Author: Doru Bercea Date: 2023-04-20T14:40:35-04:00 New Revision: 01910787d386584ea5a3d5dc317a908423ba39ed
URL: https://github.com/llvm/llvm-project/commit/01910787d386584ea5a3d5dc317a908423ba39ed DIFF: https://github.com/llvm/llvm-project/commit/01910787d386584ea5a3d5dc317a908423ba39ed.diff LOG: Fix failure with team-wide allocated variable Review: https://reviews.llvm.org/D147572 Added: clang/test/OpenMP/target_team_variable_codegen.cpp Modified: clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp Removed: ################################################################################ diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp index 2fea9c219f358..3f231703aa651 100644 --- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp +++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp @@ -3353,7 +3353,7 @@ Address CGOpenMPRuntimeGPU::getAddressOfLocalVariable(CodeGenFunction &CGF, llvm::Type *VarTy = CGF.ConvertTypeForMem(VD->getType()); auto *GV = new llvm::GlobalVariable( CGM.getModule(), VarTy, /*isConstant=*/false, - llvm::GlobalValue::InternalLinkage, llvm::Constant::getNullValue(VarTy), + llvm::GlobalValue::InternalLinkage, llvm::PoisonValue::get(VarTy), VD->getName(), /*InsertBefore=*/nullptr, llvm::GlobalValue::NotThreadLocal, CGM.getContext().getTargetAddressSpace(AS)); diff --git a/clang/test/OpenMP/target_team_variable_codegen.cpp b/clang/test/OpenMP/target_team_variable_codegen.cpp new file mode 100644 index 0000000000000..cc82503a52d2a --- /dev/null +++ b/clang/test/OpenMP/target_team_variable_codegen.cpp @@ -0,0 +1,57 @@ +// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --check-globals --prefix-filecheck-ir-name _ --global-value-regex "llvm.compiler.used" "_[0-9a-zA-Z]+A[0-9a-zA-Z]+pi[0-9a-zA-Z]+" "_[0-9a-zA-Z]+anotherPi" --version 2 +// REQUIRES: amdgpu-registered-target + + +// Test target codegen - host bc file has to be created first. +// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm-bc %s -o %t-ppc-host-amd.bc +// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple amdgcn-amd-amdhsa -fopenmp-targets=amdgcn-amd-amdhsa -emit-llvm %s -fopenmp-target-debug -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host-amd.bc -o - | FileCheck %s --check-prefix=CHECK-AMD + +// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host-nvidia.bc +// RUN: %clang_cc1 -verify -fopenmp -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-unknown-unknown -emit-llvm %s -fopenmp-target-debug -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host-nvidia.bc -o - | FileCheck %s --check-prefix=CHECK-NVIDIA + +// expected-no-diagnostics + +#ifndef HEADER +#define HEADER + +typedef enum omp_allocator_handle_t { + omp_null_allocator = 0, + omp_default_mem_alloc = 1, + omp_large_cap_mem_alloc = 2, + omp_const_mem_alloc = 3, + omp_high_bw_mem_alloc = 4, + omp_low_lat_mem_alloc = 5, + omp_cgroup_mem_alloc = 6, + omp_pteam_mem_alloc = 7, + omp_thread_mem_alloc = 8, + KMP_ALLOCATOR_MAX_HANDLE = __UINTPTR_MAX__ +} omp_allocator_handle_t; + +//. +// CHECK-AMD: @local_a = internal addrspace(3) global [10 x i32] poison, align 4 +//. +// CHECK-NVIDIA: @local_a = internal addrspace(3) global [10 x i32] poison, align 4 +//. +int main() +{ + int N = 10000; + int *a = new int[N]; +#pragma omp target data map(tofrom:a[:N]) + { +#pragma omp target teams distribute parallel for + for(int i = 0; i < N; i++) + { + int local_a[10]; +#pragma omp allocate(local_a) allocator(omp_pteam_mem_alloc) + for(int j = 0; j < 10; j++) + local_a[j] = a[(i + j) % N]; + a[i] = local_a[0]; + } + } + return a[17]; +} + +#endif +//// NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line: +// CHECK-AMD: {{.*}} +// CHECK-NVIDIA: {{.*}} _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
