Files
TheRock/compiler/amd-llvm/clang/test/CodeGenHIP/builtins-amdgcn-gfx1250-cooperative-atomics-templated.hip
T
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

92 lines
5.0 KiB
Plaintext

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --include-generated-funcs --version 5
// REQUIRES: amdgpu-registered-target
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1250 -fcuda-is-device -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1251 -fcuda-is-device -emit-llvm -o - %s | FileCheck %s
#define __device__ __attribute__((device))
typedef int v2i __attribute__((ext_vector_type(2)));
typedef int v4i __attribute__((ext_vector_type(4)));
template<unsigned AO>
__device__ void template_cooperative_atomic_store_32x4B(int* gaddr, int val) {
__builtin_amdgcn_cooperative_atomic_store_32x4B(gaddr, val, AO, "agent");
}
__device__ void test_amdgcn_cooperative_atomic_store_32x4B(int* gaddr, int val)
{
template_cooperative_atomic_store_32x4B<__ATOMIC_SEQ_CST>(gaddr, val);
}
template<unsigned AO>
__device__ int template_cooperative_atomic_load_32x4B(int* gaddr) {
return __builtin_amdgcn_cooperative_atomic_load_32x4B(gaddr, AO, "");
}
__device__ void test_amdgcn_cooperative_atomic_load_32x4B(int* addr, int *out)
{
*out = template_cooperative_atomic_load_32x4B<__ATOMIC_SEQ_CST>(addr);
}
// CHECK-LABEL: define dso_local void @_Z42test_amdgcn_cooperative_atomic_store_32x4BPii(
// CHECK-SAME: ptr noundef [[GADDR:%.*]], i32 noundef [[VAL:%.*]]) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[GADDR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// CHECK-NEXT: [[VAL_ADDR:%.*]] = alloca i32, align 4, addrspace(5)
// CHECK-NEXT: [[GADDR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[GADDR_ADDR]] to ptr
// CHECK-NEXT: [[VAL_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VAL_ADDR]] to ptr
// CHECK-NEXT: store ptr [[GADDR]], ptr [[GADDR_ADDR_ASCAST]], align 8
// CHECK-NEXT: store i32 [[VAL]], ptr [[VAL_ADDR_ASCAST]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[GADDR_ADDR_ASCAST]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[VAL_ADDR_ASCAST]], align 4
// CHECK-NEXT: call void @_Z39template_cooperative_atomic_store_32x4BILj5EEvPii(ptr noundef [[TMP0]], i32 noundef [[TMP1]]) #[[ATTR3:[0-9]+]]
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define linkonce_odr void @_Z39template_cooperative_atomic_store_32x4BILj5EEvPii(
// CHECK-SAME: ptr noundef [[GADDR:%.*]], i32 noundef [[VAL:%.*]]) #[[ATTR0]] comdat {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[GADDR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// CHECK-NEXT: [[VAL_ADDR:%.*]] = alloca i32, align 4, addrspace(5)
// CHECK-NEXT: [[GADDR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[GADDR_ADDR]] to ptr
// CHECK-NEXT: [[VAL_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[VAL_ADDR]] to ptr
// CHECK-NEXT: store ptr [[GADDR]], ptr [[GADDR_ADDR_ASCAST]], align 8
// CHECK-NEXT: store i32 [[VAL]], ptr [[VAL_ADDR_ASCAST]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[GADDR_ADDR_ASCAST]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[VAL_ADDR_ASCAST]], align 4
// CHECK-NEXT: call void @llvm.amdgcn.cooperative.atomic.store.32x4B.p0(ptr [[TMP0]], i32 [[TMP1]], i32 5, metadata [[META4:![0-9]+]])
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define dso_local void @_Z41test_amdgcn_cooperative_atomic_load_32x4BPiS_(
// CHECK-SAME: ptr noundef [[ADDR:%.*]], ptr noundef [[OUT:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[ADDR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// CHECK-NEXT: [[OUT_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// CHECK-NEXT: [[ADDR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[ADDR_ADDR]] to ptr
// CHECK-NEXT: [[OUT_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[OUT_ADDR]] to ptr
// CHECK-NEXT: store ptr [[ADDR]], ptr [[ADDR_ADDR_ASCAST]], align 8
// CHECK-NEXT: store ptr [[OUT]], ptr [[OUT_ADDR_ASCAST]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[ADDR_ADDR_ASCAST]], align 8
// CHECK-NEXT: [[CALL:%.*]] = call noundef i32 @_Z38template_cooperative_atomic_load_32x4BILj5EEiPi(ptr noundef [[TMP0]]) #[[ATTR3]]
// CHECK-NEXT: [[TMP1:%.*]] = load ptr, ptr [[OUT_ADDR_ASCAST]], align 8
// CHECK-NEXT: store i32 [[CALL]], ptr [[TMP1]], align 4
// CHECK-NEXT: ret void
//
//
// CHECK-LABEL: define linkonce_odr noundef i32 @_Z38template_cooperative_atomic_load_32x4BILj5EEiPi(
// CHECK-SAME: ptr noundef [[GADDR:%.*]]) #[[ATTR0]] comdat {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: [[GADDR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
// CHECK-NEXT: [[GADDR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[GADDR_ADDR]] to ptr
// CHECK-NEXT: store ptr [[GADDR]], ptr [[GADDR_ADDR_ASCAST]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[GADDR_ADDR_ASCAST]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = call i32 @llvm.amdgcn.cooperative.atomic.load.32x4B.p0(ptr [[TMP0]], i32 5, metadata [[META5:![0-9]+]])
// CHECK-NEXT: ret i32 [[TMP1]]
//
//.
// CHECK: [[META4]] = !{!"agent"}
// CHECK: [[META5]] = !{!""}
//.