summaryrefslogtreecommitdiffstats
path: root/lib/Driver/ToolChains/Cuda.cpp
diff options
context:
space:
mode:
authorGheorghe-Teodor Bercea <gheorghe-teod.bercea@ibm.com>2017-08-09 15:56:54 +0000
committerGheorghe-Teodor Bercea <gheorghe-teod.bercea@ibm.com>2017-08-09 15:56:54 +0000
commit7984a2104f8822c9222dc8ca3b1b30b05b5d61af (patch)
tree780d96e1655107ebd43a42a4e499c83ef0bb88c9 /lib/Driver/ToolChains/Cuda.cpp
parent0420738bf55dfd0302ca318299a19905a27f7c18 (diff)
[OpenMP] Add flag for overwriting default PTX version for OpenMP targets
Summary: This flag "--fopenmp-ptx=" enables the overwriting of the default PTX version used for GPU offloaded OpenMP target regions: "+ptx42". Reviewers: arpith-jacob, caomhin, carlo.bertolli, ABataev, Hahnfeld, jlebar, hfinkel, tstellar Reviewed By: ABataev Subscribers: rengolin, cfe-commits Differential Revision: https://reviews.llvm.org/D29660 git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@310489 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Driver/ToolChains/Cuda.cpp')
-rw-r--r--lib/Driver/ToolChains/Cuda.cpp8
1 files changed, 7 insertions, 1 deletions
diff --git a/lib/Driver/ToolChains/Cuda.cpp b/lib/Driver/ToolChains/Cuda.cpp
index 1ff41ce66d..b6a7b829f5 100644
--- a/lib/Driver/ToolChains/Cuda.cpp
+++ b/lib/Driver/ToolChains/Cuda.cpp
@@ -481,7 +481,13 @@ void CudaToolChain::addClangTargetOptions(
// than LLVM defaults to. Use PTX4.2 which is the PTX version that
// came with CUDA-7.0.
CC1Args.push_back("-target-feature");
- CC1Args.push_back("+ptx42");
+
+ if (DeviceOffloadingKind == Action::OFK_OpenMP)
+ CC1Args.push_back(
+ DriverArgs.getLastArgValue(options::OPT_fopenmp_ptx_EQ,
+ "+ptx42").data());
+ else
+ CC1Args.push_back("+ptx42");
}
void CudaToolChain::AddCudaIncludeArgs(const ArgList &DriverArgs,