[PATCH] D130989: [AMDGPU][MC][GFX11] Correct v_dot2_f16_f16 and v_dot2_bf16_bf16

Joe Nash via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Tue Aug 2 08:11:33 PDT 2022


Joe_Nash added a comment.

This looks fine for v_dot2_f16_f16. 
For v_dot2_bf16_bf16 I am a bit unsure. Because we treat bf16 as int16, will ISel work correctly if we use the FP16InputMods? We don't have a codegen test for that, one should probably be added to llvm.amdgcn.fdot2.bf16.bf16.ll . IntOpSelMods is a potential alternative SrcModifiers operand class to use.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D130989/new/

https://reviews.llvm.org/D130989



More information about the llvm-commits mailing list