llvm-project/clang/test/OpenMP/task_target_device_codegen.c

106 lines
7.7 KiB
C

// 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 _
// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp -fopenmp-version=50 -x c -emit-llvm %s -o - | FileCheck %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -x c -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp -fopenmp-version=50 -x c -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s
// RUN: %clang_cc1 -verify -triple x86_64-apple-darwin10 -fopenmp-simd -fopenmp-version=50 -x c -emit-llvm %s -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -x c -triple x86_64-apple-darwin10 -emit-pch -o %t %s
// RUN: %clang_cc1 -fopenmp-simd -fopenmp-version=50 -x c -triple x86_64-apple-darwin10 -include-pch %t -verify %s -emit-llvm -o - | FileCheck --check-prefix SIMD-ONLY0 %s
// SIMD-ONLY0-NOT: {{__kmpc|__tgt}}
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
void test_task_affinity(void) {
int t;
#pragma omp task
{
#pragma omp target device(t)
;
}
}
#endif
// CHECK-LABEL: define {{[^@]+}}@test_task_affinity
// CHECK-SAME: () #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[T:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[AGG_CAPTURED:%.*]] = alloca [[STRUCT_ANON:%.*]], align 1
// CHECK-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB1:[0-9]+]])
// CHECK-NEXT: [[TMP1:%.*]] = call i8* @__kmpc_omp_task_alloc(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i32 1, i64 48, i64 0, i32 (i32, i8*)* bitcast (i32 (i32, %struct.kmp_task_t_with_privates*)* @.omp_task_entry. to i32 (i32, i8*)*))
// CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[TMP1]] to %struct.kmp_task_t_with_privates*
// CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP2]], i32 0, i32 0
// CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES]], %struct.kmp_task_t_with_privates* [[TMP2]], i32 0, i32 1
// CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP4]], i32 0, i32 0
// CHECK-NEXT: [[TMP6:%.*]] = load i32, i32* [[T]], align 4
// CHECK-NEXT: store i32 [[TMP6]], i32* [[TMP5]], align 8
// CHECK-NEXT: [[TMP7:%.*]] = call i32 @__kmpc_omp_task(%struct.ident_t* @[[GLOB1]], i32 [[TMP0]], i8* [[TMP1]])
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_test_task_affinity_l18
// CHECK-SAME: () #[[ATTR1:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@.omp_task_privates_map.
// CHECK-SAME: (%struct..kmp_privates.t* noalias noundef [[TMP0:%.*]], i32** noalias noundef [[TMP1:%.*]]) #[[ATTR2:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DOTADDR:%.*]] = alloca %struct..kmp_privates.t*, align 8
// CHECK-NEXT: [[DOTADDR1:%.*]] = alloca i32**, align 8
// CHECK-NEXT: store %struct..kmp_privates.t* [[TMP0]], %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK-NEXT: store i32** [[TMP1]], i32*** [[DOTADDR1]], align 8
// CHECK-NEXT: [[TMP2:%.*]] = load %struct..kmp_privates.t*, %struct..kmp_privates.t** [[DOTADDR]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT__KMP_PRIVATES_T:%.*]], %struct..kmp_privates.t* [[TMP2]], i32 0, i32 0
// CHECK-NEXT: [[TMP4:%.*]] = load i32**, i32*** [[DOTADDR1]], align 8
// CHECK-NEXT: store i32* [[TMP3]], i32** [[TMP4]], align 8
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define {{[^@]+}}@.omp_task_entry.
// CHECK-SAME: (i32 noundef [[TMP0:%.*]], %struct.kmp_task_t_with_privates* noalias noundef [[TMP1:%.*]]) #[[ATTR3:[0-9]+]] {
// CHECK-NEXT: entry:
// CHECK-NEXT: [[DOTGLOBAL_TID__ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[DOTPART_ID__ADDR_I:%.*]] = alloca i32*, align 8
// CHECK-NEXT: [[DOTPRIVATES__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK-NEXT: [[DOTCOPY_FN__ADDR_I:%.*]] = alloca void (i8*, ...)*, align 8
// CHECK-NEXT: [[DOTTASK_T__ADDR_I:%.*]] = alloca i8*, align 8
// CHECK-NEXT: [[__CONTEXT_ADDR_I:%.*]] = alloca %struct.anon*, align 8
// CHECK-NEXT: [[DOTFIRSTPRIV_PTR_ADDR_I:%.*]] = alloca i32*, align 8
// CHECK-NEXT: [[DOTCAPTURE_EXPR__I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[DOTADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[DOTADDR1:%.*]] = alloca %struct.kmp_task_t_with_privates*, align 8
// CHECK-NEXT: store i32 [[TMP0]], i32* [[DOTADDR]], align 4
// CHECK-NEXT: store %struct.kmp_task_t_with_privates* [[TMP1]], %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[DOTADDR]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load %struct.kmp_task_t_with_privates*, %struct.kmp_task_t_with_privates** [[DOTADDR1]], align 8
// CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES:%.*]], %struct.kmp_task_t_with_privates* [[TMP3]], i32 0, i32 0
// CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T:%.*]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 2
// CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T]], %struct.kmp_task_t* [[TMP4]], i32 0, i32 0
// CHECK-NEXT: [[TMP7:%.*]] = load i8*, i8** [[TMP6]], align 8
// CHECK-NEXT: [[TMP8:%.*]] = bitcast i8* [[TMP7]] to %struct.anon*
// CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds [[STRUCT_KMP_TASK_T_WITH_PRIVATES]], %struct.kmp_task_t_with_privates* [[TMP3]], i32 0, i32 1
// CHECK-NEXT: [[TMP10:%.*]] = bitcast %struct..kmp_privates.t* [[TMP9]] to i8*
// CHECK-NEXT: [[TMP11:%.*]] = bitcast %struct.kmp_task_t_with_privates* [[TMP3]] to i8*
// CHECK-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META3:![0-9]+]])
// CHECK-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META6:![0-9]+]])
// CHECK-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META8:![0-9]+]])
// CHECK-NEXT: call void @llvm.experimental.noalias.scope.decl(metadata [[META10:![0-9]+]])
// CHECK-NEXT: store i32 [[TMP2]], i32* [[DOTGLOBAL_TID__ADDR_I]], align 4, !noalias !12
// CHECK-NEXT: store i32* [[TMP5]], i32** [[DOTPART_ID__ADDR_I]], align 8, !noalias !12
// CHECK-NEXT: store i8* [[TMP10]], i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !12
// CHECK-NEXT: store void (i8*, ...)* bitcast (void (%struct..kmp_privates.t*, i32**)* @.omp_task_privates_map. to void (i8*, ...)*), void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !12
// CHECK-NEXT: store i8* [[TMP11]], i8** [[DOTTASK_T__ADDR_I]], align 8, !noalias !12
// CHECK-NEXT: store %struct.anon* [[TMP8]], %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK-NEXT: [[TMP12:%.*]] = load %struct.anon*, %struct.anon** [[__CONTEXT_ADDR_I]], align 8, !noalias !12
// CHECK-NEXT: [[TMP13:%.*]] = load void (i8*, ...)*, void (i8*, ...)** [[DOTCOPY_FN__ADDR_I]], align 8, !noalias !12
// CHECK-NEXT: [[TMP14:%.*]] = load i8*, i8** [[DOTPRIVATES__ADDR_I]], align 8, !noalias !12
// CHECK-NEXT: [[TMP15:%.*]] = bitcast void (i8*, ...)* [[TMP13]] to void (i8*, i32**)*
// CHECK-NEXT: call void [[TMP15]](i8* [[TMP14]], i32** [[DOTFIRSTPRIV_PTR_ADDR_I]]) #[[ATTR4:[0-9]+]]
// CHECK-NEXT: [[TMP16:%.*]] = load i32*, i32** [[DOTFIRSTPRIV_PTR_ADDR_I]], align 8, !noalias !12
// CHECK-NEXT: [[TMP17:%.*]] = load i32, i32* [[TMP16]], align 4
// CHECK-NEXT: store i32 [[TMP17]], i32* [[DOTCAPTURE_EXPR__I]], align 4, !noalias !12
// CHECK-NEXT: call void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_test_task_affinity_l18() #[[ATTR4]]
// CHECK-NEXT: ret i32 0
//