[all-commits] [llvm/llvm-project] c9b281: AMDGPU: Fix cost model for 16-bit operations on gf...

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: c9b28163888574bcfba0171372ae0dcfb40abbfa
      https://github.com/llvm/llvm-project/commit/c9b28163888574bcfba0171372ae0dcfb40abbfa
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2025-06-18 (Wed, 18 Jun 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
    M llvm/test/Analysis/CostModel/AMDGPU/canonicalize.ll
    M llvm/test/Analysis/CostModel/AMDGPU/copysign.ll
    M llvm/test/Transforms/SLPVectorizer/AMDGPU/slp-v2f16.ll

  Log Message:
  -----------
  AMDGPU: Fix cost model for 16-bit operations on gfx8 (#141943)

We should only divide the number of pieces to fit the packed instructions
if we actually have pk instructions. This increases the cost of copysign,
but is closer to the current codegen output. It could be much cheaper
than it is now.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications