projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 77382be) | patch
AMDGPU/SI: Remove zero_extend patterns for i16 ops selected to 32-bit insts
authorTom Stellard <thomas.stellard@amd.com>
Fri, 18 Nov 2016 13:53:34 +0000 (13:53 +0000)
committerTom Stellard <thomas.stellard@amd.com>
Fri, 18 Nov 2016 13:53:34 +0000 (13:53 +0000)
commit01e65d2cfc537d9163af6fd1a282868c41bae3fc
tree76ba70b9cc2dd71e9533736aa6c45f612dfe114ctree | snapshot
parent77382be56b3f1ff11cb7e44e6cccb0f429781e01commit | diff
AMDGPU/SI: Remove zero_extend patterns for i16 ops selected to 32-bit insts

Summary:
The 32-bit instructions don't zero the high 16-bits like the 16-bit
instructions do.

Reviewers: arsenm

Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, llvm-commits, tony-tye

Differential Revision: https://reviews.llvm.org/D26828

llvm-svn: 287342
llvm/lib/Target/AMDGPU/VOP2Instructions.td diff | blob | history
llvm/test/CodeGen/AMDGPU/extend-bit-ops-i16.ll [new file with mode: 0644] blob
Domain: System / Toolchain;