[PATCH] D81547: [X86][SSE] combineVectorSizedSetCCEquality - handle OR vector reductions

[Sanjay Patel via Phabricator via llvm-commits]

spatel added inline comments.


================
Comment at: llvm/lib/Target/X86/X86ISelLowering.cpp:45534
 
   // We're looking for an oversized integer equality comparison.
+  bool IsReduction = false;
----------------
Code comments like this and the function name don't apply if we're matching a reduction, right?
I think we need to refactor and/or update comments to reduce confusion.


================
Comment at: llvm/test/CodeGen/X86/pr45378.ll:12
 
 define void @parseHeaders(i64 * %ptr) {
 ; SSE2-LABEL: parseHeaders:
----------------
Add 'nounwind' attribute to remove .cfi noise?
Would it make sense to minimize the test to return the i1 icmp rather than branch and make an external call?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D81547/new/

https://reviews.llvm.org/D81547