[all-commits] [llvm/llvm-project] eb7c94: AMDGPU: Correct legal literal operand logic for mu...

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: eb7c947272952d40d3235d89652a10da52cb2b4d
      https://github.com/llvm/llvm-project/commit/eb7c947272952d40d3235d89652a10da52cb2b4d
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2025-02-18 (Tue, 18 Feb 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    M llvm/test/CodeGen/AMDGPU/eliminate-frame-index-v-add-co-u32.mir
    A llvm/test/CodeGen/AMDGPU/fold-literal-multiple-gfx10.mir
    M llvm/test/CodeGen/AMDGPU/fold-vgpr-copy.mir

  Log Message:
  -----------
  AMDGPU: Correct legal literal operand logic for multiple uses (#127594)

The same literal can be used multiple times in an instruction,
not just once. We were not tracking the used value to verify this,
so correct this.

This helps avoid regressions in a future patch.



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