Changeset View
Changeset View
Standalone View
Standalone View
clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
// Test target codegen - host bc file has to be created first. | // Test target codegen - host bc file has to be created first. | ||||
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc | // RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -x c++ -triple powerpc64le-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm-bc %s -o %t-ppc-host.bc | ||||
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 | // RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -x c++ -triple nvptx64-unknown-unknown -fopenmp-targets=nvptx64-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-ppc-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 | ||||
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc | // RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -x c++ -triple i386-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm-bc %s -o %t-x86-host.bc | ||||
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 | // RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 | ||||
// RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 | // RUN: %clang_cc1 -verify -fopenmp -fopenmp-cuda-mode -fexceptions -fcxx-exceptions -x c++ -triple nvptx-unknown-unknown -fopenmp-targets=nvptx-nvidia-cuda -emit-llvm %s -fopenmp-is-device -fopenmp-host-ir-file-path %t-x86-host.bc -o - | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 | ||||
// expected-no-diagnostics | // expected-no-diagnostics | ||||
#ifndef HEADER | #ifndef HEADER | ||||
#define HEADER | #define HEADER | ||||
// Check for the data transfer medium in shared memory to transfer the reduction list to the first warp. | // Check for the data transfer medium in shared memory to transfer the reduction list to the first warp. | ||||
// CHECK-DAG: [[TRANSFER_STORAGE:@.+]] = common addrspace([[SHARED_ADDRSPACE:[0-9]+]]) global [32 x i32] | // CHECK-DAG: [[TRANSFER_STORAGE:@.+]] = weak addrspace([[SHARED_ADDRSPACE:[0-9]+]]) global [32 x i32] | ||||
// Check that the execution mode of all 3 target regions is set to Spmd Mode. | // Check that the execution mode of all 3 target regions is set to Spmd Mode. | ||||
// CHECK-DAG: {{@__omp_offloading_.+l27}}_exec_mode = weak constant i8 0 | // CHECK-DAG: {{@__omp_offloading_.+l27}}_exec_mode = weak constant i8 0 | ||||
// CHECK-DAG: {{@__omp_offloading_.+l32}}_exec_mode = weak constant i8 0 | // CHECK-DAG: {{@__omp_offloading_.+l32}}_exec_mode = weak constant i8 0 | ||||
// CHECK-DAG: {{@__omp_offloading_.+l38}}_exec_mode = weak constant i8 0 | // CHECK-DAG: {{@__omp_offloading_.+l38}}_exec_mode = weak constant i8 0 | ||||
template<typename tx> | template<typename tx> | ||||
tx ftemplate(int n) { | tx ftemplate(int n) { | ||||
▲ Show 20 Lines • Show All 787 Lines • Show Last 20 Lines |