[PATCH] D142782: [AMDGPU] Add basic support for extended i8 perm matching

[Jay Foad via Phabricator via llvm-commits]

foad added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/fast-unaligned-load-store.global.ll:42
 ; GFX9-NEXT:    s_waitcnt vmcnt(0)
-; GFX9-NEXT:    v_lshl_or_b32 v0, v3, 16, v2
 ; GFX9-NEXT:    s_setpc_b64 s[30:31]
----------------
These kind of changes look like regressions for some combination of code size / latency / sgpr pressure.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D142782/new/

https://reviews.llvm.org/D142782