[PATCH] D48768: [X86] When have BMI2, prefer shifts to clear low/high bits, rather than variable mask.

[Roman Lebedev via Phabricator via llvm-commits]

lebedev.ri created this revision.
lebedev.ri added reviewers: craig.topper, RKSimon, spatel.

This adds a reverse transform for the instcombine canonicalizations
that were added in https://reviews.llvm.org/D47980, https://reviews.llvm.org/D47981.

As discussed later, that was worse at least for the code size,
and potentially for the performance, too.


Repository:
  rL LLVM

https://reviews.llvm.org/D48768

Files:
  lib/Target/X86/X86InstrCompiler.td
  lib/Target/X86/X86InstrInfo.td
  test/CodeGen/X86/clear-highbits.ll
  test/CodeGen/X86/clear-lowbits.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D48768.153478.patch
Type: text/x-patch
Size: 16497 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180629/c9f55f1b/attachment.bin>