shri-acha wrote: I checked out the changes made by me and it seems as though, I was confused, so as to not to be confused in making any future changes, I'd like to explain my understand and please mention if I am wrong in anyway:
> When we mention ep(i/u)8 , I will be using explicitly signed vectors like > _v64q(s/u) > When we mention ep(i/u)16, I will be using _v32h(i/u) > When we mention ep(i/u)32, I will be using _v32s(i/u) > When we mention ep(i/u)64, I will be using _v32d(i/u) https://github.com/llvm/llvm-project/pull/169452 _______________________________________________ cfe-commits mailing list [email protected] https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
