[PATCH] D46008: [X86][AArch64][NFC] Add tests for vector masked merge unfolding

[Roman Lebedev via Phabricator via llvm-commits]

lebedev.ri created this revision.
lebedev.ri added reviewers: spatel, craig.topper, RKSimon.
Herald added a reviewer: javed.absar.

This is PR37104 <https://bugs.llvm.org/show_bug.cgi?id=37104>.

PR6773 <https://bugs.llvm.org/show_bug.cgi?id=6773> will introduce an IR canonicalization that is likely bad for the end assembly.
Previously, `andps`+`andnps` / `bsl` would be generated. (see `@out`)
Now, they would no longer be generated  (see `@in`).

Also, i think one more piece is missing - shouldn't the `blend` instruction be used?


Repository:
  rL LLVM

https://reviews.llvm.org/D46008

Files:
  test/CodeGen/AArch64/unfold-masked-merge-vector-variablemask.ll
  test/CodeGen/X86/unfold-masked-merge-vector-variablemask.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D46008.143726.patch
Type: text/x-patch
Size: 523120 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180424/04a033d8/attachment-0001.bin>