diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2019-02-12 23:30:11 +0000 |
|---|---|---|
| committer | Matt Arsenault <Matthew.Arsenault@amd.com> | 2019-02-12 23:30:11 +0000 |
| commit | d24296e282bffe2702f5a795bb4f9ef4f581cb69 (patch) | |
| tree | 5b0e2148b0cd7cd501d8b716ce1eb1db1d93d339 /llvm/lib/Target | |
| parent | 749dc51e452d1eaed82b0418c9acc54c3e5e5bbf (diff) | |
| download | bcm5719-llvm-d24296e282bffe2702f5a795bb4f9ef4f581cb69.tar.gz bcm5719-llvm-d24296e282bffe2702f5a795bb4f9ef4f581cb69.zip | |
AMDGPU: Ignore CodeObjectV3 when inlining
This was inhibiting inlining of library functions when clang was
invoking the inliner directly. This is covering a bit of a mess with
subtarget feature handling, and this shouldn't be a subtarget
feature. The behavior is different depending on whether you are using
a -mattr flag in clang, or llc, opt.
llvm-svn: 353899
Diffstat (limited to 'llvm/lib/Target')
| -rw-r--r-- | llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h index 5965072f81e..e5840062cb8 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h +++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.h @@ -84,6 +84,7 @@ class GCNTTIImpl final : public BasicTTIImplBase<GCNTTIImpl> { AMDGPU::FeatureSGPRInitBug, AMDGPU::FeatureXNACK, AMDGPU::FeatureTrapHandler, + AMDGPU::FeatureCodeObjectV3, // Perf-tuning features AMDGPU::FeatureFastFMAF32, |
