This is the mail archive of the
mailing list for the GCC project.
Re: [PATCH V5, rs6000] Support vrotr<mode>3 for int vector types
On Tue, Aug 06, 2019 at 10:19:34AM +0800, Kewen.Lin wrote:
> on 2019/8/6 上午5:21, Segher Boessenkool wrote:
> > The other case is if not all shift counts are the same. I'm not sure
> > we actually care much about this case :-)
> Got it, I think even for the "other" case, the neg operation without masking
> is also safe since the hardware instructions do ignore the unrelated bits.
Oh it is perfectly safe. Only wondering how well we optimise this :-)