32 6, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, i32*, %struct.S.0*, %struct.S.0*, i32*, [2 x i32]*, [2 x %struct.S.0]*)* @.omp_outlined..1 to void (i32*, i32*, ...)*), i32* [[T_VAR]], %struct.S.0* [[VAR]], %struct.S.0* [[VAR1]], i32* [[T_VAR1]], [2 x i32]* [[VEC]], [2 x %struct.S.0]* [[S_ARR]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: store i32 0, i32* [[RETVAL]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR1]]) #[[ATTR4]]
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[ARRAY_BEGIN:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[S_ARR]], i32 0, i32 0
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAY_BEGIN]], i64 2
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[ARRAYDESTROY_BODY:%.*]]
// CHECK2: arraydestroy.body:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENTPAST:%.*]] = phi %struct.S.0* [ [[TMP1]], [[ENTRY:%.*]] ], [ [[ARRAYDESTROY_ELEMENT:%.*]], [[ARRAYDESTROY_BODY]] ]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[ARRAYDESTROY_ELEMENT]] = getelementptr inbounds [[STRUCT_S_0]], %struct.S.0* [[ARRAYDESTROY_ELEMENTPAST]], i64 -1
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[ARRAYDESTROY_ELEMENT]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[ARRAYDESTROY_DONE:%.*]] = icmp eq %struct.S.0* [[ARRAYDESTROY_ELEMENT]], [[ARRAY_BEGIN]]
// CHECK2-NEXT: br i1 [[ARRAYDESTROY_DONE]], label [[ARRAYDESTROY_DONE1:%.*]], label [[ARRAYDESTROY_BODY]]
// CHECK2: arraydestroy.done1:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TEST]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP2:%.*]] = load i32, i32* [[RETVAL]], align 4
// CHECK2-NEXT: ret i32 [[TMP2]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT: [[TMP0:%.*]] = load volatile double, double* @g, align 8
// CHECK2-NEXT: [[CONV:%.*]] = fptrunc double [[TMP0]] to float
// CHECK2-NEXT: store float [[CONV]], float* [[F]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfEC2Ef
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]], float noundef [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca float, align 4
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store float [[A]], float* [[A_ADDR]], align 4
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S:%.*]], %struct.S* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT: [[TMP0:%.*]] = load float, float* [[A_ADDR]], align 4
// CHECK2-NEXT: [[CONV:%.*]] = fpext float [[TMP0]] to double
// CHECK2-NEXT: [[TMP1:%.*]] = load volatile double, double* @g, align 8
// CHECK2-NEXT: [[ADD:%.*]] = fadd double [[CONV]], [[TMP1]]
// CHECK2-NEXT: [[CONV2:%.*]] = fptrunc double [[ADD]] to float
// CHECK2-NEXT: store float [[CONV2]], float* [[F]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIfED2Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: store %struct.S* [[THIS]], %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S*, %struct.S** [[THIS_ADDR]], align 8
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiEC2Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS1]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC1Ei
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 noundef [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiEC2Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS1]], i32 noundef [[TMP0]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined..1
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK2-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], i32* noundef nonnull align 4 dereferenceable(4) [[T_VAR:%.*]], %struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR:%.*]], %struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR1:%.*]], i32* noundef nonnull align 4 dereferenceable(4) [[T_VAR1:%.*]], [2 x i32]* noundef nonnull align 4 dereferenceable(8) [[VEC:%.*]], [2 x %struct.S.0]* noundef nonnull align 4 dereferenceable(8) [[S_ARR:%.*]]) #[[ATTR3]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[T_VAR_ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[VAR_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[VAR1_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[T_VAR1_ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[VEC_ADDR:%.*]] = alloca [2 x i32]*, align 8
// CHECK2-NEXT: [[S_ARR_ADDR:%.*]] = alloca [2 x %struct.S.0]*, align 8
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[DOTOMP_SECTIONS_LB_:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_SECTIONS_UB_:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_SECTIONS_ST_:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_SECTIONS_IL_:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[DOTOMP_SECTIONS_IV_:%.*]] = alloca i32, align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[T_VAR2:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[VAR3:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK2-NEXT: [[VAR14:%.*]] = alloca [[STRUCT_S_0]], align 4
// CHECK2-NEXT: [[T_VAR15:%.*]] = alloca i32, align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [4 x i8*], align 8
// CHECK2-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S_0]], align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[REF_TMP13:%.*]] = alloca [[STRUCT_S_0]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: store i32* [[T_VAR]], i32** [[T_VAR_ADDR]], align 8
// CHECK2-NEXT: store %struct.S.0* [[VAR]], %struct.S.0** [[VAR_ADDR]], align 8
// CHECK2-NEXT: store %struct.S.0* [[VAR1]], %struct.S.0** [[VAR1_ADDR]], align 8
// CHECK2-NEXT: store i32* [[T_VAR1]], i32** [[T_VAR1_ADDR]], align 8
// CHECK2-NEXT: store [2 x i32]* [[VEC]], [2 x i32]** [[VEC_ADDR]], align 8
// CHECK2-NEXT: store [2 x %struct.S.0]* [[S_ARR]], [2 x %struct.S.0]** [[S_ARR_ADDR]], align 8
// CHECK2-NEXT: [[TMP0:%.*]] = load i32*, i32** [[T_VAR_ADDR]], align 8
// CHECK2-NEXT: [[TMP1:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR_ADDR]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load %struct.S.0*, %struct.S.0** [[VAR1_ADDR]], align 8
// CHECK2-NEXT: [[TMP3:%.*]] = load i32*, i32** [[T_VAR1_ADDR]], align 8
// CHECK2-NEXT: [[TMP4:%.*]] = load [2 x i32]*, [2 x i32]** [[VEC_ADDR]], align 8
// CHECK2-NEXT: [[TMP5:%.*]] = load [2 x %struct.S.0]*, [2 x %struct.S.0]** [[S_ARR_ADDR]], align 8
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_LB_]], align 4
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_SECTIONS_ST_]], align 4
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_IL_]], align 4
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: store i32 0, i32* [[T_VAR2]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR3]])
// CHECK2-NEXT: call void @_ZN1SIiEC1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR14]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: store i32 2147483647, i32* [[T_VAR15]], align 4
// CHECK2-NEXT: [[TMP6:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK2-NEXT: [[TMP7:%.*]] = load i32, i32* [[TMP6]], align 4
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1]], i32 [[TMP7]], i32 34, i32* [[DOTOMP_SECTIONS_IL_]], i32* [[DOTOMP_SECTIONS_LB_]], i32* [[DOTOMP_SECTIONS_UB_]], i32* [[DOTOMP_SECTIONS_ST_]], i32 1, i32 1)
// CHECK2-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK2-NEXT: [[TMP9:%.*]] = icmp slt i32 [[TMP8]], 1
// CHECK2-NEXT: [[TMP10:%.*]] = select i1 [[TMP9]], i32 [[TMP8]], i32 1
// CHECK2-NEXT: store i32 [[TMP10]], i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK2-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_LB_]], align 4
// CHECK2-NEXT: store i32 [[TMP11]], i32* [[DOTOMP_SECTIONS_IV_]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK2: omp.inner.for.cond:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP12:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK2-NEXT: [[TMP13:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK2-NEXT: [[CMP:%.*]] = icmp sle i32 [[TMP12]], [[TMP13]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br i1 [[CMP]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
// CHECK2: omp.inner.for.body:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP14:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK2-NEXT: switch i32 [[TMP14]], label [[DOTOMP_SECTIONS_EXIT:%.*]] [
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: i32 0, label [[DOTOMP_SECTIONS_CASE:%.*]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: i32 1, label [[DOTOMP_SECTIONS_CASE6:%.*]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: ]
// CHECK2: .omp.sections.case:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP15:%.*]] = load i32, i32* [[T_VAR2]], align 4
// CHECK2-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds [2 x i32], [2 x i32]* [[TMP4]], i64 0, i64 0
// CHECK2-NEXT: store i32 [[TMP15]], i32* [[ARRAYIDX]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[DOTOMP_SECTIONS_EXIT]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2: .omp.sections.case6:
// CHECK2-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds [2 x %struct.S.0], [2 x %struct.S.0]* [[TMP5]], i64 0, i64 0
// CHECK2-NEXT: [[TMP16:%.*]] = bitcast %struct.S.0* [[ARRAYIDX7]] to i8*
// CHECK2-NEXT: [[TMP17:%.*]] = bitcast %struct.S.0* [[VAR3]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP16]], i8* align 4 [[TMP17]], i64 4, i1 false)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[DOTOMP_SECTIONS_EXIT]]
// CHECK2: .omp.sections.exit:
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK2: omp.inner.for.inc:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP18:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK2-NEXT: [[INC:%.*]] = add nsw i32 [[TMP18]], 1
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: store i32 [[INC]], i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK2: omp.inner.for.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP7]])
// CHECK2-NEXT: [[TMP19:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast i32* [[T_VAR2]] to i8*
// CHECK2-NEXT: store i8* [[TMP20]], i8** [[TMP19]], align 8
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 1
// CHECK2-NEXT: [[TMP22:%.*]] = bitcast %struct.S.0* [[VAR3]] to i8*
// CHECK2-NEXT: store i8* [[TMP22]], i8** [[TMP21]], align 8
// CHECK2-NEXT: [[TMP23:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 2
// CHECK2-NEXT: [[TMP24:%.*]] = bitcast %struct.S.0* [[VAR14]] to i8*
// CHECK2-NEXT: store i8* [[TMP24]], i8** [[TMP23]], align 8
// CHECK2-NEXT: [[TMP25:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 3
// CHECK2-NEXT: [[TMP26:%.*]] = bitcast i32* [[T_VAR15]] to i8*
// CHECK2-NEXT: store i8* [[TMP26]], i8** [[TMP25]], align 8
// CHECK2-NEXT: [[TMP27:%.*]] = bitcast [4 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
// CHECK2-NEXT: [[TMP28:%.*]] = call i32 @__kmpc_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP7]], i32 4, i64 32, i8* [[TMP27]], void (i8*, i8*)* @.omp.reduction.reduction_func.2, [8 x i32]* @.gomp_critical_user_.reduction.var)
// CHECK2-NEXT: switch i32 [[TMP28]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
// CHECK2-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
// CHECK2-NEXT: ]
// CHECK2: .omp.reduction.case1:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP29:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[T_VAR2]], align 4
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP29]], [[TMP30]]
// CHECK2-NEXT: store i32 [[ADD]], i32* [[TMP0]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL:%.*]] = call noundef nonnull align 4 dereferenceable(4) %struct.S.0* @_ZN1SIiEanERKS0_(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP1]], %struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR3]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP31:%.*]] = bitcast %struct.S.0* [[TMP1]] to i8*
// CHECK2-NEXT: [[TMP32:%.*]] = bitcast %struct.S.0* [[CALL]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP31]], i8* align 4 [[TMP32]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL8:%.*]] = call noundef i32 @_ZN1SIiEcviEv(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP2]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[CALL8]], 0
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
// CHECK2: land.rhs:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL9:%.*]] = call noundef i32 @_ZN1SIiEcviEv(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR14]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TOBOOL10:%.*]] = icmp ne i32 [[CALL9]], 0
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[LAND_END]]
// CHECK2: land.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP33:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE1]] ], [ [[TOBOOL10]], [[LAND_RHS]] ]
// CHECK2-NEXT: [[CONV:%.*]] = zext i1 [[TMP33]] to i32
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]], i32 noundef [[CONV]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP34:%.*]] = bitcast %struct.S.0* [[TMP2]] to i8*
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S.0* [[REF_TMP]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP34]], i8* align 4 [[TMP35]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP36:%.*]] = load i32, i32* [[TMP3]], align 4
// CHECK2-NEXT: [[TMP37:%.*]] = load i32, i32* [[T_VAR15]], align 4
// CHECK2-NEXT: [[CMP11:%.*]] = icmp slt i32 [[TMP36]], [[TMP37]]
// CHECK2-NEXT: br i1 [[CMP11]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2: cond.true:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP3]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[COND_END:%.*]]
// CHECK2: cond.false:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP39:%.*]] = load i32, i32* [[T_VAR15]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[COND_END]]
// CHECK2: cond.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ [[TMP38]], [[COND_TRUE]] ], [ [[TMP39]], [[COND_FALSE]] ]
// CHECK2-NEXT: store i32 [[COND]], i32* [[TMP3]], align 4
// CHECK2-NEXT: call void @__kmpc_end_reduce_nowait(%struct.ident_t* @[[GLOB2]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.reduction.var)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK2: .omp.reduction.case2:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP40:%.*]] = load i32, i32* [[T_VAR2]], align 4
// CHECK2-NEXT: [[TMP41:%.*]] = atomicrmw add i32* [[TMP0]], i32 [[TMP40]] monotonic, align 4
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL12:%.*]] = call noundef nonnull align 4 dereferenceable(4) %struct.S.0* @_ZN1SIiEanERKS0_(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP1]], %struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR3]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP42:%.*]] = bitcast %struct.S.0* [[TMP1]] to i8*
// CHECK2-NEXT: [[TMP43:%.*]] = bitcast %struct.S.0* [[CALL12]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP42]], i8* align 4 [[TMP43]], i64 4, i1 false)
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
// CHECK2-NEXT: call void @__kmpc_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL14:%.*]] = call noundef i32 @_ZN1SIiEcviEv(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP2]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TOBOOL15:%.*]] = icmp ne i32 [[CALL14]], 0
// CHECK2-NEXT: br i1 [[TOBOOL15]], label [[LAND_RHS16:%.*]], label [[LAND_END19:%.*]]
// CHECK2: land.rhs16:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL17:%.*]] = call noundef i32 @_ZN1SIiEcviEv(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR14]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TOBOOL18:%.*]] = icmp ne i32 [[CALL17]], 0
// CHECK2-NEXT: br label [[LAND_END19]]
// CHECK2: land.end19:
// CHECK2-NEXT: [[TMP44:%.*]] = phi i1 [ false, [[DOTOMP_REDUCTION_CASE2]] ], [ [[TOBOOL18]], [[LAND_RHS16]] ]
// CHECK2-NEXT: [[CONV20:%.*]] = zext i1 [[TMP44]] to i32
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[REF_TMP13]], i32 noundef [[CONV20]])
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: [[TMP45:%.*]] = bitcast %struct.S.0* [[TMP2]] to i8*
// CHECK2-NEXT: [[TMP46:%.*]] = bitcast %struct.S.0* [[REF_TMP13]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP45]], i8* align 4 [[TMP46]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[REF_TMP13]]) #[[ATTR4]]
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK2-NEXT: call void @__kmpc_end_critical(%struct.ident_t* @[[GLOB3]], i32 [[TMP7]], [8 x i32]* @.gomp_critical_user_.atomic_reduction.var)
// CHECK2-NEXT: [[TMP47:%.*]] = load i32, i32* [[T_VAR15]], align 4
// CHECK2-NEXT: [[TMP48:%.*]] = atomicrmw min i32* [[TMP3]], i32 [[TMP47]] monotonic, align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK2: .omp.reduction.default:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR14]]) #[[ATTR4]]
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[VAR3]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func.2
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK2-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR5]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK2-NEXT: [[REF_TMP:%.*]] = alloca [[STRUCT_S_0:%.*]], align 4
// CHECK2-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK2-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK2-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [4 x i8*]*
// CHECK2-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
// CHECK2-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [4 x i8*]*
// CHECK2-NEXT: [[TMP6:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 0
// CHECK2-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK2-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to i32*
// CHECK2-NEXT: [[TMP9:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 0
// CHECK2-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
// CHECK2-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to i32*
// CHECK2-NEXT: [[TMP12:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 1
// CHECK2-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP12]], align 8
// CHECK2-NEXT: [[TMP14:%.*]] = bitcast i8* [[TMP13]] to %struct.S.0*
// CHECK2-NEXT: [[TMP15:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 1
// CHECK2-NEXT: [[TMP16:%.*]] = load i8*, i8** [[TMP15]], align 8
// CHECK2-NEXT: [[TMP17:%.*]] = bitcast i8* [[TMP16]] to %struct.S.0*
// CHECK2-NEXT: [[TMP18:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 2
// CHECK2-NEXT: [[TMP19:%.*]] = load i8*, i8** [[TMP18]], align 8
// CHECK2-NEXT: [[TMP20:%.*]] = bitcast i8* [[TMP19]] to %struct.S.0*
// CHECK2-NEXT: [[TMP21:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 2
// CHECK2-NEXT: [[TMP22:%.*]] = load i8*, i8** [[TMP21]], align 8
// CHECK2-NEXT: [[TMP23:%.*]] = bitcast i8* [[TMP22]] to %struct.S.0*
// CHECK2-NEXT: [[TMP24:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP5]], i64 0, i64 3
// CHECK2-NEXT: [[TMP25:%.*]] = load i8*, i8** [[TMP24]], align 8
// CHECK2-NEXT: [[TMP26:%.*]] = bitcast i8* [[TMP25]] to i32*
// CHECK2-NEXT: [[TMP27:%.*]] = getelementptr inbounds [4 x i8*], [4 x i8*]* [[TMP3]], i64 0, i64 3
// CHECK2-NEXT: [[TMP28:%.*]] = load i8*, i8** [[TMP27]], align 8
// CHECK2-NEXT: [[TMP29:%.*]] = bitcast i8* [[TMP28]] to i32*
// CHECK2-NEXT: [[TMP30:%.*]] = load i32, i32* [[TMP11]], align 4
// CHECK2-NEXT: [[TMP31:%.*]] = load i32, i32* [[TMP8]], align 4
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 [[TMP30]], [[TMP31]]
// CHECK2-NEXT: store i32 [[ADD]], i32* [[TMP11]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL:%.*]] = call noundef nonnull align 4 dereferenceable(4) %struct.S.0* @_ZN1SIiEanERKS0_(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP17]], %struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP14]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TMP32:%.*]] = bitcast %struct.S.0* [[TMP17]] to i8*
// CHECK2-NEXT: [[TMP33:%.*]] = bitcast %struct.S.0* [[CALL]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP32]], i8* align 4 [[TMP33]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL2:%.*]] = call noundef i32 @_ZN1SIiEcviEv(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP23]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TOBOOL:%.*]] = icmp ne i32 [[CALL2]], 0
// CHECK2-NEXT: br i1 [[TOBOOL]], label [[LAND_RHS:%.*]], label [[LAND_END:%.*]]
// CHECK2: land.rhs:
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: [[CALL3:%.*]] = call noundef i32 @_ZN1SIiEcviEv(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP20]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TOBOOL4:%.*]] = icmp ne i32 [[CALL3]], 0
// CHECK2-NEXT: br label [[LAND_END]]
// CHECK2: land.end:
// CHECK2-NEXT: [[TMP34:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[TOBOOL4]], [[LAND_RHS]] ]
// CHECK2-NEXT: [[CONV:%.*]] = zext i1 [[TMP34]] to i32
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiEC1Ei(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]], i32 noundef [[CONV]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TMP35:%.*]] = bitcast %struct.S.0* [[TMP23]] to i8*
// CHECK2-NEXT: [[TMP36:%.*]] = bitcast %struct.S.0* [[REF_TMP]] to i8*
// CHECK2-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 4 [[TMP35]], i8* align 4 [[TMP36]], i64 4, i1 false)
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiED1Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[REF_TMP]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: [[TMP37:%.*]] = load i32, i32* [[TMP29]], align 4
// CHECK2-NEXT: [[TMP38:%.*]] = load i32, i32* [[TMP26]], align 4
// CHECK2-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP37]], [[TMP38]]
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
// CHECK2: cond.true:
// CHECK2-NEXT: [[TMP39:%.*]] = load i32, i32* [[TMP29]], align 4
// CHECK2-NEXT: br label [[COND_END:%.*]]
// CHECK2: cond.false:
// CHECK2-NEXT: [[TMP40:%.*]] = load i32, i32* [[TMP26]], align 4
// CHECK2-NEXT: br label [[COND_END]]
// CHECK2: cond.end:
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ [[TMP39]], [[COND_TRUE]] ], [ [[TMP40]], [[COND_FALSE]] ]
// CHECK2-NEXT: store i32 [[COND]], i32* [[TMP29]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEanERKS0_
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]], %struct.S.0* noundef nonnull align 4 dereferenceable(4) [[TMP0:%.*]]) #[[ATTR6]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store %struct.S.0* [[TMP0]], %struct.S.0** [[DOTADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: ret %struct.S.0* [[THIS1]]
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEcviEv
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) #[[ATTR6]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: ret i32 0
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiED1Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-NEXT: call void @_ZN1SIiED2Ev(%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS1]]) #[[ATTR4]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT: [[TMP0:%.*]] = load volatile double, double* @g, align 8
// CHECK2-NEXT: [[CONV:%.*]] = fptosi double [[TMP0]] to i32
// CHECK2-NEXT: store i32 [[CONV]], i32* [[F]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiEC2Ei
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]], i32 noundef [[A:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: store i32 [[A]], i32* [[A_ADDR]], align 4
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[F:%.*]] = getelementptr inbounds [[STRUCT_S_0:%.*]], %struct.S.0* [[THIS1]], i32 0, i32 0
// CHECK2-NEXT: [[TMP0:%.*]] = load i32, i32* [[A_ADDR]], align 4
// CHECK2-NEXT: [[CONV:%.*]] = sitofp i32 [[TMP0]] to double
// CHECK2-NEXT: [[TMP1:%.*]] = load volatile double, double* @g, align 8
// CHECK2-NEXT: [[ADD:%.*]] = fadd double [[CONV]], [[TMP1]]
// CHECK2-NEXT: [[CONV2:%.*]] = fptosi double [[ADD]] to i32
// CHECK2-NEXT: store i32 [[CONV2]], i32* [[F]], align 4
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN1SIiED2Ev
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK2-SAME: (%struct.S.0* noundef nonnull align 4 dereferenceable(4) [[THIS:%.*]]) unnamed_addr #[[ATTR1]] align 2 {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S.0*, align 8
// CHECK2-NEXT: store %struct.S.0* [[THIS]], %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: [[THIS1:%.*]] = load %struct.S.0*, %struct.S.0** [[THIS_ADDR]], align 8
// CHECK2-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@main
// CHECK3-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[REF_TMP:%.*]] = alloca [[CLASS_ANON:%.*]], align 1
// CHECK3-NEXT: store i32 0, i32* [[RETVAL]], align 4
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK3-NEXT: call void @"_ZZ4mainENK3$_0clEv"(%class.anon* noundef nonnull align 1 dereferenceable(1) [[REF_TMP]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: ret i32 0
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp_outlined.
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK3-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]]) #[[ATTR2:[0-9]+]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK3-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK3-NEXT: [[DOTOMP_SECTIONS_LB_:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_SECTIONS_UB_:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_SECTIONS_ST_:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_SECTIONS_IL_:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[DOTOMP_SECTIONS_IV_:%.*]] = alloca i32, align 4
// CHECK3-NEXT: [[G:%.*]] = alloca double, align 8
// CHECK3-NEXT: [[REF_TMP:%.*]] = alloca [[CLASS_ANON_0:%.*]], align 8
// CHECK3-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
// CHECK3-NEXT: [[ATOMIC_TEMP:%.*]] = alloca double, align 8
// CHECK3-NEXT: [[TMP:%.*]] = alloca double, align 8
// CHECK3-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK3-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK3-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_LB_]], align 4
// CHECK3-NEXT: store i32 1, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK3-NEXT: store i32 1, i32* [[DOTOMP_SECTIONS_ST_]], align 4
// CHECK3-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_IL_]], align 4
// CHECK3-NEXT: store double 0.000000e+00, double* [[G]], align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: [[TMP0:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK3-NEXT: [[TMP1:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK3-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP1]], i32 34, i32* [[DOTOMP_SECTIONS_IL_]], i32* [[DOTOMP_SECTIONS_LB_]], i32* [[DOTOMP_SECTIONS_UB_]], i32* [[DOTOMP_SECTIONS_ST_]], i32 1, i32 1)
// CHECK3-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK3-NEXT: [[TMP3:%.*]] = icmp slt i32 [[TMP2]], 1
// CHECK3-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], i32 [[TMP2]], i32 1
// CHECK3-NEXT: store i32 [[TMP4]], i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK3-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_LB_]], align 4
// CHECK3-NEXT: store i32 [[TMP5]], i32* [[DOTOMP_SECTIONS_IV_]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK3: omp.inner.for.cond:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK3-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK3-NEXT: [[CMP:%.*]] = icmp sle i32 [[TMP6]], [[TMP7]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: br i1 [[CMP]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
// CHECK3: omp.inner.for.body:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK3-NEXT: switch i32 [[TMP8]], label [[DOTOMP_SECTIONS_EXIT:%.*]] [
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: i32 0, label [[DOTOMP_SECTIONS_CASE:%.*]]
// CHECK3-NEXT: i32 1, label [[DOTOMP_SECTIONS_CASE1:%.*]]
// CHECK3-NEXT: ]
// CHECK3: .omp.sections.case:
// CHECK3-NEXT: store double 1.000000e+00, double* [[G]], align 8
// CHECK3-NEXT: br label [[DOTOMP_SECTIONS_EXIT]]
// CHECK3: .omp.sections.case1:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[CLASS_ANON_0]], %class.anon.0* [[REF_TMP]], i32 0, i32 0
// CHECK3-NEXT: store double* [[G]], double** [[TMP9]], align 8
[IRGen] Do not overwrite existing attributes in CGCall. When adding new attributes, existing attributes are dropped. While this appears to be a longstanding issue, this was highlighted by D105169 which dropped a lot of attributes due to adding the new noundef attribute. Ahmed Bougacha (@ab) tracked down the issue and provided the fix in CGCall.cpp. I bundled it up and updated the tests.
2022-01-20 21:45:19 +08:00
// CHECK3-NEXT: call void @"_ZZZ4mainENK3$_0clEvENKUlvE_clEv"(%class.anon.0* noundef nonnull align 8 dereferenceable(8) [[REF_TMP]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: br label [[DOTOMP_SECTIONS_EXIT]]
// CHECK3: .omp.sections.exit:
// CHECK3-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK3: omp.inner.for.inc:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK3-NEXT: [[INC:%.*]] = add nsw i32 [[TMP10]], 1
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: store i32 [[INC]], i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK3-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK3: omp.inner.for.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]])
// CHECK3-NEXT: [[TMP11:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
// CHECK3-NEXT: [[TMP12:%.*]] = bitcast double* [[G]] to i8*
// CHECK3-NEXT: store i8* [[TMP12]], i8** [[TMP11]], align 8
// CHECK3-NEXT: [[TMP13:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
// CHECK3-NEXT: [[TMP14:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP1]], i32 1, i64 8, i8* [[TMP13]], void (i8*, i8*)* @.omp.reduction.reduction_func, [8 x i32]* @.gomp_critical_user_.reduction.var)
// CHECK3-NEXT: switch i32 [[TMP14]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
// CHECK3-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
// CHECK3-NEXT: ]
// CHECK3: .omp.reduction.case1:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: [[TMP15:%.*]] = load double, double* @g, align 8
// CHECK3-NEXT: [[TMP16:%.*]] = load double, double* [[G]], align 8
// CHECK3-NEXT: [[ADD:%.*]] = fadd double [[TMP15]], [[TMP16]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: store double [[ADD]], double* @g, align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP1]], [8 x i32]* @.gomp_critical_user_.reduction.var)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK3: .omp.reduction.case2:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: [[TMP17:%.*]] = load double, double* [[G]], align 8
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i64, i64* bitcast (double* @g to i64*) monotonic, align 8
// CHECK3-NEXT: br label [[ATOMIC_CONT:%.*]]
// CHECK3: atomic_cont:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: [[TMP18:%.*]] = phi i64 [ [[ATOMIC_LOAD]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[TMP25:%.*]], [[ATOMIC_CONT]] ]
// CHECK3-NEXT: [[TMP19:%.*]] = bitcast double* [[ATOMIC_TEMP]] to i64*
// CHECK3-NEXT: [[TMP20:%.*]] = bitcast i64 [[TMP18]] to double
// CHECK3-NEXT: store double [[TMP20]], double* [[TMP]], align 8
// CHECK3-NEXT: [[TMP21:%.*]] = load double, double* [[TMP]], align 8
// CHECK3-NEXT: [[TMP22:%.*]] = load double, double* [[G]], align 8
// CHECK3-NEXT: [[ADD2:%.*]] = fadd double [[TMP21]], [[TMP22]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: store double [[ADD2]], double* [[ATOMIC_TEMP]], align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: [[TMP23:%.*]] = load i64, i64* [[TMP19]], align 8
// CHECK3-NEXT: [[TMP24:%.*]] = cmpxchg i64* bitcast (double* @g to i64*), i64 [[TMP18]], i64 [[TMP23]] monotonic monotonic, align 8
// CHECK3-NEXT: [[TMP25]] = extractvalue { i64, i1 } [[TMP24]], 0
// CHECK3-NEXT: [[TMP26:%.*]] = extractvalue { i64, i1 } [[TMP24]], 1
// CHECK3-NEXT: br i1 [[TMP26]], label [[ATOMIC_EXIT:%.*]], label [[ATOMIC_CONT]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3: atomic_exit:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP1]], [8 x i32]* @.gomp_critical_user_.reduction.var)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK3: .omp.reduction.default:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK3-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB3:[0-9]+]], i32 [[TMP1]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK3-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR4:[0-9]+]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK3-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK3-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK3-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK3-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK3-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
// CHECK3-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
// CHECK3-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
// CHECK3-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
// CHECK3-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK3-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to double*
// CHECK3-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
// CHECK3-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
// CHECK3-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to double*
// CHECK3-NEXT: [[TMP12:%.*]] = load double, double* [[TMP11]], align 8
// CHECK3-NEXT: [[TMP13:%.*]] = load double, double* [[TMP8]], align 8
// CHECK3-NEXT: [[ADD:%.*]] = fadd double [[TMP12]], [[TMP13]]
// CHECK3-NEXT: store double [[ADD]], double* [[TMP11]], align 8
// CHECK3-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@main
// CHECK4-SAME: () #[[ATTR1:[0-9]+]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[RETVAL:%.*]] = alloca i32, align 4
// CHECK4-NEXT: store i32 0, i32* [[RETVAL]], align 4
// CHECK4-NEXT: [[TMP0:%.*]] = load i8*, i8** getelementptr inbounds ([[STRUCT___BLOCK_LITERAL_GENERIC:%.*]], %struct.__block_literal_generic* bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor* }* @__block_literal_global to %struct.__block_literal_generic*), i32 0, i32 3), align 8
// CHECK4-NEXT: [[TMP1:%.*]] = bitcast i8* [[TMP0]] to void (i8*)*
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK4-NEXT: call void [[TMP1]](i8* noundef bitcast ({ i8**, i32, i32, i8*, %struct.__block_descriptor* }* @__block_literal_global to i8*))
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: ret i32 0
//
//
// CHECK4-LABEL: define {{[^@]+}}@__main_block_invoke
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK4-SAME: (i8* noundef [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR2:[0-9]+]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca i8*, align 8
// CHECK4-NEXT: [[BLOCK_ADDR:%.*]] = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>*, align 8
// CHECK4-NEXT: store i8* [[DOTBLOCK_DESCRIPTOR]], i8** [[DOTBLOCK_DESCRIPTOR_ADDR]], align 8
// CHECK4-NEXT: [[BLOCK:%.*]] = bitcast i8* [[DOTBLOCK_DESCRIPTOR]] to <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>*
// CHECK4-NEXT: store <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>* [[BLOCK]], <{ i8*, i32, i32, i8*, %struct.__block_descriptor* }>** [[BLOCK_ADDR]], align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB4:[0-9]+]], i32 0, void (i32*, i32*, ...)* bitcast (void (i32*, i32*)* @.omp_outlined. to void (i32*, i32*, ...)*))
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp_outlined.
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK4-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]]) #[[ATTR3:[0-9]+]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT: [[DOTOMP_SECTIONS_LB_:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_SECTIONS_UB_:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_SECTIONS_ST_:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_SECTIONS_IL_:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[DOTOMP_SECTIONS_IV_:%.*]] = alloca i32, align 4
// CHECK4-NEXT: [[G:%.*]] = alloca double, align 8
// CHECK4-NEXT: [[BLOCK:%.*]] = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>, align 8
// CHECK4-NEXT: [[DOTOMP_REDUCTION_RED_LIST:%.*]] = alloca [1 x i8*], align 8
// CHECK4-NEXT: [[ATOMIC_TEMP:%.*]] = alloca double, align 8
// CHECK4-NEXT: [[TMP:%.*]] = alloca double, align 8
// CHECK4-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK4-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK4-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_LB_]], align 4
// CHECK4-NEXT: store i32 1, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK4-NEXT: store i32 1, i32* [[DOTOMP_SECTIONS_ST_]], align 4
// CHECK4-NEXT: store i32 0, i32* [[DOTOMP_SECTIONS_IL_]], align 4
// CHECK4-NEXT: store double 0.000000e+00, double* [[G]], align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: [[TMP0:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK4-NEXT: [[TMP1:%.*]] = load i32, i32* [[TMP0]], align 4
// CHECK4-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP1]], i32 34, i32* [[DOTOMP_SECTIONS_IL_]], i32* [[DOTOMP_SECTIONS_LB_]], i32* [[DOTOMP_SECTIONS_UB_]], i32* [[DOTOMP_SECTIONS_ST_]], i32 1, i32 1)
// CHECK4-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK4-NEXT: [[TMP3:%.*]] = icmp slt i32 [[TMP2]], 1
// CHECK4-NEXT: [[TMP4:%.*]] = select i1 [[TMP3]], i32 [[TMP2]], i32 1
// CHECK4-NEXT: store i32 [[TMP4]], i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK4-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_LB_]], align 4
// CHECK4-NEXT: store i32 [[TMP5]], i32* [[DOTOMP_SECTIONS_IV_]], align 4
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
// CHECK4: omp.inner.for.cond:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK4-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_UB_]], align 4
// CHECK4-NEXT: [[CMP:%.*]] = icmp sle i32 [[TMP6]], [[TMP7]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: br i1 [[CMP]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
// CHECK4: omp.inner.for.body:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK4-NEXT: switch i32 [[TMP8]], label [[DOTOMP_SECTIONS_EXIT:%.*]] [
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: i32 0, label [[DOTOMP_SECTIONS_CASE:%.*]]
// CHECK4-NEXT: i32 1, label [[DOTOMP_SECTIONS_CASE1:%.*]]
// CHECK4-NEXT: ]
// CHECK4: .omp.sections.case:
// CHECK4-NEXT: store double 1.000000e+00, double* [[G]], align 8
// CHECK4-NEXT: br label [[DOTOMP_SECTIONS_EXIT]]
// CHECK4: .omp.sections.case1:
// CHECK4-NEXT: [[BLOCK_ISA:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>* [[BLOCK]], i32 0, i32 0
// CHECK4-NEXT: store i8* bitcast (i8** @_NSConcreteStackBlock to i8*), i8** [[BLOCK_ISA]], align 8
// CHECK4-NEXT: [[BLOCK_FLAGS:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>* [[BLOCK]], i32 0, i32 1
// CHECK4-NEXT: store i32 1073741824, i32* [[BLOCK_FLAGS]], align 8
// CHECK4-NEXT: [[BLOCK_RESERVED:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>* [[BLOCK]], i32 0, i32 2
// CHECK4-NEXT: store i32 0, i32* [[BLOCK_RESERVED]], align 4
// CHECK4-NEXT: [[BLOCK_INVOKE:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>* [[BLOCK]], i32 0, i32 3
// CHECK4-NEXT: store i8* bitcast (void (i8*)* @_block_invoke to i8*), i8** [[BLOCK_INVOKE]], align 8
// CHECK4-NEXT: [[BLOCK_DESCRIPTOR:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>* [[BLOCK]], i32 0, i32 4
// CHECK4-NEXT: store %struct.__block_descriptor* bitcast ({ i64, i64, i8*, i8* }* @__block_descriptor_tmp.1 to %struct.__block_descriptor*), %struct.__block_descriptor** [[BLOCK_DESCRIPTOR]], align 8
// CHECK4-NEXT: [[BLOCK_CAPTURED:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>* [[BLOCK]], i32 0, i32 5
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: [[TMP9:%.*]] = load volatile double, double* [[G]], align 8
// CHECK4-NEXT: store volatile double [[TMP9]], double* [[BLOCK_CAPTURED]], align 8
// CHECK4-NEXT: [[TMP10:%.*]] = bitcast <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>* [[BLOCK]] to void ()*
// CHECK4-NEXT: [[BLOCK_LITERAL:%.*]] = bitcast void ()* [[TMP10]] to %struct.__block_literal_generic*
// CHECK4-NEXT: [[TMP11:%.*]] = getelementptr inbounds [[STRUCT___BLOCK_LITERAL_GENERIC:%.*]], %struct.__block_literal_generic* [[BLOCK_LITERAL]], i32 0, i32 3
// CHECK4-NEXT: [[TMP12:%.*]] = bitcast %struct.__block_literal_generic* [[BLOCK_LITERAL]] to i8*
// CHECK4-NEXT: [[TMP13:%.*]] = load i8*, i8** [[TMP11]], align 8
// CHECK4-NEXT: [[TMP14:%.*]] = bitcast i8* [[TMP13]] to void (i8*)*
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK4-NEXT: call void [[TMP14]](i8* noundef [[TMP12]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: br label [[DOTOMP_SECTIONS_EXIT]]
// CHECK4: .omp.sections.exit:
// CHECK4-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
// CHECK4: omp.inner.for.inc:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: [[TMP15:%.*]] = load i32, i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK4-NEXT: [[INC:%.*]] = add nsw i32 [[TMP15]], 1
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: store i32 [[INC]], i32* [[DOTOMP_SECTIONS_IV_]], align 4
// CHECK4-NEXT: br label [[OMP_INNER_FOR_COND]]
// CHECK4: omp.inner.for.end:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP1]])
// CHECK4-NEXT: [[TMP16:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]], i64 0, i64 0
// CHECK4-NEXT: [[TMP17:%.*]] = bitcast double* [[G]] to i8*
// CHECK4-NEXT: store i8* [[TMP17]], i8** [[TMP16]], align 8
// CHECK4-NEXT: [[TMP18:%.*]] = bitcast [1 x i8*]* [[DOTOMP_REDUCTION_RED_LIST]] to i8*
// CHECK4-NEXT: [[TMP19:%.*]] = call i32 @__kmpc_reduce(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 [[TMP1]], i32 1, i64 8, i8* [[TMP18]], void (i8*, i8*)* @.omp.reduction.reduction_func, [8 x i32]* @.gomp_critical_user_.reduction.var)
// CHECK4-NEXT: switch i32 [[TMP19]], label [[DOTOMP_REDUCTION_DEFAULT:%.*]] [
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: i32 1, label [[DOTOMP_REDUCTION_CASE1:%.*]]
// CHECK4-NEXT: i32 2, label [[DOTOMP_REDUCTION_CASE2:%.*]]
// CHECK4-NEXT: ]
// CHECK4: .omp.reduction.case1:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: [[TMP20:%.*]] = load double, double* @g, align 8
// CHECK4-NEXT: [[TMP21:%.*]] = load double, double* [[G]], align 8
// CHECK4-NEXT: [[ADD:%.*]] = fadd double [[TMP20]], [[TMP21]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: store double [[ADD]], double* @g, align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP1]], [8 x i32]* @.gomp_critical_user_.reduction.var)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK4: .omp.reduction.case2:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: [[TMP22:%.*]] = load double, double* [[G]], align 8
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: [[ATOMIC_LOAD:%.*]] = load atomic i64, i64* bitcast (double* @g to i64*) monotonic, align 8
// CHECK4-NEXT: br label [[ATOMIC_CONT:%.*]]
// CHECK4: atomic_cont:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: [[TMP23:%.*]] = phi i64 [ [[ATOMIC_LOAD]], [[DOTOMP_REDUCTION_CASE2]] ], [ [[TMP30:%.*]], [[ATOMIC_CONT]] ]
// CHECK4-NEXT: [[TMP24:%.*]] = bitcast double* [[ATOMIC_TEMP]] to i64*
// CHECK4-NEXT: [[TMP25:%.*]] = bitcast i64 [[TMP23]] to double
// CHECK4-NEXT: store double [[TMP25]], double* [[TMP]], align 8
// CHECK4-NEXT: [[TMP26:%.*]] = load double, double* [[TMP]], align 8
// CHECK4-NEXT: [[TMP27:%.*]] = load double, double* [[G]], align 8
// CHECK4-NEXT: [[ADD2:%.*]] = fadd double [[TMP26]], [[TMP27]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: store double [[ADD2]], double* [[ATOMIC_TEMP]], align 8
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: [[TMP28:%.*]] = load i64, i64* [[TMP24]], align 8
// CHECK4-NEXT: [[TMP29:%.*]] = cmpxchg i64* bitcast (double* @g to i64*), i64 [[TMP23]], i64 [[TMP28]] monotonic monotonic, align 8
// CHECK4-NEXT: [[TMP30]] = extractvalue { i64, i1 } [[TMP29]], 0
// CHECK4-NEXT: [[TMP31:%.*]] = extractvalue { i64, i1 } [[TMP29]], 1
// CHECK4-NEXT: br i1 [[TMP31]], label [[ATOMIC_EXIT:%.*]], label [[ATOMIC_CONT]]
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4: atomic_exit:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: call void @__kmpc_end_reduce(%struct.ident_t* @[[GLOB2]], i32 [[TMP1]], [8 x i32]* @.gomp_critical_user_.reduction.var)
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: br label [[DOTOMP_REDUCTION_DEFAULT]]
// CHECK4: .omp.reduction.default:
Revert "[OpenMP] Codegen aggregate for outlined function captures" This reverts commit 1d66649adf28d48ae1731516d87fb899426e3349. Revert to fix AMG GPU issue.
2021-09-22 04:20:39 +08:00
// CHECK4-NEXT: call void @__kmpc_barrier(%struct.ident_t* @[[GLOB3:[0-9]+]], i32 [[TMP1]])
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@_block_invoke
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK4-SAME: (i8* noundef [[DOTBLOCK_DESCRIPTOR:%.*]]) #[[ATTR2]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[DOTBLOCK_DESCRIPTOR_ADDR:%.*]] = alloca i8*, align 8
// CHECK4-NEXT: [[BLOCK_ADDR:%.*]] = alloca <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>*, align 8
// CHECK4-NEXT: store i8* [[DOTBLOCK_DESCRIPTOR]], i8** [[DOTBLOCK_DESCRIPTOR_ADDR]], align 8
// CHECK4-NEXT: [[BLOCK:%.*]] = bitcast i8* [[DOTBLOCK_DESCRIPTOR]] to <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>*
// CHECK4-NEXT: store <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>* [[BLOCK]], <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>** [[BLOCK_ADDR]], align 8
// CHECK4-NEXT: [[BLOCK_CAPTURE_ADDR:%.*]] = getelementptr inbounds <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>, <{ i8*, i32, i32, i8*, %struct.__block_descriptor*, double }>* [[BLOCK]], i32 0, i32 5
// CHECK4-NEXT: store double 2.000000e+00, double* [[BLOCK_CAPTURE_ADDR]], align 8
// CHECK4-NEXT: ret void
//
//
// CHECK4-LABEL: define {{[^@]+}}@.omp.reduction.reduction_func
[Clang/Test]: Rename enable_noundef_analysis to disable-noundef-analysis and turn it off by default Turning on `enable_noundef_analysis` flag allows better codegen by removing freeze instructions. I modified clang by renaming `enable_noundef_analysis` flag to `disable-noundef-analysis` and turning it off by default. Test updates are made as a separate patch: D108453 Reviewed By: eugenis Differential Revision: https://reviews.llvm.org/D105169
2022-01-16 17:53:11 +08:00
// CHECK4-SAME: (i8* noundef [[TMP0:%.*]], i8* noundef [[TMP1:%.*]]) #[[ATTR5:[0-9]+]] {
[OpenMP][NFC] Refactor Clang OpenMP tests using update_cc_test_checks This patch refactors a subset of Clang OpenMP tests, generating checklines using the update_cc_test_checks script. This refactoring facilitates updating the Clang OpenMP code generation codebase by automating test generation. Reviewed By: jdoerfert Differential Revision: https://reviews.llvm.org/D101849
2021-05-06 06:13:14 +08:00
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[DOTADDR:%.*]] = alloca i8*, align 8
// CHECK4-NEXT: [[DOTADDR1:%.*]] = alloca i8*, align 8
// CHECK4-NEXT: store i8* [[TMP0]], i8** [[DOTADDR]], align 8
// CHECK4-NEXT: store i8* [[TMP1]], i8** [[DOTADDR1]], align 8
// CHECK4-NEXT: [[TMP2:%.*]] = load i8*, i8** [[DOTADDR]], align 8
// CHECK4-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP2]] to [1 x i8*]*
// CHECK4-NEXT: [[TMP4:%.*]] = load i8*, i8** [[DOTADDR1]], align 8
// CHECK4-NEXT: [[TMP5:%.*]] = bitcast i8* [[TMP4]] to [1 x i8*]*
// CHECK4-NEXT: [[TMP6:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP5]], i64 0, i64 0
// CHECK4-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK4-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to double*
// CHECK4-NEXT: [[TMP9:%.*]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[TMP3]], i64 0, i64 0
// CHECK4-NEXT: [[TMP10:%.*]] = load i8*, i8** [[TMP9]], align 8
// CHECK4-NEXT: [[TMP11:%.*]] = bitcast i8* [[TMP10]] to double*
// CHECK4-NEXT: [[TMP12:%.*]] = load double, double* [[TMP11]], align 8
// CHECK4-NEXT: [[TMP13:%.*]] = load double, double* [[TMP8]], align 8
// CHECK4-NEXT: [[ADD:%.*]] = fadd double [[TMP12]], [[TMP13]]
// CHECK4-NEXT: store double [[ADD]], double* [[TMP11]], align 8
// CHECK4-NEXT: ret void
//