diff options
| author | Justin Lebar <jlebar@google.com> | 2016-05-23 20:19:56 +0000 |
|---|---|---|
| committer | Justin Lebar <jlebar@google.com> | 2016-05-23 20:19:56 +0000 |
| commit | 445e59e90c1afb49c4f09fe8fcc1c85318967a2b (patch) | |
| tree | a544e4d7b179118db9fb427271158ffc37c3d008 /lib/Frontend/CompilerInvocation.cpp | |
| parent | cfc5968efb264f6cd7b89cb4778300fc09043478 (diff) | |
| download | clang-445e59e90c1afb49c4f09fe8fcc1c85318967a2b.tar.gz | |
[CUDA] Add -fcuda-approx-transcendentals flag.
Summary:
This lets us emit e.g. sin.approx.f32. See
http://docs.nvidia.com/cuda/parallel-thread-execution/#floating-point-instructions-sin
Reviewers: rnk
Subscribers: tra, cfe-commits
Differential Revision: http://reviews.llvm.org/D20493
git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@270484 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Frontend/CompilerInvocation.cpp')
| -rw-r--r-- | lib/Frontend/CompilerInvocation.cpp | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/lib/Frontend/CompilerInvocation.cpp b/lib/Frontend/CompilerInvocation.cpp index c5f839e673..852801ab24 100644 --- a/lib/Frontend/CompilerInvocation.cpp +++ b/lib/Frontend/CompilerInvocation.cpp @@ -1616,6 +1616,9 @@ static void ParseLangArgs(LangOptions &Opts, ArgList &Args, InputKind IK, if (Opts.CUDAIsDevice && Args.hasArg(OPT_fcuda_flush_denormals_to_zero)) Opts.CUDADeviceFlushDenormalsToZero = 1; + if (Opts.CUDAIsDevice && Args.hasArg(OPT_fcuda_approx_transcendentals)) + Opts.CUDADeviceApproxTranscendentals = 1; + if (Opts.ObjC1) { if (Arg *arg = Args.getLastArg(OPT_fobjc_runtime_EQ)) { StringRef value = arg->getValue(); |