diff options
| author | Alexey Bataev <a.bataev@hotmail.com> | 2019-05-21 15:11:58 +0000 |
|---|---|---|
| committer | Alexey Bataev <a.bataev@hotmail.com> | 2019-05-21 15:11:58 +0000 |
| commit | 8c5555c39a7a2f0cbb4720cacba32c53d601f785 (patch) | |
| tree | 9005845f0d57135a54e10f435283381041bdf86a /clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp | |
| parent | 78c3f58122f4edcf8e707b2fb8ab1c9ae2054b03 (diff) | |
| download | bcm5719-llvm-8c5555c39a7a2f0cbb4720cacba32c53d601f785.tar.gz bcm5719-llvm-8c5555c39a7a2f0cbb4720cacba32c53d601f785.zip | |
[OPENMP][NVPTX]Mark more functions as always_inline for better
performance.
Internally generated functions must be marked as always_inlines in most
cases. Patch marks some extra reduction function + outlined parallel
functions as always_inline for better performance, but only if the
optimization is requested.
llvm-svn: 361269
Diffstat (limited to 'clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp')
| -rw-r--r-- | clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp b/clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp index fc90d34da36..1aac4819841 100644 --- a/clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp +++ b/clang/test/OpenMP/nvptx_target_parallel_num_threads_codegen.cpp @@ -1,9 +1,9 @@ // Test target codegen - host bc file has to be created first. // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -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-version=45 -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-version=45 -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 - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-64 // RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -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-version=45 -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-version=45 -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-version=45 -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 - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 +// RUN: %clang_cc1 -verify -fopenmp -fopenmp-version=45 -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 - -disable-llvm-optzns | FileCheck %s --check-prefix CHECK --check-prefix CHECK-32 // expected-no-diagnostics #ifndef HEADER #define HEADER |
