AMDGPU: Don't fold subregister extracts into tied operands
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Mon, 15 Aug 2016 16:18:36 +0000 (16:18 +0000)
committerMatt Arsenault <Matthew.Arsenault@amd.com>
Mon, 15 Aug 2016 16:18:36 +0000 (16:18 +0000)
commit3661e90e718107888948a2d50e452f09df218551
treed1a3da8a9fe1372260a2f24fa013d7be79dafed1
parent7cb809983daa7c32b4ca25d268983acbefb0f2bd
AMDGPU: Don't fold subregister extracts into tied operands

llvm-svn: 278676
llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
llvm/test/CodeGen/AMDGPU/operand-folding.ll