[all-commits] [llvm/llvm-project] f96f12: [AMDGPU][InstCombine] Fold constant add/sub into t...

[Harrison Hao via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: f96f12533199911caea0ccc0fd96f18df37c8ca4
      https://github.com/llvm/llvm-project/commit/f96f12533199911caea0ccc0fd96f18df37c8ca4
  Author: Harrison Hao <57025411+harrisonGPU at users.noreply.github.com>
  Date:   2026-09-24 (Thu, 24 Sep 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
    M llvm/test/Transforms/InstCombine/AMDGPU/llvm.amdgcn.dot.ll

  Log Message:
  -----------
  [AMDGPU][InstCombine] Fold constant add/sub into the dot accumulator (#225002)

`amdgcn.{s,u}dot{2,4,8}(a, b, C) +/- K -> dot(a, b, C +/- K)` when both
the
accumulator C and K are constants. The new constant is computed with
wrapping APInt arithmetic to match the non-clamping accumulate.

Only applies when clamp is false (the saturating accumulate does not
reassociate) and the dot has a single use. K - dot is left alone since
it
would need the dot product negated.



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