AMDGPU: Fold CI-specific complex SMRD patterns into existing complex patterns

This is just a cleanup. Also, it adds checking that ByteCount is aligned to 4.

Reviewers: arsenm, nhaehnle, tstellarAMD

Subscribers: kzhuravl, wdng, yaxunl, tony-tye

Differential Revision: https://reviews.llvm.org/D28994

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@303658 91177308-0d34-0410-b5e6-96231b3b80d8
4 files changed