[PATCH] D149893: Rewrite LSV to handle longer chains.

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/GlobalISel/sdivrem.ll:1581
 ; GFX8-NEXT:    v_subb_u32_e32 v7, vcc, v7, v8, vcc
-; GFX8-NEXT:    s_waitcnt lgkmcnt(0)
-; GFX8-NEXT:    v_mov_b32_e32 v9, s5
----------------
tra wrote:
> This looks like some sort of barrier which was probably important. It would be great if someone familiar with AMDGPU backend could double check if the removal of this instruction is OK.
I wouldn't look too close at the waitcnt placement on a patch like this. This amounts to a scheduling change 


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D149893/new/

https://reviews.llvm.org/D149893