[PATCH] D122803: [AMDGPU][GlobalISel] Scalarize add/sub with overflow ops in the legalizer

[Jay Foad via Phabricator via llvm-commits]

foad added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp:635
+    .scalarize(0)
+    .scalarize(1)
     .lower();
----------------
Surely you don't need both of these lines - all operands are vectors or all are scalars.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D122803/new/

https://reviews.llvm.org/D122803