Domain: ua.ac.be
Stories and comments across the archive that link to ua.ac.be.
Comments · 11
-
Re:Just ship with a low-draw driver
Or build it like the Fastra II, but using low-end GPUs. They crammed 13 GPUs into one system.
-
Re:Uhm AWS EC2 Cluster Compute
Why not build a Fastra 2 clone? 6000 EUR for 12TFlops.
-
UAntwerp's CS program
Here's UAntwerp's subjects for year ("deel") 1-3:
http://www.ua.ac.be/main.aspx?c=.OOD2011&n=94160
In Dutch, but 95% readable to English speakers. ("gegevens"=data, "uitbating"=operating, "inleiding"=introduction)
I'm studying law in Belgium and there's lots of general education subjects, but that makes sense for law.
-
Re:Desktop Apple ain't going anywhere
Your very post contradicts itself, it's a marvel.
First you say heavy computation is being pushed to GPU, allowing CPUs to be less powerful and less power-hungry, and then you write that now small, less powerful are becoming a lot more so and simultaneously more power-hungry.
The reality is that GPU programming is tough, specific and cannot replace general computing. Think of a GPU as becoming the FPU of yesteryear. Sure every processor is going to have one, sure it's going to be useful, but no it will not displace everything.
6-8 GPU computers have existed for a while now, since 4-way SLI with dual-GPU card : here is an example.
-
Lack of background, nuanceThe comment "It's a sad day for the freedom of scientific research", misses the complexity of the debate surrounding the inherently political balance between technological advances driven by private interest and the opinion and interest of the larger populace. A colleague a has published extensively and recently on this very subject, the debate and issue of GGO's in Belgium, these two publications, available from his homepage are highly recommended:
- Maeseele, P. (2011) On News Media and Democratic Debate: Framing Agricultural Biotechnology in Northern Belgium. International Communication Gazette 73 (1-2): 83-105.
- Maeseele, P. (2010) Science journalism and social debate on modernization risks. Interview by Filippo Bonaventura. Journal of Science Communication 9 (4): C02.
-
Re:Can someone explain this to me?
"unless something dramatic changes in factoring" Something like using ATI and NVIDIA GPU's to accelerate factoring? something dramatic like that? http://eecm.cr.yp.to/pc109-20090901.pdf If you take the latest in CPU/Multi GPU configurations; and build around the idea of operating them for this purpose, i think RSA-1024 could be cracked in a similar amount of time. Far less than 10 or 5 years. Their paper doesn't make any references at all to GPU accelerated factoring, it's not even on their radar. http://fastra2.ua.ac.be/
-
It really runs Linux
Nice try at humor. But as almost always with these types of multi-processor machines, it runs Linux.
-
Direct link to the project website
The main post does not contain a direct link to the project webpage: http://fastra.ua.ac.be/, which contains a lot more info and explanations.
-
Brick of GPUs
I love this picture: http://fastra.ua.ac.be/en/images.html
Between the massive brick of GPUs and the massive CPU heatsink/fan, you can't see the mobo at all. -
Re:Incomplete articleUniversity website
Dutch Fragment:
Zodra hij contact maakt met de prooi, doet de vis zijn bek herhaaldelijk open en dicht tot het insect stevig tussen zijn kaken vastgeklemd zit. De typische zuigbeweging van in het water komt ook op het land van pas, hier om grotere prooien gemakkelijker naar binnen te werken.
Quick translation:
Dit -voor een vis- merkwaardige gedrag kan licht werpen op de evolutie van water- naar landdier en op de ingrijpende lichamelijke aanpassingen die daarvoor nodig waren.
As soon it contacts the prey, the fish opens and closes its mouth repeatedly until the insect is locked fermly between its jaws. The typical suction-movement from in the water comes handy on the land, here to work bigger prey inside more easily.
This -for a fish- weird behaviour can shed light on the evolution from water- to landanimals and on the serious adjustments which were required for this.It sounds in the journal as they are able to feed on the land, with the help of their longer and flexible spine. So the movement of the head is required to feed on the land. (the article states "without it they'd just push their prey over the ground and it would be impossible to eat it.")
I'm just relaying what I read, I'm not an expert on fish nor evolutionary biology and I don't want to dispute one source and blindly trust another. It's fascinating nonetheless. -
Some links that might be useful
I did a little search on Google to look for the system my university uses in its library, and found an interesting listing.
However, it seems to contain only commercial software (the one the guys here use, Aleph, is the first in the list), but you may find some interesting things if you browse the links (I didn't take the time for that).
--
Marcelo Vanzin