| // Test target codegen - host bc file has to be created first. |
| // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-linux-gnu -fopenmp-targets=amdgpu-amd-amdhsa -emit-llvm-bc %s -o %t-x86-host.bc |
| // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple amdgpu-amd-amdhsa -fopenmp-targets=amdgpu-amd-amdhsa -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck -check-prefixes=CHECK,CHECK-AMDGPU %s |
| // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple amdgpu-amd-amdhsa -fopenmp-targets=amdgpu-amd-amdhsa -mllvm -openmp-ir-builder-use-default-max-threads=false -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck -check-prefixes=CHECK,CHECK-AMDGPU-FLAG %s |
| // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple x86_64-unknown-linux-gnu -fopenmp-targets=spirv64-intel -emit-llvm-bc %s -o %t-x86-spirv-host.bc |
| // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple spirv64-intel -fopenmp-targets=spirv64-intel -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-spirv-host.bc -o - | FileCheck -check-prefixes=CHECK,CHECK-SPIRV %s |
| // RUN: %clang_cc1 -verify -fopenmp -x c++ -triple spirv64-intel -fopenmp-targets=spirv64-intel -mllvm -openmp-ir-builder-use-default-max-threads=false -emit-llvm %s -fopenmp-is-target-device -fopenmp-host-ir-file-path %t-x86-spirv-host.bc -o - | FileCheck -check-prefixes=CHECK,CHECK-SPIRV-FLAG %s |
| // expected-no-diagnostics |
| |
| #ifndef HEADER |
| #define HEADER |
| |
| void foo(int N) { |
| #pragma omp target teams distribute parallel for simd |
| for (int i = 0; i < N; ++i) |
| ; |
| #pragma omp target teams distribute parallel for simd thread_limit(4) |
| for (int i = 0; i < N; ++i) |
| ; |
| #pragma omp target teams distribute parallel for simd ompx_attribute(__attribute__((launch_bounds(42, 84)))) |
| for (int i = 0; i < N; ++i) |
| ; |
| #pragma omp target teams distribute parallel for simd ompx_attribute(__attribute__((launch_bounds(42, 84)))) num_threads(22) |
| for (int i = 0; i < N; ++i) |
| ; |
| #pragma omp target teams distribute parallel for simd ompx_attribute(__attribute__((launch_bounds(42, 84, 86)))) num_threads(20) |
| for (int i = 0; i < N; ++i) |
| ; |
| } |
| |
| #endif |
| |
| // CHECK: define weak_odr protected {{amdgpu|spir}}_kernel void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+__Z3fooi_}}l14({{.*}}) #[[ATTR1:.+]] { |
| // CHECK: define weak_odr protected {{amdgpu|spir}}_kernel void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+__Z3fooi_}}l17({{.*}}) #[[ATTR2:.+]] { |
| // CHECK: define weak_odr protected {{amdgpu|spir}}_kernel void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+__Z3fooi_}}l20({{.*}}) #[[ATTR3:.+]] { |
| // CHECK: define weak_odr protected {{amdgpu|spir}}_kernel void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+__Z3fooi_}}l23({{.*}}) #[[ATTR4:.+]] { |
| // CHECK: define weak_odr protected {{amdgpu|spir}}_kernel void @{{__omp_offloading_[0-9a-z]+_[0-9a-z]+__Z3fooi_}}l26({{.*}}) #[[ATTR5:.+]] { |
| |
| // CHECK-AMDGPU: attributes #[[ATTR1]] = { {{.*}} "amdgpu-flat-work-group-size"="1,256" {{.*}} } |
| // CHECK-AMDGPU: attributes #[[ATTR2]] = { {{.*}} "amdgpu-flat-work-group-size"="1,4" {{.*}} } |
| // CHECK-AMDGPU: attributes #[[ATTR3]] = { {{.*}} "amdgpu-flat-work-group-size"="1,42" {{.*}} } |
| // CHECK-AMDGPU: attributes #[[ATTR4]] = { {{.*}} "amdgpu-flat-work-group-size"="1,22" {{.*}} } |
| // CHECK-AMDGPU: attributes #[[ATTR5]] = { {{.*}} "amdgpu-flat-work-group-size"="1,20" "amdgpu-max-num-workgroups"="86,1,1" {{.*}} } |
| |
| // CHECK-SPIRV: attributes #[[ATTR1]] = { {{.*}} "omp_target_thread_limit"="256" {{.*}} } |
| // CHECK-SPIRV: attributes #[[ATTR2]] = { {{.*}} "omp_target_thread_limit"="4" {{.*}} } |
| // CHECK-SPIRV: attributes #[[ATTR3]] = { {{.*}} "omp_target_num_teams"="84" "omp_target_thread_limit"="42" {{.*}} } |
| // CHECK-SPIRV: attributes #[[ATTR4]] = { {{.*}} "omp_target_num_teams"="84" "omp_target_thread_limit"="22" {{.*}} } |
| // CHECK-SPIRV: attributes #[[ATTR5]] = { {{.*}} "omp_target_num_teams"="84" "omp_target_thread_limit"="20" {{.*}} } |
| |
| // CHECK-AMDGPU-FLAG: attributes #[[ATTR1]] = { |
| // CHECK-AMDGPU-FLAG-NOT: amdgpu-flat-work-group-size |
| // CHECK-AMDGPU-FLAG-NOT: omp_target_thread_limit |
| // CHECK-AMDGPU-FLAG-SAME: } |
| // CHECK-AMDGPU-FLAG: attributes #[[ATTR2]] = { {{.*}} "amdgpu-flat-work-group-size"="1,4" {{.*}} } |
| // CHECK-AMDGPU-FLAG: attributes #[[ATTR3]] = { {{.*}} "amdgpu-flat-work-group-size"="1,42" {{.*}} } |
| // CHECK-AMDGPU-FLAG: attributes #[[ATTR4]] = { {{.*}} "amdgpu-flat-work-group-size"="1,22" {{.*}} } |
| // CHECK-AMDGPU-FLAG: attributes #[[ATTR5]] = { {{.*}} "amdgpu-flat-work-group-size"="1,20" "amdgpu-max-num-workgroups"="86,1,1" {{.*}} } |
| |
| // CHECK-SPIRV-FLAG: attributes #[[ATTR1]] = { |
| // CHECK-SPIRV-FLAG-NOT: omp_target_thread_limit |
| // CHECK-SPIRV-FLAG-SAME: } |
| // CHECK-SPIRV-FLAG: attributes #[[ATTR2]] = { {{.*}} "omp_target_thread_limit"="4" {{.*}} } |
| // CHECK-SPIRV-FLAG: attributes #[[ATTR3]] = { {{.*}} "omp_target_num_teams"="84" "omp_target_thread_limit"="42" {{.*}} } |
| // CHECK-SPIRV-FLAG: attributes #[[ATTR4]] = { {{.*}} "omp_target_num_teams"="84" "omp_target_thread_limit"="22" {{.*}} } |
| // CHECK-SPIRV-FLAG: attributes #[[ATTR5]] = { {{.*}} "omp_target_num_teams"="84" "omp_target_thread_limit"="20" {{.*}} } |
