[all-commits] [llvm/llvm-project] 8fdfe2: AMDGPU: Fix treating unknown mem operands as uniform

[Matt Arsenault via All-commits]

  Branch: refs/heads/users/arsenm/fix-treating-unknown-mmo-uniform
  Home:   https://github.com/llvm/llvm-project
  Commit: 8fdfe29d44a44f860395c0b0d86a818745393e2c
      https://github.com/llvm/llvm-project/commit/8fdfe29d44a44f860395c0b0d86a818745393e2c
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2025-11-20 (Thu, 20 Nov 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUInstrInfo.cpp
    M llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp
    M llvm/test/CodeGen/AMDGPU/GlobalISel/extractelement.i128.ll
    M llvm/test/CodeGen/AMDGPU/GlobalISel/implicit-kernarg-backend-usage-global-isel.ll

  Log Message:
  -----------
  AMDGPU: Fix treating unknown mem operands as uniform

The test changes are mostly GlobalISel specific regressions.
GlobalISel is still relying on isUniformMMO, but it doesn't really
have an excuse for doing so. These should be avoidable with new
regbankselect.

There is an additional regression for addrspacecast for cov4. We
probably ought to be using a separate PseudoSourceValue for the
access of the queue pointer.



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