[all-commits] [llvm/llvm-project] dc0fa1: AMDGPU: Start fixing inconsistencies in usage of S...

Matt Arsenault via All-commits all-commits at lists.llvm.org
Fri Jun 21 10:11:15 PDT 2024


  Branch: refs/heads/users/arsenm/amdgpu-mubuf-subtarget-predicate-cleanup
  Home:   https://github.com/llvm/llvm-project
  Commit: dc0fa1e2d5d0660c9b629da76f09a371e4be6c6e
      https://github.com/llvm/llvm-project/commit/dc0fa1e2d5d0660c9b629da76f09a371e4be6c6e
  Author: Matt Arsenault <Matthew.Arsenault at amd.com>
  Date:   2024-06-21 (Fri, 21 Jun 2024)

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

  Log Message:
  -----------
  AMDGPU: Start fixing inconsistencies in usage of SubtargetPredicate

SubtargetPredicate should be the primary "does this instruction exist"
predicate, with OtherPredicates used for other side pieces of information.

Changes like 856d1c4410 were backwards. The problematic usage is how
GFX12 is using HasRestrictedOffset. The multiclasses for buffers
should probably be split up instead of hiding OtherPredicates inside
the buffer atomic multiclasses. The two cases are mutually exclusive
and really need a negated predicate for the not-gfx12 case.

It's pretty terrible we have to manage this in the first place.
TableGen should be able to figure out the required predicates
from any instructions that appear in the pattern output.



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


More information about the All-commits mailing list