projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: c22867f) | patch
[AMDGPU] Shrinking V_SUBBREV_U32
authorStanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
Sat, 24 Feb 2018 01:32:32 +0000 (01:32 +0000)
committerStanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com>
Sat, 24 Feb 2018 01:32:32 +0000 (01:32 +0000)
commitfa48c496e2ccde292b74b5dc45aa29c65e3748be
tree821f35f9135999480b15bcfb994d1aaf021c9369tree | snapshot
parentc22867f5fc960970d413a15cfe47a2e7379c6e29commit | diff
[AMDGPU] Shrinking V_SUBBREV_U32

V_SUBBREV_U32 is a commute opcode for V_SUBB_U32. However, when
we try to commute V_SUBB_U32 in order to shrink it we do not then
process V_SUBBREV_U32 and it stay VOP3. This is fixed.

Differential Revision: https://reviews.llvm.org/D43699

llvm-svn: 326011
llvm/lib/Target/AMDGPU/SIShrinkInstructions.cpp diff | blob | history
llvm/test/CodeGen/AMDGPU/combine-cond-add-sub.ll diff | blob | history
llvm/test/CodeGen/AMDGPU/shrink-carry.mir diff | blob | history
Domain: System / Toolchain;