[PATCH] D141693: [AArch64] turn extended vecreduce bigger than v16i8 into udot/sdot

Zain Jaffal via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Mon Jan 16 04:15:01 PST 2023


zjaffal updated this revision to Diff 489500.
zjaffal added a comment.

1. Update IsValidElementCount to check for vectors as multiples of 8.
2. Move Zero and DotOpcode outside the for loop


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D141693/new/

https://reviews.llvm.org/D141693

Files:
  llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
  llvm/test/CodeGen/AArch64/neon-dotreduce.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D141693.489500.patch
Type: text/x-patch
Size: 76826 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230116/331d1e96/attachment-0001.bin>


More information about the llvm-commits mailing list