Re: MMX built-ins performance oddities

[Prakash Punnoor <prakashp at arcor dot de>]

Andrew Pinski schrieb:
> On Feb 19, 2005, at 8:21 AM, Prakash Punnoor wrote:
>
> > Is this a known issue with gcc-3.4.3? I compiled the code using -O2
> > -march=athlon-xp -g3. If you want a smaller test case, I could try to
> > do so.
> > Right now I just didn't want to waste my time in case this is a know
> > issue or
> > I did something stupid...
>
>
> Yes the builtins are known to be a little stupid in 3.4.x.  Could you try
> a snapshot of 4.0.0?

So I tried with today's gcc4.0snapshot:

- union version is nearly as fast (or a little bit faster) as gcc3.4.3
- vector version is about 3% faster than above instead of 10% slower - wow!

But:

- vector version using mmintrin.h (intel style intrinsics) is ~3% slower than
above union version - still better than what gcc3.4.3 produces, but worse than
expected


So why is gcc 4.0 producing worse code when using intel style intrinsics and
why isn't the union version using builtins as fast as using the vector version?

Cheers
--
Prakash Punnoor

formerly known as Prakash K. Cheemplavam

Attachment: signature.asc
Description: OpenPGP digital signature