derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
70 lines
2.3 KiB
C++
70 lines
2.3 KiB
C++
// REQUIRES: amdgpu-registered-target
|
|
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -DCHECK_HINTS -triple x86_64-unknown-unknown -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm-bc %s -o %t-ppc-host.bc
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -DCHECK_HINTS -triple amdgcn-amd-amdhsa -fopenmp-targets=amdgcn-amd-amdhsa -target-cpu gfx90a -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK-HINTS
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -DCHECK_FLAG_UNSAFE -triple x86_64-unknown-unknown -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm-bc %s -o %t-ppc-host.bc
|
|
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -DCHECK_FLAG_UNSAFE -munsafe-fp-atomics -triple amdgcn-amd-amdhsa -fopenmp-targets=amdgcn-amd-amdhsa -target-cpu gfx90a -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK-FLAG-UNSAFE
|
|
|
|
// expected-no-diagnostics
|
|
#ifndef HEADER
|
|
#define HEADER
|
|
|
|
#define N 1000
|
|
|
|
#define amd_fast_fp_atomics 1<<19
|
|
#define amd_safe_fp_atomics 1<<20
|
|
|
|
#pragma omp requires unified_shared_memory
|
|
|
|
#if defined CHECK_HINTS
|
|
|
|
double test_amdgcn_target_atomic_hints() {
|
|
// CHECK-HINTS-LABEL: define {{.*}} @{{.*}}test_amdgcn_target_atomic_hints
|
|
|
|
double a = 0.0;
|
|
double b = 0.0;
|
|
|
|
#pragma omp target teams distribute parallel for map(tofrom:a,b)
|
|
for (int i = 0; i < N; i++) {
|
|
// CHECK-HINTS: = atomicrmw fadd
|
|
#pragma omp atomic hint(amd_fast_fp_atomics)
|
|
a+=(double)i;
|
|
|
|
// CHECK-HINTS: {{.*}} = atomicrmw
|
|
#pragma omp atomic hint(amd_safe_fp_atomics)
|
|
b+=(double)i;
|
|
}
|
|
// CHECK-HINTS: ret void
|
|
return a+b;
|
|
}
|
|
#endif // CHECK_HINTS
|
|
|
|
#if defined CHECK_FLAG_UNSAFE
|
|
|
|
double test_amdgcn_target_atomic_unsafe_opt() {
|
|
// CHECK-FLAG-UNSAFE-LABEL: define {{.*}} @{{.*}}test_amdgcn_target_atomic_unsafe_opt
|
|
double a = 0.0;
|
|
double b = 0.0;
|
|
double c = 0.0;
|
|
|
|
#pragma omp target teams distribute parallel for map(tofrom:a,b,c)
|
|
for (int i = 0; i < N; i++) {
|
|
// CHECK-FLAG-UNSAFE: = atomicrmw fadd
|
|
#pragma omp atomic
|
|
a+=(double)i;
|
|
|
|
// CHECK-FLAG-UNSAFE: = atomicrmw fadd
|
|
#pragma omp atomic hint(amd_fast_fp_atomics)
|
|
b+=(double)i;
|
|
|
|
// CHECK-FLAG-UNSAFE: {{.*}} = atomicrmw
|
|
#pragma omp atomic hint(amd_safe_fp_atomics)
|
|
c+=(double)i;
|
|
}
|
|
|
|
return a+b+c;
|
|
}
|
|
#endif // CHECK_FLAG_UNSAFE
|
|
|
|
#endif // HEADER
|