AMDGPU/SI: Make comments more precise.
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Sat, 15 Aug 2015 00:12:30 +0000 (00:12 +0000)
committerMatt Arsenault <Matthew.Arsenault@amd.com>
Sat, 15 Aug 2015 00:12:30 +0000 (00:12 +0000)
commit7b04c2634149a9b918d7e9d11b0fd090bb13a482
tree76104c0db33f0e5e2ea10111ccd70e6bf59d0dce
parent3b0b6f081abf8d7a8d1c17250cfa28dc05cead5a
AMDGPU/SI: Make comments more precise.

True branch instructions do behave as expected with liveness.

Avoid the phrasing "branch decision is based on a value in an SGPR"
because this could be misleading. A VALU compare instruction's
result is still based on an SGPR, even though that condition
may be divergent.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@245131 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AMDGPU/SIFixSGPRLiveRanges.cpp