[PATCH] D78606: [DAGCombine] Adding a new Newton-Raphson implementation to leverage the FMA

Scott Manley via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Tue Apr 21 20:01:19 PDT 2020


rscottmanley added a comment.

Are your accuracy and speedup numbers applicable for both f32 and f64 sqrt?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D78606/new/

https://reviews.llvm.org/D78606





More information about the llvm-commits mailing list