FAH-News

[Der Diplomat]

Danke für die Info!

[Bommer]

Hallo

Und was haste mit deinen DUAL-Opterons gemacht ???

Gruss Bommer

[S_Garbe]

die rechnen so vor sich hin

[scsimodo]

die rechnen so vor sich hin

Also alles in Butter

[Peter Fanghänel]

Bin nun durch Zufall auf die Antwort gestossen:
Es geht hierbei um den Support des QMD-Cores, dessen WUs derzeit nur an intel-CPUs vergeben werden.

What about AMD support? We are currently using the Intel Fortran compiler and libraries. This software intentially runs slowly on AMD CPUs (SSE2 is not supported). While there have been hacks around this issue, such modifications violate Intel's EULA. At FAH, we follow software EULAs and are thus bound to this limitation imposed by Intel.
That's not fair to AMD chips! Yes, it isn't fair and AMD is taking actions against this. We hope that things will change, but our hands are tied here. We could give these WUs to AMD machines, but they would have a much worse points per day (less than half of what one gets on Intel hardware) and would not perform well in general.

Quelle: http://folding.stanford.edu/QMD.html
Natürlich nur für die von Interesse, die nicht ohnehin inzwischen den SMP-Client einsetzen.

wie kommst du darauf das f@h auf intel systeme ausgelegt ist?

[Michael H.W. Weber]

Es gibt eine neue Veröffentlichung des FAH-Teams in PNAS, in der es um den Einfluß des Lösungsmittels auf die Proteinfaltungskinetik und -thermodynamik geht: http://www.pnas.org/cgi/content/abstrac ... 10430?etoc

Michael.

[Sven]

Some buildings at the medical school (and perhaps more broadly) are having an unplanned network outage. We're working with them to see what we can do. For now, we're mainly waiting on them, while we investigate other possible fixes.

For the most part, FAH's built in redundancies in our server-side backend is working well, so I think we'll be ok, but just a heads up to all the folders (and especially in case the networking gets worse and we can't post updates).

Diese Meldung ist von Gestern und betrifft anscheinend nicht alle Server, denn WUs werden up- und down-geloadet, lediglich die Informations-/Statistikseiten etc. sind nicht zu erreichen.


Erledigt

[Sven]

Seit einigen Tagen steht parallel zu den News ein neues Blog zur Verfügung =>

http://folding.typepad.com/

dieses soll eventuell die News-Seite ersetzen.

[willmannand]

Bei FAH wurde die Webseite überarbeitet. Sie ist jetzt auch in verschiedenen Sprachen (unter anderem Deutsch) verfügbar. Allerdings ist sie noch fehlerhaft: wenn die Statistik eines Teams oder die persönliche statistik betrachtet wird, wird noch die alte Webseite angezeigt., dies funktioniert einwandfrei. Allerdings werden noch die alten Links angezeigt, d.h. wenn aus der Statistikseite z.B. auf den Link "Home" geklickt wird, erscheint die Fehlermeldung, daß die Webseite nicht gefunden wurde.

[Bommer]

Hier mal einige NEWS vom 24.01.2008 und 25.01.2008 von der FAH-Seite !!!

24.01.2008

Update on new GPU core

Several people have been curious about any news regarding a new GPU client/core. We hit a few snags and then hit the holiday break, but the team is back now. We have the new client running in our lab and we're doing some final Q&A on it. The new code is running on the latest ATI cards (2xxx and 3xxx) and getting pretty good performance so far. The performance is pretty good now (after some optimizations from Mark and Mike H.), so I'm optimistic. This does not look like a 6-month delay, more like a few week delay, but it's hard to tell -- you can't predict the unpredictable things which can come up.


25.01.2008

Code development updates

Here are some code development updates on some important client/cores

GPU core: we've got the GPU core running in house and we found and fixed some bugs in our QA stage. We're now continuing QA to see if we find any more bugs. Right now, the GPU core is running on all new ATI cards, so we're excited to roll it out. We are using CAL now (ATI's hardware abstraction layer) and that seems to make life a lot easier, and also should make running a GPU client a lot easier from the point of view of donors, as the driver issues and complexities should now be resolved. We are still looking into an NVIDIA client. The NVIDIA GPUs are very different to program, so a port isn't a simple thing to do. We are looking into this, though.

SMP core: right now, SMP on Linux and OSX is behaving fairly well, whereas Windows is giving some issues. This is perhaps not a surprise, since the SMP code must use MPI, which has its origins on UNIX and is a newcomer to Windows. We have been working with Windows MPI developers to improve the situation, but they tell us this isn't a simple fix. Since we are in the business of studying proteins, not writing MPI libraries for Windows, we will wait until the MPI experts improve the Windows MPI before we make any claims of improvement there.

Finally, beta clients will be expiring soon, and we are in the process of QA for new clients. We will also extend the expiration deadlines in the future clients to give some more time, and since the clients are appearing to be maturing.



Gruss Bommer

[arminius]

Hier ein aktueller Artikel bei golem:
http://www.golem.de/0802/57485.html
a.

[Michael H.W. Weber]

Ob die neuen ATI 3870 X2 Karten unter FAH voll ausgefahren werden können, ist zur Zeit unbekannt.

Michael.