[PATCH] D147408: [AMDGPU] Iterative scan implementation for atomic optimizer.

[Jay Foad via Phabricator via llvm-commits]

foad added inline comments.


================
Comment at: llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll:459-462
+; GFX8-NEXT:    s_ff1_i32_b32 s5, s3
+; GFX8-NEXT:    s_ff1_i32_b32 s6, s2
+; GFX8-NEXT:    s_add_i32 s5, s5, 32
+; GFX8-NEXT:    s_min_u32 s5, s6, s5
----------------
Not your fault, but we really ought to be able to select s_ff1_i32_b64 here.


================
Comment at: llvm/test/CodeGen/AMDGPU/atomic_optimizations_buffer.ll:468
+; GFX8-NEXT:    s_add_i32 s4, s4, s8
+; GFX8-NEXT:    s_andn2_b64 s[2:3], s[2:3], s[6:7]
+; GFX8-NEXT:    s_cmp_lg_u64 s[2:3], 0
----------------
Not your fault, but we really ought to be able to select s_bitset0_b64 here.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D147408/new/

https://reviews.llvm.org/D147408