[llvm] r312095 - [AMDGPU] Use v_max_f* for fcanonicalize
Matt Arsenault via llvm-commits
llvm-commits at lists.llvm.org
Tue Aug 29 21:24:20 PDT 2017
> On Aug 29, 2017, at 20:27, Mekhanoshin, Stanislav <Stanislav.Mekhanoshin at amd.com> wrote:
>
> Is there a packed max, I do not recall?
>
> Stas
Yes, v_pk_max_f16
More information about the llvm-commits
mailing list