[gmx-developers]

[Erik Lindahl]

Hi Brendan,

I've put a presentation I made a while ago on the Altivec 
(single-instruction-multiple-data) optimization at:

http://lindahl.sbc.su.se/~lindahl/outgoing/gmx_optimization/

(it's a bit too large for posting to the list).

The SIMD optimizations might not apply at all, but the document also 
contains a summary of the important algorithm and what the "expensive" 
parts of the code do.

I'll be happy to assist in case you need more information.

Cheers,

Erik


On Apr 22, 2005, at 6:20 PM, Brendan Moran wrote:

> Hi,
> I saw that there was a discussion of a hardware accellerator for gmx a 
> while back.  I would be interested in contributing to such a project 
> and I have access to a PCI FPGA platform that I can experiment with.
>
> If there are still people who are interested in a gmx hardware 
> accellerator, I'd like to help out.  If someone could point me at the 
> more processor intensive sections of the gmx algorithm (I don't know 
> the gmx code at all yet), I could have a look and see if FPGA based 
> optimization looks practical.
>
> Thanks,
> Brendan
> _______________________________________________
> gmx-developers mailing list
> gmx-developers at gromacs.org
> http://www.gromacs.org/mailman/listinfo/gmx-developers
> Please don't post (un)subscribe requests to the list. Use the www 
> interface or send it to gmx-developers-request at gromacs.org.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 2363 bytes
Desc: not available
URL: <http://maillist.sys.kth.se/pipermail/gromacs.org_gmx-developers/attachments/20050422/29ae1846/attachment.p7s>