forked from OSchip/llvm-project
347 lines
22 KiB
C++
347 lines
22 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 -no-opaque-pointers -verify -fopenmp -x c++ -triple x86_64-unknown-unknown -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK1
|
|
// RUN: %clang_cc1 -no-opaque-pointers -fopenmp -x c++ -std=c++11 -triple x86_64-unknown-unknown -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -no-opaque-pointers -fopenmp -x c++ -triple x86_64-unknown-unknown -std=c++11 -include-pch %t -verify %s -emit-llvm -o - | FileCheck %s --check-prefix=CHECK2
|
|
// RUN: %clang_cc1 -no-opaque-pointers -verify -fopenmp -x c++ -std=c++11 -DLAMBDA -triple x86_64-unknown-linux -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK3
|
|
// RUN: %clang_cc1 -no-opaque-pointers -verify -fopenmp -x c++ -fblocks -DBLOCKS -triple x86_64-unknown-linux -emit-llvm %s -o - | FileCheck %s --check-prefix=CHECK4
|
|
|
|
// RUN: %clang_cc1 -no-opaque-pointers -verify -fopenmp-simd -x c++ -triple x86_64-unknown-unknown -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-unknown-unknown -emit-pch -o %t %s
|
|
// RUN: %clang_cc1 -no-opaque-pointers -fopenmp-simd -x c++ -triple x86_64-unknown-unknown -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-unknown-linux -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-unknown-linux -emit-llvm %s -o - | FileCheck %s --implicit-check-not="{{__kmpc|__tgt}}"
|
|
// expected-no-diagnostics
|
|
#ifndef HEADER
|
|
#define HEADER
|
|
|
|
void foo(float *c) {
|
|
#pragma omp parallel for simd aligned(c)
|
|
for (int i = 0; i < 10; ++i);
|
|
}
|
|
|
|
#endif
|
|
|
|
// CHECK1-LABEL: define {{[^@]+}}@_Z3fooPf
|
|
// CHECK1-SAME: (float* noundef [[C:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[C_ADDR:%.*]] = alloca float*, align 8
|
|
// CHECK1-NEXT: store float* [[C]], float** [[C_ADDR]], align 8
|
|
// CHECK1-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, float**)* @.omp_outlined. to void (i32*, i32*, ...)*), float** [[C_ADDR]])
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK1-LABEL: define {{[^@]+}}@.omp_outlined.
|
|
// CHECK1-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], float** noundef nonnull align 8 dereferenceable(8) [[C:%.*]]) #[[ATTR1:[0-9]+]] {
|
|
// CHECK1-NEXT: entry:
|
|
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK1-NEXT: [[C_ADDR:%.*]] = alloca float**, align 8
|
|
// CHECK1-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: store float** [[C]], float*** [[C_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP0:%.*]] = load float**, float*** [[C_ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP1:%.*]] = load float*, float** [[TMP0]], align 8
|
|
// CHECK1-NEXT: call void @llvm.assume(i1 true) [ "align"(float* [[TMP1]], i64 16) ]
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK1-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP2:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK1-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP3]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK1-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP4]], 9
|
|
// CHECK1-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK1: cond.true:
|
|
// CHECK1-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK1: cond.false:
|
|
// CHECK1-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: br label [[COND_END]]
|
|
// CHECK1: cond.end:
|
|
// CHECK1-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP5]], [[COND_FALSE]] ]
|
|
// CHECK1-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK1-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK1-NEXT: store i32 [[TMP6]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK1: omp.inner.for.cond:
|
|
// CHECK1-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK1-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4, !llvm.access.group !3
|
|
// CHECK1-NEXT: [[CMP1:%.*]] = icmp sle i32 [[TMP7]], [[TMP8]]
|
|
// CHECK1-NEXT: br i1 [[CMP1]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK1: omp.inner.for.body:
|
|
// CHECK1-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK1-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP9]], 1
|
|
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK1-NEXT: store i32 [[ADD]], i32* [[I]], align 4, !llvm.access.group !3
|
|
// CHECK1-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK1: omp.body.continue:
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK1: omp.inner.for.inc:
|
|
// CHECK1-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK1-NEXT: [[ADD2:%.*]] = add nsw i32 [[TMP10]], 1
|
|
// CHECK1-NEXT: store i32 [[ADD2]], i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK1-NEXT: br label [[OMP_INNER_FOR_COND]], !llvm.loop [[LOOP4:![0-9]+]]
|
|
// CHECK1: omp.inner.for.end:
|
|
// CHECK1-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK1: omp.loop.exit:
|
|
// CHECK1-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP3]])
|
|
// CHECK1-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK1-NEXT: [[TMP12:%.*]] = icmp ne i32 [[TMP11]], 0
|
|
// CHECK1-NEXT: br i1 [[TMP12]], label [[DOTOMP_FINAL_THEN:%.*]], label [[DOTOMP_FINAL_DONE:%.*]]
|
|
// CHECK1: .omp.final.then:
|
|
// CHECK1-NEXT: store i32 10, i32* [[I]], align 4
|
|
// CHECK1-NEXT: br label [[DOTOMP_FINAL_DONE]]
|
|
// CHECK1: .omp.final.done:
|
|
// CHECK1-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@_Z3fooPf
|
|
// CHECK2-SAME: (float* noundef [[C:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[C_ADDR:%.*]] = alloca float*, align 8
|
|
// CHECK2-NEXT: store float* [[C]], float** [[C_ADDR]], align 8
|
|
// CHECK2-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, float**)* @.omp_outlined. to void (i32*, i32*, ...)*), float** [[C_ADDR]])
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK2-LABEL: define {{[^@]+}}@.omp_outlined.
|
|
// CHECK2-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], float** noundef nonnull align 8 dereferenceable(8) [[C:%.*]]) #[[ATTR1:[0-9]+]] {
|
|
// CHECK2-NEXT: entry:
|
|
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK2-NEXT: [[C_ADDR:%.*]] = alloca float**, align 8
|
|
// CHECK2-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: store float** [[C]], float*** [[C_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP0:%.*]] = load float**, float*** [[C_ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP1:%.*]] = load float*, float** [[TMP0]], align 8
|
|
// CHECK2-NEXT: call void @llvm.assume(i1 true) [ "align"(float* [[TMP1]], i64 16) ]
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK2-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP2:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK2-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP3]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK2-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP4]], 9
|
|
// CHECK2-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK2: cond.true:
|
|
// CHECK2-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK2: cond.false:
|
|
// CHECK2-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: br label [[COND_END]]
|
|
// CHECK2: cond.end:
|
|
// CHECK2-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP5]], [[COND_FALSE]] ]
|
|
// CHECK2-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK2-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK2-NEXT: store i32 [[TMP6]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK2: omp.inner.for.cond:
|
|
// CHECK2-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK2-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4, !llvm.access.group !3
|
|
// CHECK2-NEXT: [[CMP1:%.*]] = icmp sle i32 [[TMP7]], [[TMP8]]
|
|
// CHECK2-NEXT: br i1 [[CMP1]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK2: omp.inner.for.body:
|
|
// CHECK2-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK2-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP9]], 1
|
|
// CHECK2-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK2-NEXT: store i32 [[ADD]], i32* [[I]], align 4, !llvm.access.group !3
|
|
// CHECK2-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK2: omp.body.continue:
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK2: omp.inner.for.inc:
|
|
// CHECK2-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK2-NEXT: [[ADD2:%.*]] = add nsw i32 [[TMP10]], 1
|
|
// CHECK2-NEXT: store i32 [[ADD2]], i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK2-NEXT: br label [[OMP_INNER_FOR_COND]], !llvm.loop [[LOOP4:![0-9]+]]
|
|
// CHECK2: omp.inner.for.end:
|
|
// CHECK2-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK2: omp.loop.exit:
|
|
// CHECK2-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP3]])
|
|
// CHECK2-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK2-NEXT: [[TMP12:%.*]] = icmp ne i32 [[TMP11]], 0
|
|
// CHECK2-NEXT: br i1 [[TMP12]], label [[DOTOMP_FINAL_THEN:%.*]], label [[DOTOMP_FINAL_DONE:%.*]]
|
|
// CHECK2: .omp.final.then:
|
|
// CHECK2-NEXT: store i32 10, i32* [[I]], align 4
|
|
// CHECK2-NEXT: br label [[DOTOMP_FINAL_DONE]]
|
|
// CHECK2: .omp.final.done:
|
|
// CHECK2-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK3-LABEL: define {{[^@]+}}@_Z3fooPf
|
|
// CHECK3-SAME: (float* noundef [[C:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
// CHECK3-NEXT: entry:
|
|
// CHECK3-NEXT: [[C_ADDR:%.*]] = alloca float*, align 8
|
|
// CHECK3-NEXT: store float* [[C]], float** [[C_ADDR]], align 8
|
|
// CHECK3-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, float**)* @.omp_outlined. to void (i32*, i32*, ...)*), float** [[C_ADDR]])
|
|
// CHECK3-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK3-LABEL: define {{[^@]+}}@.omp_outlined.
|
|
// CHECK3-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], float** noundef nonnull align 8 dereferenceable(8) [[C:%.*]]) #[[ATTR1:[0-9]+]] {
|
|
// CHECK3-NEXT: entry:
|
|
// CHECK3-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK3-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK3-NEXT: [[C_ADDR:%.*]] = alloca float**, align 8
|
|
// CHECK3-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK3-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// 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 float** [[C]], float*** [[C_ADDR]], align 8
|
|
// CHECK3-NEXT: [[TMP0:%.*]] = load float**, float*** [[C_ADDR]], align 8
|
|
// CHECK3-NEXT: [[TMP1:%.*]] = load float*, float** [[TMP0]], align 8
|
|
// CHECK3-NEXT: call void @llvm.assume(i1 true) [ "align"(float* [[TMP1]], i64 16) ]
|
|
// CHECK3-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK3-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK3-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK3-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK3-NEXT: [[TMP2:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK3-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
|
|
// CHECK3-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP3]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK3-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK3-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP4]], 9
|
|
// CHECK3-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK3: cond.true:
|
|
// CHECK3-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK3: cond.false:
|
|
// CHECK3-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK3-NEXT: br label [[COND_END]]
|
|
// CHECK3: cond.end:
|
|
// CHECK3-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP5]], [[COND_FALSE]] ]
|
|
// CHECK3-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK3-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK3-NEXT: store i32 [[TMP6]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK3-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK3: omp.inner.for.cond:
|
|
// CHECK3-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK3-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4, !llvm.access.group !3
|
|
// CHECK3-NEXT: [[CMP1:%.*]] = icmp sle i32 [[TMP7]], [[TMP8]]
|
|
// CHECK3-NEXT: br i1 [[CMP1]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK3: omp.inner.for.body:
|
|
// CHECK3-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK3-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP9]], 1
|
|
// CHECK3-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK3-NEXT: store i32 [[ADD]], i32* [[I]], align 4, !llvm.access.group !3
|
|
// CHECK3-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK3: omp.body.continue:
|
|
// CHECK3-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK3: omp.inner.for.inc:
|
|
// CHECK3-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK3-NEXT: [[ADD2:%.*]] = add nsw i32 [[TMP10]], 1
|
|
// CHECK3-NEXT: store i32 [[ADD2]], i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK3-NEXT: br label [[OMP_INNER_FOR_COND]], !llvm.loop [[LOOP4:![0-9]+]]
|
|
// CHECK3: omp.inner.for.end:
|
|
// CHECK3-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK3: omp.loop.exit:
|
|
// CHECK3-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP3]])
|
|
// CHECK3-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK3-NEXT: [[TMP12:%.*]] = icmp ne i32 [[TMP11]], 0
|
|
// CHECK3-NEXT: br i1 [[TMP12]], label [[DOTOMP_FINAL_THEN:%.*]], label [[DOTOMP_FINAL_DONE:%.*]]
|
|
// CHECK3: .omp.final.then:
|
|
// CHECK3-NEXT: store i32 10, i32* [[I]], align 4
|
|
// CHECK3-NEXT: br label [[DOTOMP_FINAL_DONE]]
|
|
// CHECK3: .omp.final.done:
|
|
// CHECK3-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK4-LABEL: define {{[^@]+}}@_Z3fooPf
|
|
// CHECK4-SAME: (float* noundef [[C:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
// CHECK4-NEXT: entry:
|
|
// CHECK4-NEXT: [[C_ADDR:%.*]] = alloca float*, align 8
|
|
// CHECK4-NEXT: store float* [[C]], float** [[C_ADDR]], align 8
|
|
// CHECK4-NEXT: call void (%struct.ident_t*, i32, void (i32*, i32*, ...)*, ...) @__kmpc_fork_call(%struct.ident_t* @[[GLOB2:[0-9]+]], i32 1, void (i32*, i32*, ...)* bitcast (void (i32*, i32*, float**)* @.omp_outlined. to void (i32*, i32*, ...)*), float** [[C_ADDR]])
|
|
// CHECK4-NEXT: ret void
|
|
//
|
|
//
|
|
// CHECK4-LABEL: define {{[^@]+}}@.omp_outlined.
|
|
// CHECK4-SAME: (i32* noalias noundef [[DOTGLOBAL_TID_:%.*]], i32* noalias noundef [[DOTBOUND_TID_:%.*]], float** noundef nonnull align 8 dereferenceable(8) [[C:%.*]]) #[[ATTR1:[0-9]+]] {
|
|
// CHECK4-NEXT: entry:
|
|
// CHECK4-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK4-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
|
|
// CHECK4-NEXT: [[C_ADDR:%.*]] = alloca float**, align 8
|
|
// CHECK4-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[TMP:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[DOTOMP_STRIDE:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[DOTOMP_IS_LAST:%.*]] = alloca i32, align 4
|
|
// CHECK4-NEXT: [[I:%.*]] = alloca i32, align 4
|
|
// 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 float** [[C]], float*** [[C_ADDR]], align 8
|
|
// CHECK4-NEXT: [[TMP0:%.*]] = load float**, float*** [[C_ADDR]], align 8
|
|
// CHECK4-NEXT: [[TMP1:%.*]] = load float*, float** [[TMP0]], align 8
|
|
// CHECK4-NEXT: call void @llvm.assume(i1 true) [ "align"(float* [[TMP1]], i64 16) ]
|
|
// CHECK4-NEXT: store i32 0, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK4-NEXT: store i32 9, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK4-NEXT: store i32 1, i32* [[DOTOMP_STRIDE]], align 4
|
|
// CHECK4-NEXT: store i32 0, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK4-NEXT: [[TMP2:%.*]] = load i32*, i32** [[DOTGLOBAL_TID__ADDR]], align 8
|
|
// CHECK4-NEXT: [[TMP3:%.*]] = load i32, i32* [[TMP2]], align 4
|
|
// CHECK4-NEXT: call void @__kmpc_for_static_init_4(%struct.ident_t* @[[GLOB1:[0-9]+]], i32 [[TMP3]], i32 34, i32* [[DOTOMP_IS_LAST]], i32* [[DOTOMP_LB]], i32* [[DOTOMP_UB]], i32* [[DOTOMP_STRIDE]], i32 1, i32 1)
|
|
// CHECK4-NEXT: [[TMP4:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK4-NEXT: [[CMP:%.*]] = icmp sgt i32 [[TMP4]], 9
|
|
// CHECK4-NEXT: br i1 [[CMP]], label [[COND_TRUE:%.*]], label [[COND_FALSE:%.*]]
|
|
// CHECK4: cond.true:
|
|
// CHECK4-NEXT: br label [[COND_END:%.*]]
|
|
// CHECK4: cond.false:
|
|
// CHECK4-NEXT: [[TMP5:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4
|
|
// CHECK4-NEXT: br label [[COND_END]]
|
|
// CHECK4: cond.end:
|
|
// CHECK4-NEXT: [[COND:%.*]] = phi i32 [ 9, [[COND_TRUE]] ], [ [[TMP5]], [[COND_FALSE]] ]
|
|
// CHECK4-NEXT: store i32 [[COND]], i32* [[DOTOMP_UB]], align 4
|
|
// CHECK4-NEXT: [[TMP6:%.*]] = load i32, i32* [[DOTOMP_LB]], align 4
|
|
// CHECK4-NEXT: store i32 [[TMP6]], i32* [[DOTOMP_IV]], align 4
|
|
// CHECK4-NEXT: br label [[OMP_INNER_FOR_COND:%.*]]
|
|
// CHECK4: omp.inner.for.cond:
|
|
// CHECK4-NEXT: [[TMP7:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK4-NEXT: [[TMP8:%.*]] = load i32, i32* [[DOTOMP_UB]], align 4, !llvm.access.group !3
|
|
// CHECK4-NEXT: [[CMP1:%.*]] = icmp sle i32 [[TMP7]], [[TMP8]]
|
|
// CHECK4-NEXT: br i1 [[CMP1]], label [[OMP_INNER_FOR_BODY:%.*]], label [[OMP_INNER_FOR_END:%.*]]
|
|
// CHECK4: omp.inner.for.body:
|
|
// CHECK4-NEXT: [[TMP9:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK4-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP9]], 1
|
|
// CHECK4-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK4-NEXT: store i32 [[ADD]], i32* [[I]], align 4, !llvm.access.group !3
|
|
// CHECK4-NEXT: br label [[OMP_BODY_CONTINUE:%.*]]
|
|
// CHECK4: omp.body.continue:
|
|
// CHECK4-NEXT: br label [[OMP_INNER_FOR_INC:%.*]]
|
|
// CHECK4: omp.inner.for.inc:
|
|
// CHECK4-NEXT: [[TMP10:%.*]] = load i32, i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK4-NEXT: [[ADD2:%.*]] = add nsw i32 [[TMP10]], 1
|
|
// CHECK4-NEXT: store i32 [[ADD2]], i32* [[DOTOMP_IV]], align 4, !llvm.access.group !3
|
|
// CHECK4-NEXT: br label [[OMP_INNER_FOR_COND]], !llvm.loop [[LOOP4:![0-9]+]]
|
|
// CHECK4: omp.inner.for.end:
|
|
// CHECK4-NEXT: br label [[OMP_LOOP_EXIT:%.*]]
|
|
// CHECK4: omp.loop.exit:
|
|
// CHECK4-NEXT: call void @__kmpc_for_static_fini(%struct.ident_t* @[[GLOB1]], i32 [[TMP3]])
|
|
// CHECK4-NEXT: [[TMP11:%.*]] = load i32, i32* [[DOTOMP_IS_LAST]], align 4
|
|
// CHECK4-NEXT: [[TMP12:%.*]] = icmp ne i32 [[TMP11]], 0
|
|
// CHECK4-NEXT: br i1 [[TMP12]], label [[DOTOMP_FINAL_THEN:%.*]], label [[DOTOMP_FINAL_DONE:%.*]]
|
|
// CHECK4: .omp.final.then:
|
|
// CHECK4-NEXT: store i32 10, i32* [[I]], align 4
|
|
// CHECK4-NEXT: br label [[DOTOMP_FINAL_DONE]]
|
|
// CHECK4: .omp.final.done:
|
|
// CHECK4-NEXT: ret void
|
|
//
|