[PATCH] D85653: [GlobalISel][AMDGPU] Lower G_SMULH/G_UMULH

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp:545
+  if (ST.hasVOP3PInsts()) {
+    Mulh.fewerElementsIf(elementTypeIsNot(0, S8), scalarize(0));
+  } else {
----------------
This isn't the right logic, the intent is to go down to 2 elements for cases that can promote to <2 x i16>. s8 is't special here


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D85653/new/

https://reviews.llvm.org/D85653