[PATCH] D93599: [DAG] Simplify icmp(EQ/NE, OR(X,SHL(Y,BW/2), 0/-1) patterns

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon created this revision.
RKSimon added reviewers: spatel, efriedma, lebedev.ri.
Herald added subscribers: pengfei, hiraditya.
RKSimon requested review of this revision.
Herald added a project: LLVM.

Attempt to simplify none-of/all-of style patterns that concatenate 2 smaller integers together into an and/or + icmp 0/-1 instead.

This is mainly to help some bool predicate reduction patterns where we end up concatenating bool vectors that have been bitcasted to integers.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D93599

Files:
  llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
  llvm/test/CodeGen/X86/avx512-mask-op.ll
  llvm/test/CodeGen/X86/movmsk-cmp.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D93599.312984.patch
Type: text/x-patch
Size: 38129 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20201220/aeffe9cf/attachment.bin>