[PATCH] D68457: [X86] Enable AVX512BW for memcmp

[David Zarzycki via Phabricator via llvm-commits]

davezarzycki updated this revision to Diff 223365.
davezarzycki retitled this revision from "[X86] Enable AVX512BW and AVX512VL for memcmp" to "[X86] Enable AVX512BW for memcmp".
davezarzycki added a comment.

Simplified to just enabling AVX512BW for 512 and let 128/256 keep using AVX/AVX2.

PS – I trust your knowledge of instruction latencies. I wonder what Agner Fog did wrong if he measured PMOVMSKB as having 2-3 cycles of latency.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D68457/new/

https://reviews.llvm.org/D68457

Files:
  lib/Target/X86/X86ISelLowering.cpp
  llvm/test/CodeGen/X86/memcmp.ll
  llvm/test/CodeGen/X86/setcc-wide-types.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D68457.223365.patch
Type: text/x-patch
Size: 8454 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20191005/7b348015/attachment.bin>