diff options
| author | Nicolai Haehnle <nhaehnle@gmail.com> | 2016-05-02 17:37:01 +0000 |
|---|---|---|
| committer | Nicolai Haehnle <nhaehnle@gmail.com> | 2016-05-02 17:37:01 +0000 |
| commit | 119d3d80cbb53ff601f5bf56affb464d3b5f55ea (patch) | |
| tree | 683002e241fa797689f012ac51e8a443080babcd /llvm/lib/Target/AMDGPU/SIInsertWaits.cpp | |
| parent | e951a1d739d6cc7479451d4465f2cf74b41ae374 (diff) | |
| download | bcm5719-llvm-119d3d80cbb53ff601f5bf56affb464d3b5f55ea.tar.gz bcm5719-llvm-119d3d80cbb53ff601f5bf56affb464d3b5f55ea.zip | |
AMDGPU: llvm.SI.fs.constant is a source of divergence
Summary:
This intrinsic is used to get flat-shaded fragment shader inputs. Those are
uniform across a primitive, but a fragment shader wave may process pixels from
multiple primitives (as indicated by the prim_mask), and so that's where
divergence can arise.
Reviewers: arsenm, tstellarAMD
Subscribers: arsenm, llvm-commits
Differential Revision: http://reviews.llvm.org/D19747
llvm-svn: 268259
Diffstat (limited to 'llvm/lib/Target/AMDGPU/SIInsertWaits.cpp')
0 files changed, 0 insertions, 0 deletions
