[all-commits] [llvm/llvm-project] af717d: [AMDGPU][MachineVerifier] Alignment check for fp32...
Christudasan Devadasan via All-commits
all-commits at lists.llvm.org
Wed Mar 16 19:57:29 PDT 2022
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
More information about the All-commits
mailing list