[all-commits] [llvm/llvm-project] 73d904: AMDGPU: Fix using useless cachepolicy argument in ...

[Matt Arsenault via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 73d90412541983b817296712669fe1b134105d56
      https://github.com/llvm/llvm-project/commit/73d90412541983b817296712669fe1b134105d56
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-06-10 (Mon, 10 Jun 2024)

  Changed paths:
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.fadd.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.fadd.ll

  Log Message:
  -----------
  AMDGPU: Fix using useless cachepolicy argument in buffer atomic test

This was probably intended to test the immediate offset addressing
mode. Add some tests to check immediate offsets, and clean up run lines.


  Commit: dbc99e9521d61cfe2e0604adc7d6cc2b12ad56ca
      https://github.com/llvm/llvm-project/commit/dbc99e9521d61cfe2e0604adc7d6cc2b12ad56ca
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-06-10 (Mon, 10 Jun 2024)

  Changed paths:
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.raw.buffer.atomic.fadd.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.atomic.fadd.ll

  Log Message:
  -----------
  AMDGPU: Simplify some tests by not using amdgpu_ps

Since inreg now works for the default calling convention, we can
check the output with fewer argument shuffling instructions.


Compare: https://github.com/llvm/llvm-project/compare/e19199bd9c91...dbc99e9521d6

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