[all-commits] [llvm/llvm-project] 90d396: AMDGPU: Fix cost model for 16-bit operations on gfx8

Matt Arsenault via All-commits all-commits at lists.llvm.org
Tue Jun 17 16:05:23 PDT 2025


  Branch: refs/heads/users/arsenm/amdgpu/fix-cost-of-16-bit-ops
  Home:   https://github.com/llvm/llvm-project
  Commit: 90d3969fd5400b43a658622ba460a78d42fdf215
      https://github.com/llvm/llvm-project/commit/90d3969fd5400b43a658622ba460a78d42fdf215
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2025-06-17 (Tue, 17 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

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


More information about the All-commits mailing list