[patch] Simplify a vpermilps with constant mask

Rafael EspĂ­ndola rafael.espindola at gmail.com
Mon Apr 21 11:26:18 PDT 2014


On 21 April 2014 13:47, Jim Grosbach <grosbach at apple.com> wrote:
> Why not change the clang IR codegen to just get this right in the first place?

Because an intermediate optimization can make the mask constant.

Cheers,
Rafael



More information about the llvm-commits mailing list