[PATCH] D110486: [DAG] scalarizeExtractedVectorLoad - replace getABITypeAlign with allowsMemoryAccess (PR45116)

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon created this revision.
RKSimon added reviewers: dmgreen, fhahn, efriedma, spatel.
Herald added subscribers: ecnelises, pengfei, arphaman, hiraditya.
RKSimon requested review of this revision.
Herald added a project: LLVM.

One of the cases identified in PR45116 - we don't need to limit extracted loads to ABI alignment, we can use allowsMemoryAccess - which tests using getABITypeAlign, but also checks if a target permits (fast) misaligned memory loads by checking allowsMisalignedMemoryAccesses as a fallback.

I've also cleaned up the alignment calculation code - if we have a constant extraction index then the alignment can be based on an offset from the original vector load alignment, but for non-constant indices we should assume the worst (byte alignment only), which changes the vecloadextract.ll test checks.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D110486

Files:
  llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
  llvm/test/CodeGen/AArch64/arm64-indexed-vector-ldst.ll
  llvm/test/CodeGen/X86/merge-consecutive-stores-nt.ll
  llvm/test/CodeGen/X86/vecloadextract.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D110486.375059.patch
Type: text/x-patch
Size: 8382 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210925/23a2fc46/attachment.bin>