[PATCH] D85327: [SVE] Implement lowering for fixed length vector multiplication.

[Eli Friedman via Phabricator via llvm-commits]

efriedma added a comment.

If I'm following correctly, this enables the use of SVE for NEON-sized vectors by default if SVE is available.  I think this would actually mark the first time we're generating SVE instructions for -march=armv8.4-a+sve without the user explicitly requesting scalable vector operations, right?  I'd like to see test coverage for this, at least.  Or maybe we want to be more conservative for a little while...


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D85327/new/

https://reviews.llvm.org/D85327