[gmx-users] Possible problem in trxio.c
p.zuccato at exadron.com
Thu Jul 1 17:42:03 CEST 2004
Thanks to both of you
please do not take my benchmark as reliable yet. I'm working on it and I
hope to come with more reasonable numbers soon.
Also thanks for considering my proposal for enriching the gromacs site.
I'll post any new data as soon as possible
Erik Lindahl wrote:
>>> Are there any news on the new assembly loops for the Opteron?
>>> I read a message mentioning that gromacs 4 will know of the k8
>> This will not make a big change, at least not for single precision.
>> According to Erik L. the performance is identical.
> Actually it's a _tiny_ bit slower, since the pointers are 64 bit. The
> big advantage of AMD64 is that there are 8 additional registers
> though, and as soon as I've rewritten the water-water core to use all
> 16 XMM registers it should be very useful. Future EMT64 (Intel's
> 'copy' of amd64) will be able to use this too.
>>> What do you think of creating a page on the gromacs site with the best
>>> optimization flags for the major processors? I guess that most users
>>> have tried this, but it is quite complex and time-consuming. I'm
>>> thinking of something like a Wiki.
>> Could be useful, we could do it at gromacs.org, but the disadvantage of
>> a Wiki (as compared to a mailing list) is that you have to go there and
>> check out stuff.
> We try to include any new flags we know of in the automatic setup (it
> detects the compiler you are using), so post a message to the
> developers list with a clear subject so I don't miss it :-)
> gmx-users mailing list
> gmx-users at gromacs.org
> Please don't post (un)subscribe requests to the list. Use the www
> interface or send it to gmx-users-request at gromacs.org.
EXADRON, a division of Eurotech Spa
Via Jacopo Linussio, 1
33020 AMARO (UD) - ITALY
Phone: +39 0433 940 54
Fax: +39 0433 485 499
More information about the gromacs.org_gmx-users