tree 0997a10170b38fa20b25f833b2d24f6bd79ccd5e
parent bf3266d130c74f715897dd860cec93ab42eed105
author Changpeng Fang <changpeng.fang@gmail.com> 1547593956 +0000
committer Changpeng Fang <changpeng.fang@gmail.com> 1547593956 +0000

AMDGPU: Raise the priority of MAD24 in instruction selection.

Summary:
  We have seen performance regression when v_add3 is generated. The major reason is that the v_mad pattern
is broken when v_add3 is generated. We also see the register pressure increased. While we could not properly
estimate register pressure during instruction selection, we can give mad a higher priority.

In this work, we raise the priority for mad24 in selection and resolve the performance regression.

Reviewers:
  rampitec

Differential Revision:
  https://reviews.llvm.org/D56745

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@351273 91177308-0d34-0410-b5e6-96231b3b80d8