[gmx-users] Re: gmx-users Digest, Vol 1, Issue 1430

[Erik Lindahl]

Hi,

> I am a bit confused by these results, it seems that the Mac has some
> advantage from the altivec loop on the systems with a lot of water, but
> really loses when it comes to large amounts of non-water molecules. It
> could also be a memory related problem, but it that was the main cause 
> the
> polymer should also do well on the Mac.

That's what I would expect. The altivec unit is higher performance than 
SSE, but it requires more permutations of the coordinates after load. 
For water-water interactions we do more calculations per load, so those 
will see more speedup than non-water interactions.

Cheers,

Erik