[PATCH] D62818: [InstCombine] Allow ((X << Y) & SignMask) != 0 to be optimized as (X << Y) s< 0.

Roman Lebedev via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Mon Jun 3 11:00:16 PDT 2019

Previous message: [PATCH] D62818: [InstCombine] Allow ((X << Y) & SignMask) != 0 to be optimized as (X << Y) s< 0.
Next message: [PATCH] D62818: [InstCombine] Allow ((X << Y) & SignMask) != 0 to be optimized as (X << Y) s< 0.
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

lebedev.ri added a comment.

Though this transform is also bad for X86: https://godbolt.org/z/KFM3gQ
When the `C2 << Y` isn't being hoisted out of the loop that is of course.


Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D62818/new/

https://reviews.llvm.org/D62818

Previous message: [PATCH] D62818: [InstCombine] Allow ((X << Y) & SignMask) != 0 to be optimized as (X << Y) s< 0.
Next message: [PATCH] D62818: [InstCombine] Allow ((X << Y) & SignMask) != 0 to be optimized as (X << Y) s< 0.
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

More information about the llvm-commits mailing list