Files
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

62 lines
3.5 KiB
C++

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 5
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple amdgcn-amd-amdhsa -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm %s -fopenmp-is-target-device -o - | FileCheck -check-prefix=DEFAULT %s
// RUN: %clang_cc1 -fopenmp -x c++ -std=c++11 -triple amdgcn-amd-amdhsa -fopenmp-targets=amdgcn-amd-amdhsa -munsafe-fp-atomics -emit-llvm %s -fopenmp-is-target-device -o - | FileCheck -check-prefix=UNSAFE-FP-ATOMICS %s
#pragma omp declare target
float fv, fx;
double dv, dx;
// DEFAULT-LABEL: define hidden void @_Z15atomic_fadd_f32v(
// DEFAULT-SAME: ) #[[ATTR0:[0-9]+]] {
// DEFAULT-NEXT: [[ENTRY:.*:]]
// DEFAULT-NEXT: [[TMP0:%.*]] = load float, ptr addrspacecast (ptr addrspace(1) @fv to ptr), align 4
// DEFAULT-NEXT: [[TMP1:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @fx to ptr), float [[TMP0]] monotonic, align 4, !amdgpu.no.fine.grained.memory [[META5:![0-9]+]], !amdgpu.no.remote.memory [[META5]]
// DEFAULT-NEXT: [[ADD:%.*]] = fadd float [[TMP1]], [[TMP0]]
// DEFAULT-NEXT: store float [[ADD]], ptr addrspacecast (ptr addrspace(1) @fv to ptr), align 4
// DEFAULT-NEXT: ret void
//
// UNSAFE-FP-ATOMICS-LABEL: define hidden void @_Z15atomic_fadd_f32v(
// UNSAFE-FP-ATOMICS-SAME: ) #[[ATTR0:[0-9]+]] {
// UNSAFE-FP-ATOMICS-NEXT: [[ENTRY:.*:]]
// UNSAFE-FP-ATOMICS-NEXT: [[TMP0:%.*]] = load float, ptr addrspacecast (ptr addrspace(1) @fv to ptr), align 4
// UNSAFE-FP-ATOMICS-NEXT: [[TMP1:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @fx to ptr), float [[TMP0]] monotonic, align 4, !amdgpu.no.fine.grained.memory [[META5:![0-9]+]], !amdgpu.no.remote.memory [[META5]], !amdgpu.ignore.denormal.mode [[META5]]
// UNSAFE-FP-ATOMICS-NEXT: [[ADD:%.*]] = fadd float [[TMP1]], [[TMP0]]
// UNSAFE-FP-ATOMICS-NEXT: store float [[ADD]], ptr addrspacecast (ptr addrspace(1) @fv to ptr), align 4
// UNSAFE-FP-ATOMICS-NEXT: ret void
//
void atomic_fadd_f32() {
#pragma omp atomic capture
fv = fx = fx + fv;
}
// DEFAULT-LABEL: define hidden void @_Z15atomic_fadd_f64v(
// DEFAULT-SAME: ) #[[ATTR0]] {
// DEFAULT-NEXT: [[ENTRY:.*:]]
// DEFAULT-NEXT: [[TMP0:%.*]] = load double, ptr addrspacecast (ptr addrspace(1) @dv to ptr), align 8
// DEFAULT-NEXT: [[TMP1:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @dx to ptr), double [[TMP0]] monotonic, align 8, !amdgpu.no.fine.grained.memory [[META5]], !amdgpu.no.remote.memory [[META5]]
// DEFAULT-NEXT: [[ADD:%.*]] = fadd double [[TMP1]], [[TMP0]]
// DEFAULT-NEXT: store double [[ADD]], ptr addrspacecast (ptr addrspace(1) @dv to ptr), align 8
// DEFAULT-NEXT: ret void
//
// UNSAFE-FP-ATOMICS-LABEL: define hidden void @_Z15atomic_fadd_f64v(
// UNSAFE-FP-ATOMICS-SAME: ) #[[ATTR0]] {
// UNSAFE-FP-ATOMICS-NEXT: [[ENTRY:.*:]]
// UNSAFE-FP-ATOMICS-NEXT: [[TMP0:%.*]] = load double, ptr addrspacecast (ptr addrspace(1) @dv to ptr), align 8
// UNSAFE-FP-ATOMICS-NEXT: [[TMP1:%.*]] = atomicrmw fadd ptr addrspacecast (ptr addrspace(1) @dx to ptr), double [[TMP0]] monotonic, align 8, !amdgpu.no.fine.grained.memory [[META5]], !amdgpu.no.remote.memory [[META5]]
// UNSAFE-FP-ATOMICS-NEXT: [[ADD:%.*]] = fadd double [[TMP1]], [[TMP0]]
// UNSAFE-FP-ATOMICS-NEXT: store double [[ADD]], ptr addrspacecast (ptr addrspace(1) @dv to ptr), align 8
// UNSAFE-FP-ATOMICS-NEXT: ret void
//
void atomic_fadd_f64() {
#pragma omp atomic capture
dv = dx = dx + dv;
}
#pragma omp end declare target
//.
// DEFAULT: [[META5]] = !{}
//.
// UNSAFE-FP-ATOMICS: [[META5]] = !{}
//.