[PATCH] D103321: Stop mulhi from doing 24 bit mul for uniform values

[David Stuttard via Phabricator via llvm-commits]

dstuttard created this revision.
Herald added subscribers: foad, kerbowa, hiraditya, nhaehnle, jvesely, arsenm.
dstuttard requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

Added support to check if architecture supports s_mulhi which is used as part of
the decision whether or not to use valu 24 bit mul (if the mulhi gets
transformed to a valu op anyway, then may as well use it).

This is an extension of the work in D97063 <https://reviews.llvm.org/D97063>


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D103321

Files:
  llvm/lib/Target/AMDGPU/AMDGPUISelLowering.cpp
  llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
  llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
  llvm/test/CodeGen/AMDGPU/mul_int24.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D103321.348537.patch
Type: text/x-patch
Size: 6301 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210528/42ffb566/attachment.bin>