]> granicus.if.org Git - llvm/commit
AMDGPU: Don't rematerialize mov with implicit operands
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Mon, 4 Feb 2019 22:26:21 +0000 (22:26 +0000)
committerMatt Arsenault <Matthew.Arsenault@amd.com>
Mon, 4 Feb 2019 22:26:21 +0000 (22:26 +0000)
commit5d2f3ca3d6847bd8667b50af98dd9abbe34ecf90
treed324deb603fff33a3c2ac1f885cb1d226d47bbae
parent11ecb01af0732e06e21ad73b1e2cb50378545940
AMDGPU: Don't rematerialize mov with implicit operands

This was pulling the mov used for register indexing on gfx9 out of the
loop.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@353101 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AMDGPU/SIInstrInfo.cpp
test/CodeGen/AMDGPU/no-remat-indirect-mov.mir [new file with mode: 0644]