[PATCH] D153620: [X86] Combine MUL+SRL+TRUNC to MULX for i32 on 64-bit

[Eli Friedman via Phabricator via llvm-commits]

efriedma added a comment.

> "does not read or write arithmetic flags" described in intrinsic guide

How much do we actually care about honoring this?  A program written in C can't tell if an intrinsic overwrites arithmetic flags; I'd feel free to just pick the fastest lowering, regardless of what the guide says.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D153620/new/

https://reviews.llvm.org/D153620