[PATCH] D155288: [RISCV] Add a new select combine for when the condition is a setcc that will be inverted

[Philip Reames via Phabricator via llvm-commits]

reames added a comment.

In D155288#4593318 <https://reviews.llvm.org/D155288#4593318>, @craig.topper wrote:

> Looks like we're only seeing any benefit on forced-atomics.ll now? @reames can you share a reproducer for the BR_CC issue?

Will do.  Will probably take me a couple days; I had been working only from a binary, and need to go figure out the build system for said benchmark.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D155288/new/

https://reviews.llvm.org/D155288