[all-commits] [llvm/llvm-project] 6f5153: [AMDGPU] Route no-modifier reg-or-inline AsmParser...

[Valery Pykhtin via All-commits]

  Branch: refs/heads/users/vpykhtin/amdgpu-asmparser-nomods-align-aware
  Home:   https://github.com/llvm/llvm-project
  Commit: 6f5153332881c207354a22d4dc5b8b623036b0f2
      https://github.com/llvm/llvm-project/commit/6f5153332881c207354a22d4dc5b8b623036b0f2
  Author: Valery Pykhtin <valery.pykhtin at amd.com>
  Date:   2026-09-08 (Tue, 08 Sep 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
    M llvm/test/MC/AMDGPU/misaligned-vgpr-tuples-err.s

  Log Message:
  -----------
  [AMDGPU] Route no-modifier reg-or-inline AsmParser operands through HwMode predicate

Convert the reg-or-inline operands with no modifiers (MFMA VGPR/AGPR
sources, VCSrc, v_pk_mov_b32, VOP scalar f64) from the fixed-class
isRegOrInlineNoMods to the HwMode-aware isRegOrInlineNoModsByHwMode, so an
odd-aligned tuple is rejected at the offending operand column instead of by
the validateVGPRAlign catch-all.

Co-Authored-By: Claude <noreply at anthropic.com>


  Commit: f079886541e51166ce6b1ece7a52a3aa046871b2
      https://github.com/llvm/llvm-project/commit/f079886541e51166ce6b1ece7a52a3aa046871b2
  Author: Valery Pykhtin <valery.pykhtin at amd.com>
  Date:   2026-09-08 (Tue, 08 Sep 2026)

  Changed paths:
    M llvm/test/MC/AMDGPU/misaligned-vgpr-tuples-err.s
    M llvm/test/MC/AMDGPU/out-of-range-registers.s

  Log Message:
  -----------
  [AMDGPU] Update no-modifier operand tests for the dropped align diagnostic

The no-modifier reg-or-inline operands routed through the HwMode
predicate now report a misaligned tuple as a plain invalid operand,
matching the diagnostic dropped earlier in the stack.


Compare: https://github.com/llvm/llvm-project/compare/0a11146524d2...f079886541e5

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