[PATCH] D139398: [AMDGPU] Add bf16 storage support

[Matt Arsenault via Phabricator via llvm-commits]

arsenm added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUCallingConv.td:49
+  CCIfType<[bf16], CCBitConvertToType<i16>>,
+  CCIfType<[v2bf16], CCBitConvertToType<i32>>,
   CCIfNotInReg<CCIfType<[f32, i32, f16, i16, v2i16, v2f16] , CCAssignToReg<[
----------------
Without being added to a register class, all the tablegen changes should not do anything


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D139398/new/

https://reviews.llvm.org/D139398