[MPlayer-dev-eng] altivec patch 1/5: missing vec_splat in vec_clip

[Romain Dolbeau]

Luca Barbato wrote:

> There is a simpler but maybe longer solution, that one is an ugly 
> workaround just to check if load and splat is that bad, if you think 
> that is a bug you know the lovely gcc bts and I'd love to see a reply 
> from them =)

The only time I tried the gcc mailing list was a long while
ago. I offered to try the devel version on an architecture
that was explicitely labeled as being of interest. I got
flamed for annoying the gods^Wdevelopers.

I've since assumed they don't need my help.

> I don't know why gcc should assume you don't want a load single element 
> and it has to automagically expand {a} to {a,a,a,a} and then use load 
> vector...

That's what specifications are for. The guys who designed
the instructions set made one, and gcc decided to not go
along and made their own, apparently. Or maybe it's just
broken.

> I'd rather have code working on the current mantained compilers and that 
> seems to mean gcc-fsf and xlc ...

Is that supposed to be a troll ? Apple maintains its own branch very
well, thank you very much. In fact, I'd go all the way and say
it's the *only* supported gcc w.r.t. AltiVec.

-- 
Romain Dolbeau
<romain at dolbeau.org>