[clang] [llvm] [RFC][AMDGPU] Use `bf16` instead of `i16` for bfloat (PR #80908)
Shilei Tian via llvm-commits
llvm-commits at lists.llvm.org
Tue Feb 13 15:47:06 PST 2024
================
@@ -2819,11 +2819,11 @@ def int_amdgcn_fdot2_f16_f16 :
def int_amdgcn_fdot2_bf16_bf16 :
ClangBuiltin<"__builtin_amdgcn_fdot2_bf16_bf16">,
DefaultAttrsIntrinsic<
- [llvm_i16_ty], // %r
+ [llvm_bfloat_ty], // %r
----------------
shiltian wrote:
The cast will be inserted automatically in `clang/lib/CodeGen/CGBuiltin.cpp` after removing the two assertions. I reverted my change to the test case by accident. Lol
https://github.com/llvm/llvm-project/pull/80908
More information about the llvm-commits
mailing list