[all-commits] [llvm/llvm-project] e45993: [AMDGPU] Fix sub-dword atomic flat saddr store wit...

[Stanislav Mekhanoshin via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: e45993d9a7ad2c07989d18888e56c5fc3276902f
      https://github.com/llvm/llvm-project/commit/e45993d9a7ad2c07989d18888e56c5fc3276902f
  Author: Stanislav Mekhanoshin <Stanislav.Mekhanoshin at amd.com>
  Date:   2025-09-23 (Tue, 23 Sep 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/FLATInstructions.td

  Log Message:
  -----------
  [AMDGPU] Fix sub-dword atomic flat saddr store with no D16. NFCI (#160253)

The pattern does not factor saddr. There is no way to write a test
for it because gfx1200 does not have sram-ecc but also no saddr,
and gfx1250 does not fall into this preserving category while has
sram-ecc. Nevertheless, the day we could fix it that would become a
problem. For now it is OK that change does not fail.

That was untested before and it is untested now, but at least t16
block uses t16 patterns.



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