================

----------------
RKSimon wrote:

I'm hesitant to use `__builtin_convertvector` as although it looks like we're 
consistent with fp32 -> bf16 using round rmNearestTiesToEven in dag, I don't 
know the code well enough to be sure that we do this everywhere - do you think 
its ok?

https://github.com/llvm/llvm-project/pull/169841
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Reply via email to