[PATCH] D93963: [GlobalISel][AMDGPU] Lower G_UMULO/G_SMULO

Pushpinder Singh via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Sun Jan 10 23:45:28 PST 2021


pdhaliwal marked an inline comment as done.
pdhaliwal added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp:606
 
+  getActionDefinitionsBuilder({G_UMULO, G_SMULO}).lower();
+
----------------
arsenm wrote:
> Would you get better results if you:
> 1. scalarized vectors first
> 2. Promoted small scalar types first?
In both cases, the MULO is somehow considered legal by compiler. For e.g. even for s32, expansion does not occur, compiler is directly using S/UMULO instructions. I am investigating this.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D93963/new/

https://reviews.llvm.org/D93963



More information about the llvm-commits mailing list