[all-commits] [llvm/llvm-project] af717d: [AMDGPU][MachineVerifier] Alignment check for fp32...

[Christudasan Devadasan via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: af717d4acac81b3abef6d76123b41d96c2bc7356
      https://github.com/llvm/llvm-project/commit/af717d4acac81b3abef6d76123b41d96c2bc7356
  Author: Christudasan Devadasan <Christudasan.Devadasan at amd.com>
  Date:   2022-03-17 (Thu, 17 Mar 2022)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInstrInfo.cpp
    M llvm/test/CodeGen/AMDGPU/verify-gfx90a-aligned-vgprs.mir

  Log Message:
  -----------
  [AMDGPU][MachineVerifier] Alignment check for fp32 packed math instructions

The fp32 packed math instructions are introduced in gfx90a.
If their vector register operands are not properly aligned, the
verifier should flag them. Currently, the verifier failed to
report it and the compiler ended up emitting a broken assembly.
This patch fixes that missed case in TII::verifyInstruction.

Reviewed By: arsenm

Differential Revision: https://reviews.llvm.org/D121794