From 8061acd501f1cb6c00a886f4ee5cb9adc6cda39a Mon Sep 17 00:00:00 2001 From: Alexey Bataev Date: Wed, 20 Feb 2019 16:36:22 +0000 Subject: [OPENMP][NVPTX]Use faster teams reduction algorithm. A faster way to reduce the values in teams reductions was found, the codegen is updated to use this faster algorithm and new runtime functions. llvm-svn: 354479 --- clang/test/Driver/openmp-offload-gpu.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'clang/test/Driver/openmp-offload-gpu.c') diff --git a/clang/test/Driver/openmp-offload-gpu.c b/clang/test/Driver/openmp-offload-gpu.c index dfdc79b5f70..7a4dd95e541 100644 --- a/clang/test/Driver/openmp-offload-gpu.c +++ b/clang/test/Driver/openmp-offload-gpu.c @@ -273,3 +273,8 @@ // RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fopenmp-cuda-force-full-runtime -fno-openmp-cuda-force-full-runtime 2>&1 \ // RUN: | FileCheck -check-prefix=NO_FULL_RUNTIME %s // NO_FULL_RUNTIME-NOT: "-{{fno-|f}}openmp-cuda-force-full-runtime" + +// RUN: %clang -### -no-canonical-prefixes -fopenmp=libomp -fopenmp-targets=nvptx64-nvidia-cuda -Xopenmp-target -march=sm_60 %s -fopenmp-cuda-teams-reduction-recs-num=2048 2>&1 \ +// RUN: | FileCheck -check-prefix=CUDA_RED_RECS %s +// CUDA_RED_RECS: clang{{.*}}"-cc1"{{.*}}"-triple" "nvptx64-nvidia-cuda" +// CUDA_RED_RECS-SAME: "-fopenmp-cuda-teams-reduction-recs-num=2048" -- cgit v1.2.3