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
113 lines
7.7 KiB
C++
113 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 -fopenmp -x c++ -std=c++11 -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 -triple amdgcn-amd-amdhsa -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s
|
|
// expected-no-diagnostics
|
|
|
|
void compute_reduced_sum(int n, int &x) {
|
|
#pragma omp target teams distribute parallel for reduction(+ : x)
|
|
for (int i = 0; i < n; ++i)
|
|
x += i;
|
|
}
|
|
|
|
int main()
|
|
{
|
|
int n = 1000;
|
|
int sum = 0;
|
|
compute_reduced_sum(n, sum);
|
|
}
|
|
|
|
// CHECK-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z19compute_reduced_sumiRi_l7
|
|
// CHECK-SAME: (i64 noundef [[N:%.*]], ptr noundef nonnull align 4 dereferenceable(4) [[X:%.*]], ptr noundef [[TMP0:%.*]], ptr noundef [[TMP1:%.*]], ptr noalias noundef [[DYN_PTR:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[N_ADDR:%.*]] = alloca i64, align 8, addrspace(5)
|
|
// CHECK-NEXT: [[X_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
|
|
// CHECK-NEXT: [[DOTADDR:%.*]] = alloca ptr, align 8, addrspace(5)
|
|
// CHECK-NEXT: [[DOTADDR1:%.*]] = alloca ptr, align 8, addrspace(5)
|
|
// CHECK-NEXT: [[DYN_PTR_ADDR:%.*]] = alloca ptr, align 8, addrspace(5)
|
|
// CHECK-NEXT: [[TMP:%.*]] = alloca ptr, align 8, addrspace(5)
|
|
// CHECK-NEXT: [[I:%.*]] = alloca i32, align 4, addrspace(5)
|
|
// CHECK-NEXT: [[DOTCAPTURE_EXPR_:%.*]] = alloca i32, align 4, addrspace(5)
|
|
// CHECK-NEXT: [[DOTCAPTURE_EXPR_2:%.*]] = alloca i32, align 4, addrspace(5)
|
|
// CHECK-NEXT: [[DOTOMP_LB:%.*]] = alloca i32, align 4, addrspace(5)
|
|
// CHECK-NEXT: [[DOTOMP_UB:%.*]] = alloca i32, align 4, addrspace(5)
|
|
// CHECK-NEXT: [[DOTOMP_IV:%.*]] = alloca i32, align 4, addrspace(5)
|
|
// CHECK-NEXT: [[N_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[N_ADDR]] to ptr
|
|
// CHECK-NEXT: [[X_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[X_ADDR]] to ptr
|
|
// CHECK-NEXT: [[DOTADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTADDR]] to ptr
|
|
// CHECK-NEXT: [[DOTADDR1_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTADDR1]] to ptr
|
|
// CHECK-NEXT: [[DYN_PTR_ADDR_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DYN_PTR_ADDR]] to ptr
|
|
// CHECK-NEXT: [[TMP_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[TMP]] to ptr
|
|
// CHECK-NEXT: [[I_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[I]] to ptr
|
|
// CHECK-NEXT: [[DOTCAPTURE_EXPR__ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_]] to ptr
|
|
// CHECK-NEXT: [[DOTCAPTURE_EXPR_2_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTCAPTURE_EXPR_2]] to ptr
|
|
// CHECK-NEXT: [[DOTOMP_LB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_LB]] to ptr
|
|
// CHECK-NEXT: [[DOTOMP_UB_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_UB]] to ptr
|
|
// CHECK-NEXT: [[DOTOMP_IV_ASCAST:%.*]] = addrspacecast ptr addrspace(5) [[DOTOMP_IV]] to ptr
|
|
// CHECK-NEXT: store i64 [[N]], ptr [[N_ADDR_ASCAST]], align 8
|
|
// CHECK-NEXT: store ptr [[X]], ptr [[X_ADDR_ASCAST]], align 8
|
|
// CHECK-NEXT: store ptr [[TMP0]], ptr [[DOTADDR_ASCAST]], align 8
|
|
// CHECK-NEXT: store ptr [[TMP1]], ptr [[DOTADDR1_ASCAST]], align 8
|
|
// CHECK-NEXT: store ptr [[DYN_PTR]], ptr [[DYN_PTR_ADDR_ASCAST]], align 8
|
|
// CHECK-NEXT: [[TMP2:%.*]] = load ptr, ptr [[X_ADDR_ASCAST]], align 8, !nonnull [[META5:![0-9]+]], !align [[META6:![0-9]+]]
|
|
// CHECK-NEXT: store ptr [[TMP2]], ptr [[TMP_ASCAST]], align 8
|
|
// CHECK-NEXT: call void @__kmpc_specialized_kernel_init()
|
|
// CHECK-NEXT: [[TMP3:%.*]] = alloca i32, align 4, addrspace(5)
|
|
// CHECK-NEXT: store i32 0, ptr addrspace(5) [[TMP3]], align 4
|
|
// CHECK-NEXT: store i32 0, ptr [[I_ASCAST]], align 4
|
|
// CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr [[N_ADDR_ASCAST]], align 4
|
|
// CHECK-NEXT: store i32 [[TMP4]], ptr [[DOTCAPTURE_EXPR__ASCAST]], align 4
|
|
// CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR__ASCAST]], align 4
|
|
// CHECK-NEXT: [[SUB:%.*]] = sub nsw i32 [[TMP5]], 0
|
|
// CHECK-NEXT: [[DIV:%.*]] = sdiv i32 [[SUB]], 1
|
|
// CHECK-NEXT: [[SUB3:%.*]] = sub nsw i32 [[DIV]], 1
|
|
// CHECK-NEXT: store i32 [[SUB3]], ptr [[DOTCAPTURE_EXPR_2_ASCAST]], align 4
|
|
// CHECK-NEXT: store i32 0, ptr [[I_ASCAST]], align 4
|
|
// CHECK-NEXT: store i32 0, ptr [[DOTOMP_LB_ASCAST]], align 4
|
|
// CHECK-NEXT: [[TMP6:%.*]] = load i32, ptr [[DOTCAPTURE_EXPR_2_ASCAST]], align 4
|
|
// CHECK-NEXT: store i32 [[TMP6]], ptr [[DOTOMP_UB_ASCAST]], align 4
|
|
// CHECK-NEXT: [[TMP7:%.*]] = load i32, ptr [[DOTOMP_LB_ASCAST]], align 4
|
|
// CHECK-NEXT: store i32 [[TMP7]], ptr [[DOTOMP_IV_ASCAST]], align 4
|
|
// CHECK-NEXT: [[TMP8:%.*]] = call i32 @__kmpc_get_hardware_thread_id_in_block()
|
|
// CHECK-NEXT: [[NVPTX_NUM_THREADS:%.*]] = call i32 @__kmpc_get_hardware_num_threads_in_block()
|
|
// CHECK-NEXT: [[GPU_BLOCK_ID:%.*]] = call i32 @llvm.amdgcn.workgroup.id.x()
|
|
// CHECK-NEXT: [[TMP9:%.*]] = mul i32 [[GPU_BLOCK_ID]], [[NVPTX_NUM_THREADS]]
|
|
// CHECK-NEXT: [[TMP10:%.*]] = add i32 [[TMP9]], [[TMP8]]
|
|
// CHECK-NEXT: [[TMP11:%.*]] = mul i32 [[TMP10]], 1
|
|
// CHECK-NEXT: [[TMP12:%.*]] = load i32, ptr [[DOTOMP_IV_ASCAST]], align 4
|
|
// CHECK-NEXT: [[TMP13:%.*]] = add i32 [[TMP11]], [[TMP12]]
|
|
// CHECK-NEXT: [[TMP14:%.*]] = call i32 @__kmpc_get_hardware_num_blocks()
|
|
// CHECK-NEXT: [[TMP15:%.*]] = zext i32 [[TMP13]] to i64
|
|
// CHECK-NEXT: store i32 [[TMP13]], ptr [[DOTOMP_IV_ASCAST]], align 4
|
|
// CHECK-NEXT: br label [[FOR_COND:%.*]]
|
|
// CHECK: for.cond:
|
|
// CHECK-NEXT: [[TMP16:%.*]] = load i32, ptr [[DOTOMP_IV_ASCAST]], align 4
|
|
// CHECK-NEXT: [[TMP17:%.*]] = load i32, ptr [[DOTOMP_UB_ASCAST]], align 4
|
|
// CHECK-NEXT: [[CMP:%.*]] = icmp sle i32 [[TMP16]], [[TMP17]]
|
|
// CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY:%.*]], label [[FOR_END:%.*]]
|
|
// CHECK: for.body:
|
|
// CHECK-NEXT: [[TMP18:%.*]] = load i32, ptr [[DOTOMP_IV_ASCAST]], align 4
|
|
// CHECK-NEXT: [[MUL:%.*]] = mul nsw i32 [[TMP18]], 1
|
|
// CHECK-NEXT: [[ADD:%.*]] = add nsw i32 0, [[MUL]]
|
|
// CHECK-NEXT: store i32 [[ADD]], ptr [[I_ASCAST]], align 4
|
|
// CHECK-NEXT: [[TMP19:%.*]] = load i32, ptr [[I_ASCAST]], align 4
|
|
// CHECK-NEXT: [[TMP20:%.*]] = load i32, ptr addrspace(5) [[TMP3]], align 4
|
|
// CHECK-NEXT: [[TMP21:%.*]] = add i32 [[TMP20]], [[TMP19]]
|
|
// CHECK-NEXT: store i32 [[TMP21]], ptr addrspace(5) [[TMP3]], align 4
|
|
// CHECK-NEXT: br label [[FOR_INC:%.*]]
|
|
// CHECK: for.inc:
|
|
// CHECK-NEXT: [[NVPTX_NUM_THREADS4:%.*]] = call i32 @__kmpc_get_hardware_num_threads_in_block()
|
|
// CHECK-NEXT: [[TMP22:%.*]] = mul i32 [[NVPTX_NUM_THREADS4]], [[TMP14]]
|
|
// CHECK-NEXT: [[TMP23:%.*]] = mul i32 [[TMP22]], 1
|
|
// CHECK-NEXT: [[TMP24:%.*]] = load i32, ptr [[DOTOMP_IV_ASCAST]], align 4
|
|
// CHECK-NEXT: [[TMP25:%.*]] = add i32 [[TMP23]], [[TMP24]]
|
|
// CHECK-NEXT: store i32 [[TMP25]], ptr [[DOTOMP_IV_ASCAST]], align 4
|
|
// CHECK-NEXT: br label [[FOR_COND]], !llvm.loop [[LOOP7:![0-9]+]]
|
|
// CHECK: for.end:
|
|
// CHECK-NEXT: [[TMP26:%.*]] = load ptr, ptr [[DOTADDR_ASCAST]], align 8
|
|
// CHECK-NEXT: [[TMP27:%.*]] = load ptr, ptr [[DOTADDR1_ASCAST]], align 8
|
|
// CHECK-NEXT: [[TMP28:%.*]] = load ptr, ptr [[TMP_ASCAST]], align 8, !nonnull [[META5]], !align [[META6]]
|
|
// CHECK-NEXT: [[TMP29:%.*]] = load i32, ptr addrspace(5) [[TMP3]], align 4
|
|
// CHECK-NEXT: call void @__kmpc_xteamr_i_16x64(i32 [[TMP29]], ptr [[TMP28]], ptr [[TMP26]], ptr [[TMP27]], ptr @__kmpc_rfun_sum_i, ptr @__kmpc_rfun_sum_lds_i, i32 0, i64 [[TMP15]], i32 [[TMP14]], i32 1)
|
|
// CHECK-NEXT: ret void
|
|
//
|