[PATCH] D87452: [InstCombine] matchRotate - support (uniform) constant rotation amounts (PR46895)

[Simon Pilgrim via Phabricator via llvm-commits]

RKSimon added a comment.

In D87452#2295999 <https://reviews.llvm.org/D87452#2295999>, @nikic wrote:

> There's a 40% code size increase on CMakeFiles/7zip-benchmark.dir/CPP/7zip/Crypto/Sha1.cpp.o, might be worth double checking that we're not missing some optimizations on funnel shifts.

Looking at this now: https://wide.godbolt.org/z/h9GoTo

At first glance it looks like some really poor funnel/rotate cost model values - before we were vectorizing the expanded or+shift patterns - but fail to do the same for rotate intrinsics


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D87452/new/

https://reviews.llvm.org/D87452