[PATCH] D113448: [AMDGPU] Check for unneeded shift mask in shift PatFrags.

[Abinav Puthan Purayil via Phabricator via llvm-commits]

abinavpp added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/constrained-shift.ll:19
+; GISEL-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GISEL-NEXT:    v_and_b32_e32 v1, 15, v1
+; GISEL-NEXT:    v_lshlrev_b16_e32 v2, v1, v0
----------------
Do we see anything obvious in this change that's not allowing us to eliminate the `and` in global-isel for the divergent cases?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D113448/new/

https://reviews.llvm.org/D113448