160ff83765
Provides AMDGCN and NVPTX specific specialization of getGPUWarpSize, getGPUThreadID, and getGPUNumThreads methods. Adds tests for AMDGCN codegen for these methods in generic and simd modes. Also changes the precondition in InitTempAlloca to be slightly more permissive. Useful for AMDGCN OpenMP codegen where allocas are created with a cast to an address space. Reviewed By: ABataev Differential Revision: https://reviews.llvm.org/D84260
25 lines
904 B
C++
25 lines
904 B
C++
// REQUIRES: amdgpu-registered-target
|
|
|
|
// 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
|
|
|
|
#define N 100
|
|
|
|
int test_amdgcn_target_temp_alloca() {
|
|
// CHECK-LABEL: test_amdgcn_target_temp_alloca
|
|
|
|
int arr[N];
|
|
|
|
// CHECK: [[VAR_ADDR:%.+]] = alloca [100 x i32]*, align 8, addrspace(5)
|
|
// CHECK-NEXT: [[VAR_ADDR_CAST:%.+]] = addrspacecast [100 x i32]* addrspace(5)* [[VAR_ADDR]] to [100 x i32]**
|
|
// CHECK: store [100 x i32]* [[VAR:%.+]], [100 x i32]** [[VAR_ADDR_CAST]], align 8
|
|
|
|
#pragma omp target
|
|
for (int i = 0; i < N; i++) {
|
|
arr[i] = 1;
|
|
}
|
|
|
|
return arr[0];
|
|
}
|