<article>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#article09_12_16_2255259</id>
	<title>FASTRA II Puts 13 GPUs In a Desktop Supercomputer</title>
	<author>timothy</author>
	<datestamp>1260961620000</datestamp>
	<htmltext>An anonymous reader writes <i>"Last year tomography researchers of the ASTRA group at the University of Antwerp developed a desktop supercomputer <a href="http://tech.slashdot.org/story/08/05/31/1633214/Supercomputer-Built-With-8-GPUs">with four NVIDIA GeForce 9800 GX2 graphics cards</a>. The performance of the FASTRA GPGPU system was amazing; it was slightly faster than the university's 512-core supercomputer and cost less than 4000EUR. Today the researchers announce <a href="http://fastra2.ua.ac.be/">FASTRA II</a>, a new 6000EUR <a href="http://en.wikipedia.org/wiki/GPGPU">GPGPU</a> computing beast with six dual-GPU NVIDIA GeForce GTX 295 graphics cards and one GeForce GTX 275. The development of the new system was more complicated and there are still some stability issues, but tests reveal <a href="http://www.dvhardware.net/articles25\_fastra\_2\_desktop\_supercomputer.html">the 13 GPUs deliver 3.75x more performance</a> than the old system. For the tomography reconstruction calculations these researchers need to do, the compact FASTRA II is four times faster than the university's supercomputer cluster, while being roughly 300 times more energy efficient."</i></htmltext>
<tokenext>An anonymous reader writes " Last year tomography researchers of the ASTRA group at the University of Antwerp developed a desktop supercomputer with four NVIDIA GeForce 9800 GX2 graphics cards .
The performance of the FASTRA GPGPU system was amazing ; it was slightly faster than the university 's 512-core supercomputer and cost less than 4000EUR .
Today the researchers announce FASTRA II , a new 6000EUR GPGPU computing beast with six dual-GPU NVIDIA GeForce GTX 295 graphics cards and one GeForce GTX 275 .
The development of the new system was more complicated and there are still some stability issues , but tests reveal the 13 GPUs deliver 3.75x more performance than the old system .
For the tomography reconstruction calculations these researchers need to do , the compact FASTRA II is four times faster than the university 's supercomputer cluster , while being roughly 300 times more energy efficient .
"</tokentext>
<sentencetext>An anonymous reader writes "Last year tomography researchers of the ASTRA group at the University of Antwerp developed a desktop supercomputer with four NVIDIA GeForce 9800 GX2 graphics cards.
The performance of the FASTRA GPGPU system was amazing; it was slightly faster than the university's 512-core supercomputer and cost less than 4000EUR.
Today the researchers announce FASTRA II, a new 6000EUR GPGPU computing beast with six dual-GPU NVIDIA GeForce GTX 295 graphics cards and one GeForce GTX 275.
The development of the new system was more complicated and there are still some stability issues, but tests reveal the 13 GPUs deliver 3.75x more performance than the old system.
For the tomography reconstruction calculations these researchers need to do, the compact FASTRA II is four times faster than the university's supercomputer cluster, while being roughly 300 times more energy efficient.
"</sentencetext>
</article>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466390</id>
	<title>Re:Awesome</title>
	<author>sadness203</author>
	<datestamp>1259670540000</datestamp>
	<modclass>Funny</modclass>
	<modscore>4</modscore>
	<htmltext>Only if you imagine a beowolf cluster of these<br>
Here goes the redundant and offtopic mod.</htmltext>
<tokenext>Only if you imagine a beowolf cluster of these Here goes the redundant and offtopic mod .</tokentext>
<sentencetext>Only if you imagine a beowolf cluster of these
Here goes the redundant and offtopic mod.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466190</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466444</id>
	<title>Nigger Woods got athlete of the decade?</title>
	<author>Anonymous</author>
	<datestamp>1259670720000</datestamp>
	<modclass>Troll</modclass>
	<modscore>-1</modscore>
	<htmltext>You got to be shitting me.</htmltext>
<tokenext>You got to be shitting me .</tokentext>
<sentencetext>You got to be shitting me.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469290</id>
	<title>Re:times less</title>
	<author>timeOday</author>
	<datestamp>1259690520000</datestamp>
	<modclass>Insightful</modclass>
	<modscore>4</modscore>
	<htmltext>Can we please just officially define "n times less" as "1/n" and not feel bad about it anymore?</htmltext>
<tokenext>Can we please just officially define " n times less " as " 1/n " and not feel bad about it anymore ?</tokentext>
<sentencetext>Can we please just officially define "n times less" as "1/n" and not feel bad about it anymore?</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466510</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30472006</id>
	<title>I wants?</title>
	<author>ewersj</author>
	<datestamp>1261054920000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>My lab will soon be building a computer or cluster for bioinformatics. Would something like this be appropriate / scaleable for gene microarray analysis, clustering algorithm tasks, etc? We need the capability to work with datasets in the 400 GB range, and with many permutations, but the specific datapoints are not large. Any suggestions or input would be much appreciated...</htmltext>
<tokenext>My lab will soon be building a computer or cluster for bioinformatics .
Would something like this be appropriate / scaleable for gene microarray analysis , clustering algorithm tasks , etc ?
We need the capability to work with datasets in the 400 GB range , and with many permutations , but the specific datapoints are not large .
Any suggestions or input would be much appreciated.. .</tokentext>
<sentencetext>My lab will soon be building a computer or cluster for bioinformatics.
Would something like this be appropriate / scaleable for gene microarray analysis, clustering algorithm tasks, etc?
We need the capability to work with datasets in the 400 GB range, and with many permutations, but the specific datapoints are not large.
Any suggestions or input would be much appreciated...</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467638</id>
	<title>What the hell is up with the clothing?</title>
	<author>tyrione</author>
	<datestamp>1259677740000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>The Brady Bunch called they want their set clothes back!</htmltext>
<tokenext>The Brady Bunch called they want their set clothes back !</tokentext>
<sentencetext>The Brady Bunch called they want their set clothes back!</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30468968</id>
	<title>Cramped cases...</title>
	<author>Dusthead Jr.</author>
	<datestamp>1259688060000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>Maybe there's a really good reason for it that I'm not fully aware of, but why are PC cases, motherboards, add-on cards etc. all seen to be designed around such limited amounts of space? Is there a such thing a s PC case that size of a mini-fridge or bigger? A motherboard with freaking 10 or 12 slots with enough space between them? A video card the size of a motherboard? Anything but a cramped little box with limited expansion? Is that such a bizarre thing to want?</htmltext>
<tokenext>Maybe there 's a really good reason for it that I 'm not fully aware of , but why are PC cases , motherboards , add-on cards etc .
all seen to be designed around such limited amounts of space ?
Is there a such thing a s PC case that size of a mini-fridge or bigger ?
A motherboard with freaking 10 or 12 slots with enough space between them ?
A video card the size of a motherboard ?
Anything but a cramped little box with limited expansion ?
Is that such a bizarre thing to want ?</tokentext>
<sentencetext>Maybe there's a really good reason for it that I'm not fully aware of, but why are PC cases, motherboards, add-on cards etc.
all seen to be designed around such limited amounts of space?
Is there a such thing a s PC case that size of a mini-fridge or bigger?
A motherboard with freaking 10 or 12 slots with enough space between them?
A video card the size of a motherboard?
Anything but a cramped little box with limited expansion?
Is that such a bizarre thing to want?</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466972</id>
	<title>Can't be to impressed: Folding@home guys did more.</title>
	<author>blind biker</author>
	<datestamp>1259673540000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>Folding@home enthusiasts and academic contributors did more than that, and a long time ago, too. Just check <a href="http://foldingforum.org/viewtopic.php?f=38&amp;t=7902" title="foldingforum.org">this thread at foldingforums</a> [foldingforum.org] for one example.</p></htmltext>
<tokenext>Folding @ home enthusiasts and academic contributors did more than that , and a long time ago , too .
Just check this thread at foldingforums [ foldingforum.org ] for one example .</tokentext>
<sentencetext>Folding@home enthusiasts and academic contributors did more than that, and a long time ago, too.
Just check this thread at foldingforums [foldingforum.org] for one example.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30473474</id>
	<title>My Karma is too bad</title>
	<author>NaughtyNimitz</author>
	<datestamp>1261065960000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext>What the fuck is WRONG with you guys at Slashdot. I posted this on Tuesday and my submission get's turned down.

Is it because i am not Anglosaxon?

Whose **** do i need to suck?</htmltext>
<tokenext>What the fuck is WRONG with you guys at Slashdot .
I posted this on Tuesday and my submission get 's turned down .
Is it because i am not Anglosaxon ?
Whose * * * * do i need to suck ?</tokentext>
<sentencetext>What the fuck is WRONG with you guys at Slashdot.
I posted this on Tuesday and my submission get's turned down.
Is it because i am not Anglosaxon?
Whose **** do i need to suck?</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469840</id>
	<title>Re:Awesome</title>
	<author>Firehed</author>
	<datestamp>1259695080000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>And in Soviet Russia, 13 GPUs supercompute using you!</p><p>(Is that the smell of burning Karma?)</p></htmltext>
<tokenext>And in Soviet Russia , 13 GPUs supercompute using you !
( Is that the smell of burning Karma ?
)</tokentext>
<sentencetext>And in Soviet Russia, 13 GPUs supercompute using you!
(Is that the smell of burning Karma?
)</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466390</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30468096</id>
	<title>Re:Awesome</title>
	<author>TejWC</author>
	<datestamp>1259680500000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>Sadly it doesn't. Why? Because it appears to be running <a href="http://www.dvhardware.net/news/2009/fastra\_2/fastra\_ii\_desktop\_supercomputer.jpg" title="dvhardware.net">Linux</a> [dvhardware.net].</p></htmltext>
<tokenext>Sadly it does n't .
Why ? Because it appears to be running Linux [ dvhardware.net ] .</tokentext>
<sentencetext>Sadly it doesn't.
Why? Because it appears to be running Linux [dvhardware.net].</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466190</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467754</id>
	<title>Re:times less</title>
	<author>CityZen</author>
	<datestamp>1259678460000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>It makes perfect sense, given appropriate units, such as (1/watt)'s.   Okay, maybe not.</p></htmltext>
<tokenext>It makes perfect sense , given appropriate units , such as ( 1/watt ) 's .
Okay , maybe not .</tokentext>
<sentencetext>It makes perfect sense, given appropriate units, such as (1/watt)'s.
Okay, maybe not.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466510</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466822</id>
	<title>Re:Yeah but...</title>
	<author>Anonymous</author>
	<datestamp>1259672700000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>Does it run Linux?</p></htmltext>
<tokenext>Does it run Linux ?</tokentext>
<sentencetext>Does it run Linux?</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466644</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467690</id>
	<title>but does it run..</title>
	<author>Anonymous</author>
	<datestamp>1259678100000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>..hyper linux</p></htmltext>
<tokenext>..hyper linux</tokentext>
<sentencetext>..hyper linux</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466378</id>
	<title>Beef lover's night</title>
	<author>Anonymous</author>
	<datestamp>1259670480000</datestamp>
	<modclass>Offtopic</modclass>
	<modscore>-1</modscore>
	<htmltext><p>coed.jpg: WEB SITE SOUND EFFECTS BEYOND EXPECTATIONS<br>GIANT RJ-45 CONNECTORS WILL ASTOUND YOU<br>(see how they glisten and sparkle)<br>Vincent Mariani: Thank you for filling out the survey! Click here to<br>get $10 off any entree over $70 at Bennigan's!<br>coed.jpg: Ask your server for the Bennigan's Elite Club menu,<br>featuring the new Chicken Cordon Bleu Steak Sandwich, the Chicken<br>Cordon Bleu Sandwich made of 100\% all-beef steak!<br>Vincent Mariani: Now! When you spend over $700 at Bennigan's, you get<br>to join our Furniture Biter's Club! Earn the right to bite any piece<br>of furniture (glass excluded) at any Bennigan's in the continental US!<br>Offer void where prohibited by work-safety laws.<br>coed.jpg: For a limited time, kids bite free! Use coupon code 0xF1DE110<br>10:00 AM<br>Vincent Mariani: Tragically, the hexadecimal coupon code system proved<br>to be Bennigan's greatest strength, and it's greatest weakness. We'll<br>be back on Behind the Unremarkable US Casual Dining Chain-<br>coed.jpg: Please stand by, it may take a few seconds for your<br>commercial break to be submitted. Please DO NOT!!!!!!!! close this<br>window.<br>10:06 AM<br>Vincent Mariani: We should make a "bucket list" or unremarkable US<br>Casual Dining Chains in which to bone and then start a contest where<br>everyone competes to be first to bone in Bennigan's, Chili's, TGI<br>Friday's, Outback Steakhouse, etc.<br>coed.jpg:hmm<nobr> <wbr></nobr>... bennigan's, applebee's, golden corral, chili's<br>haha tgi friday's<br>i dunno, that could get depressing pretty quick!<br>Vincent Mariani: Yeah, that's the challenge<br>coed.jpg: haha<br>Vincent Mariani: can you get it up in a Golden Corral? Tough to say!<br>coed.jpg: it's okay honey, we can just hit the "salad bar" for some<br>fried chicken tacos with gravy and cheese and ranch dressing<br>oh shit, it's tuesday! that means salisbury steak! i might be getting<br>a boner after all<br>Vincent Mariani: That fellow from the commercials who looks like the<br>Hoff might be able to get a boner in Golden Corral<br>Achievement unlocked: Boner Corral<br>10:14 AM<br>coed.jpg:Go to the lettuce bowl at the end of the buffet and get the<br>silver tongs. Go to the other end of the buffet and turn around,<br>facing the roll warmer. hit X to use the tongs to get a roll, but jump<br>just before the roll goes into your pants. the roll should fly across<br>the buffet back to the salad bar. Go back to the lettuce bowl, and an<br>employee should approach you. hit X to talk. keep hitting X to<br>continue talking until she says "well, I gotta get back to work", then<br>hit square. golden corral buffet boning should commence in beautifully<br>rendered 3d polygons<br>10:18 AM<br>If you found the hidden the Golden Corral Team Member Polo and you<br>didn't wipe off the Jack Daniel's Rib Sauce from your chin on the TGI<br>Friday's level, you can skip the buffet and walk directly into the<br>kitchen. Adjust the radio station from Tejano to Smooth Jazz, and<br>Jorge will come out from the grill and start to yell at you. Answer<br>"yes, no, no." and he'll decide to bone you instead.<br>coed.jpg: achievement unlocked: beef lover's night</p></htmltext>
<tokenext>coed.jpg : WEB SITE SOUND EFFECTS BEYOND EXPECTATIONSGIANT RJ-45 CONNECTORS WILL ASTOUND YOU ( see how they glisten and sparkle ) Vincent Mariani : Thank you for filling out the survey !
Click here toget $ 10 off any entree over $ 70 at Bennigan 's ! coed.jpg : Ask your server for the Bennigan 's Elite Club menu,featuring the new Chicken Cordon Bleu Steak Sandwich , the ChickenCordon Bleu Sandwich made of 100 \ % all-beef steak ! Vincent Mariani : Now !
When you spend over $ 700 at Bennigan 's , you getto join our Furniture Biter 's Club !
Earn the right to bite any pieceof furniture ( glass excluded ) at any Bennigan 's in the continental US ! Offer void where prohibited by work-safety laws.coed.jpg : For a limited time , kids bite free !
Use coupon code 0xF1DE11010 : 00 AMVincent Mariani : Tragically , the hexadecimal coupon code system provedto be Bennigan 's greatest strength , and it 's greatest weakness .
We'llbe back on Behind the Unremarkable US Casual Dining Chain-coed.jpg : Please stand by , it may take a few seconds for yourcommercial break to be submitted .
Please DO NOT ! ! ! ! ! ! ! !
close thiswindow.10 : 06 AMVincent Mariani : We should make a " bucket list " or unremarkable USCasual Dining Chains in which to bone and then start a contest whereeveryone competes to be first to bone in Bennigan 's , Chili 's , TGIFriday 's , Outback Steakhouse , etc.coed.jpg : hmm ... bennigan 's , applebee 's , golden corral , chili'shaha tgi friday'si dunno , that could get depressing pretty quick ! Vincent Mariani : Yeah , that 's the challengecoed.jpg : hahaVincent Mariani : can you get it up in a Golden Corral ?
Tough to say ! coed.jpg : it 's okay honey , we can just hit the " salad bar " for somefried chicken tacos with gravy and cheese and ranch dressingoh shit , it 's tuesday !
that means salisbury steak !
i might be gettinga boner after allVincent Mariani : That fellow from the commercials who looks like theHoff might be able to get a boner in Golden CorralAchievement unlocked : Boner Corral10 : 14 AMcoed.jpg : Go to the lettuce bowl at the end of the buffet and get thesilver tongs .
Go to the other end of the buffet and turn around,facing the roll warmer .
hit X to use the tongs to get a roll , but jumpjust before the roll goes into your pants .
the roll should fly acrossthe buffet back to the salad bar .
Go back to the lettuce bowl , and anemployee should approach you .
hit X to talk .
keep hitting X tocontinue talking until she says " well , I got ta get back to work " , thenhit square .
golden corral buffet boning should commence in beautifullyrendered 3d polygons10 : 18 AMIf you found the hidden the Golden Corral Team Member Polo and youdid n't wipe off the Jack Daniel 's Rib Sauce from your chin on the TGIFriday 's level , you can skip the buffet and walk directly into thekitchen .
Adjust the radio station from Tejano to Smooth Jazz , andJorge will come out from the grill and start to yell at you .
Answer " yes , no , no .
" and he 'll decide to bone you instead.coed.jpg : achievement unlocked : beef lover 's night</tokentext>
<sentencetext>coed.jpg: WEB SITE SOUND EFFECTS BEYOND EXPECTATIONSGIANT RJ-45 CONNECTORS WILL ASTOUND YOU(see how they glisten and sparkle)Vincent Mariani: Thank you for filling out the survey!
Click here toget $10 off any entree over $70 at Bennigan's!coed.jpg: Ask your server for the Bennigan's Elite Club menu,featuring the new Chicken Cordon Bleu Steak Sandwich, the ChickenCordon Bleu Sandwich made of 100\% all-beef steak!Vincent Mariani: Now!
When you spend over $700 at Bennigan's, you getto join our Furniture Biter's Club!
Earn the right to bite any pieceof furniture (glass excluded) at any Bennigan's in the continental US!Offer void where prohibited by work-safety laws.coed.jpg: For a limited time, kids bite free!
Use coupon code 0xF1DE11010:00 AMVincent Mariani: Tragically, the hexadecimal coupon code system provedto be Bennigan's greatest strength, and it's greatest weakness.
We'llbe back on Behind the Unremarkable US Casual Dining Chain-coed.jpg: Please stand by, it may take a few seconds for yourcommercial break to be submitted.
Please DO NOT!!!!!!!!
close thiswindow.10:06 AMVincent Mariani: We should make a "bucket list" or unremarkable USCasual Dining Chains in which to bone and then start a contest whereeveryone competes to be first to bone in Bennigan's, Chili's, TGIFriday's, Outback Steakhouse, etc.coed.jpg:hmm ... bennigan's, applebee's, golden corral, chili'shaha tgi friday'si dunno, that could get depressing pretty quick!Vincent Mariani: Yeah, that's the challengecoed.jpg: hahaVincent Mariani: can you get it up in a Golden Corral?
Tough to say!coed.jpg: it's okay honey, we can just hit the "salad bar" for somefried chicken tacos with gravy and cheese and ranch dressingoh shit, it's tuesday!
that means salisbury steak!
i might be gettinga boner after allVincent Mariani: That fellow from the commercials who looks like theHoff might be able to get a boner in Golden CorralAchievement unlocked: Boner Corral10:14 AMcoed.jpg:Go to the lettuce bowl at the end of the buffet and get thesilver tongs.
Go to the other end of the buffet and turn around,facing the roll warmer.
hit X to use the tongs to get a roll, but jumpjust before the roll goes into your pants.
the roll should fly acrossthe buffet back to the salad bar.
Go back to the lettuce bowl, and anemployee should approach you.
hit X to talk.
keep hitting X tocontinue talking until she says "well, I gotta get back to work", thenhit square.
golden corral buffet boning should commence in beautifullyrendered 3d polygons10:18 AMIf you found the hidden the Golden Corral Team Member Polo and youdidn't wipe off the Jack Daniel's Rib Sauce from your chin on the TGIFriday's level, you can skip the buffet and walk directly into thekitchen.
Adjust the radio station from Tejano to Smooth Jazz, andJorge will come out from the grill and start to yell at you.
Answer"yes, no, no.
" and he'll decide to bone you instead.coed.jpg: achievement unlocked: beef lover's night</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466644</id>
	<title>Yeah but...</title>
	<author>Anonymous</author>
	<datestamp>1259671860000</datestamp>
	<modclass>Redundant</modclass>
	<modscore>0</modscore>
	<htmltext><p>Can it play Crysis with a high frame rate on maximum?</p></htmltext>
<tokenext>Can it play Crysis with a high frame rate on maximum ?</tokentext>
<sentencetext>Can it play Crysis with a high frame rate on maximum?</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466190</id>
	<title>Awesome</title>
	<author>enderjsv</author>
	<datestamp>1259669580000</datestamp>
	<modclass>Funny</modclass>
	<modscore>5</modscore>
	<htmltext>Almost meets the minimum requirements for Crysis 2</htmltext>
<tokenext>Almost meets the minimum requirements for Crysis 2</tokentext>
<sentencetext>Almost meets the minimum requirements for Crysis 2</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466624</id>
	<title>Not sure how fast it is, but I know it is hot...</title>
	<author>Anonymous</author>
	<datestamp>1259671800000</datestamp>
	<modclass>Interestin</modclass>
	<modscore>2</modscore>
	<htmltext><p>I've got a pair of 9800gx2 in my rig.  The cards turn room temperature air into ~46C air.  Without proper ventilation, these things will turn a chassis into an easy bake oven.</p><p>For those not familiar with the 9800gx2 cards, it essentially is two 8800gts video cards linked together to act as a single card - something called SLI on the NVidia side of marketing.  SLI typically required a mainboard/chipset that would allow you to plug in two cards and link them together.  This model allowed any mainboard to have two 'internal' cards linked together, with the option of linking another 9800gx2 if your board actually supported SLI.</p><p>The pictures did not show any SLI bridge, so it looks like they are just taking advantage of multiple GPUs per card.</p></htmltext>
<tokenext>I 've got a pair of 9800gx2 in my rig .
The cards turn room temperature air into ~ 46C air .
Without proper ventilation , these things will turn a chassis into an easy bake oven.For those not familiar with the 9800gx2 cards , it essentially is two 8800gts video cards linked together to act as a single card - something called SLI on the NVidia side of marketing .
SLI typically required a mainboard/chipset that would allow you to plug in two cards and link them together .
This model allowed any mainboard to have two 'internal ' cards linked together , with the option of linking another 9800gx2 if your board actually supported SLI.The pictures did not show any SLI bridge , so it looks like they are just taking advantage of multiple GPUs per card .</tokentext>
<sentencetext>I've got a pair of 9800gx2 in my rig.
The cards turn room temperature air into ~46C air.
Without proper ventilation, these things will turn a chassis into an easy bake oven.For those not familiar with the 9800gx2 cards, it essentially is two 8800gts video cards linked together to act as a single card - something called SLI on the NVidia side of marketing.
SLI typically required a mainboard/chipset that would allow you to plug in two cards and link them together.
This model allowed any mainboard to have two 'internal' cards linked together, with the option of linking another 9800gx2 if your board actually supported SLI.The pictures did not show any SLI bridge, so it looks like they are just taking advantage of multiple GPUs per card.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467786</id>
	<title>Generic statements FAIL!</title>
	<author>Hurricane78</author>
	<datestamp>1259678640000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p><div class="quote"><p>it was slightly faster than the university's 512-core supercomputer and cost less than 4000EUR.</p></div><p><div class="quote"><p>but tests reveal the 13 GPUs deliver 3.75x more performance than the old system.</p></div><p>It is impossible, to make such general statements about the performance, for something that is still very much specialized on long pipelines and streams of repetitive data (vector processing).</p><p>They may be much faster for tasks that fit that scheme. But slower for those that don&rsquo;t.</p></div>
	</htmltext>
<tokenext>it was slightly faster than the university 's 512-core supercomputer and cost less than 4000EUR.but tests reveal the 13 GPUs deliver 3.75x more performance than the old system.It is impossible , to make such general statements about the performance , for something that is still very much specialized on long pipelines and streams of repetitive data ( vector processing ) .They may be much faster for tasks that fit that scheme .
But slower for those that don    t .</tokentext>
<sentencetext>it was slightly faster than the university's 512-core supercomputer and cost less than 4000EUR.but tests reveal the 13 GPUs deliver 3.75x more performance than the old system.It is impossible, to make such general statements about the performance, for something that is still very much specialized on long pipelines and streams of repetitive data (vector processing).They may be much faster for tasks that fit that scheme.
But slower for those that don’t.
	</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466326</id>
	<title>That's nothing</title>
	<author>Anonymous</author>
	<datestamp>1259670240000</datestamp>
	<modclass>Offtopic</modclass>
	<modscore>-1</modscore>
	<htmltext><p>I can put 52 jellybeans in my mouth and sing "La Marseillaise."</p></htmltext>
<tokenext>I can put 52 jellybeans in my mouth and sing " La Marseillaise .
"</tokentext>
<sentencetext>I can put 52 jellybeans in my mouth and sing "La Marseillaise.
"</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467322</id>
	<title>Naming Scheme</title>
	<author>lymond01</author>
	<datestamp>1259675760000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>Wouldn't it be nice if the FASTRA II, which is 3.75 times faster than the FASTRA I, was actually called the FASTRA 375.  Then I wouldn't have to ask.</p></htmltext>
<tokenext>Would n't it be nice if the FASTRA II , which is 3.75 times faster than the FASTRA I , was actually called the FASTRA 375 .
Then I would n't have to ask .</tokentext>
<sentencetext>Wouldn't it be nice if the FASTRA II, which is 3.75 times faster than the FASTRA I, was actually called the FASTRA 375.
Then I wouldn't have to ask.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467826</id>
	<title>Why it's 13, not 14 GPUs</title>
	<author>CityZen</author>
	<datestamp>1259678940000</datestamp>
	<modclass>Interestin</modclass>
	<modscore>2</modscore>
	<htmltext><p>Apparently, the regular BIOS can't boot with more than 5? graphics cards installed due to the amount of resources (memory &amp; I/O space) that each one requires.  So the researchers asked ASUS to make a special BIOS for them which doesn't set up the graphics card resources.  However, the BIOS still needs to initialize at least one video card, so they agreed that the boot video card would be the one with only a single GPU.  Presumably, they could have also chosen a dual GPU card that happened to be different from the others in some way.</p></htmltext>
<tokenext>Apparently , the regular BIOS ca n't boot with more than 5 ?
graphics cards installed due to the amount of resources ( memory &amp; I/O space ) that each one requires .
So the researchers asked ASUS to make a special BIOS for them which does n't set up the graphics card resources .
However , the BIOS still needs to initialize at least one video card , so they agreed that the boot video card would be the one with only a single GPU .
Presumably , they could have also chosen a dual GPU card that happened to be different from the others in some way .</tokentext>
<sentencetext>Apparently, the regular BIOS can't boot with more than 5?
graphics cards installed due to the amount of resources (memory &amp; I/O space) that each one requires.
So the researchers asked ASUS to make a special BIOS for them which doesn't set up the graphics card resources.
However, the BIOS still needs to initialize at least one video card, so they agreed that the boot video card would be the one with only a single GPU.
Presumably, they could have also chosen a dual GPU card that happened to be different from the others in some way.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466510</id>
	<title>times less</title>
	<author>Tubal-Cain</author>
	<datestamp>1259671020000</datestamp>
	<modclass>Funny</modclass>
	<modscore>4</modscore>
	<htmltext><p>...consuming 300 times less power.</p><p>*sigh*</p></htmltext>
<tokenext>...consuming 300 times less power .
* sigh *</tokentext>
<sentencetext>...consuming 300 times less power.
*sigh*</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466474</id>
	<title>Swordfish</title>
	<author>Anonymous</author>
	<datestamp>1259670900000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>Why does the computer from <a href="http://www.toplessrobot.com/john\_travolta\_hugh\_jackman\_halle\_berry\_swordfish\_001.jpg" title="toplessrobot.com" rel="nofollow">Swordfish</a> [toplessrobot.com]? <br> <br> <a href="http://www.geekonwheels.com/images/Image/swordfish.jpg" title="geekonwheels.com" rel="nofollow">Get Animated</a> [geekonwheels.com] <br>*Drools*</htmltext>
<tokenext>Why does the computer from Swordfish [ toplessrobot.com ] ?
Get Animated [ geekonwheels.com ] * Drools *</tokentext>
<sentencetext>Why does the computer from Swordfish [toplessrobot.com]?
Get Animated [geekonwheels.com] *Drools*</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30472944</id>
	<title>Would be nice if it was finished</title>
	<author>kegon</author>
	<datestamp>1261063440000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>Would be nice if it actually worked. It's not much good having the fastest desktop computer in the world if it isn't stable. Or are they using the Dilbert definition of a PC upgrade ?<br>
<br>
Next time, make the fancy video when it's finished guys.</htmltext>
<tokenext>Would be nice if it actually worked .
It 's not much good having the fastest desktop computer in the world if it is n't stable .
Or are they using the Dilbert definition of a PC upgrade ?
Next time , make the fancy video when it 's finished guys .</tokentext>
<sentencetext>Would be nice if it actually worked.
It's not much good having the fastest desktop computer in the world if it isn't stable.
Or are they using the Dilbert definition of a PC upgrade ?
Next time, make the fancy video when it's finished guys.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469304</id>
	<title>Re:Cramped cases...</title>
	<author>CityZen</author>
	<datestamp>1259690640000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>Oh, and by the way, I'm wondering quite the opposite: why do we still see so many over-sized full ATX size cases being offered, when microATX motherboards have everything we (most of us) need?  Indeed, even mini-ITX motherboards are often adequate for so many needs, and yet mini-ITX cases still seem to command a premium because they are relatively rare.  It's easy (and boring) to design a big rectangular ATX box.  It's an engineering challenge to make a good-looking small box that does everything you need and is still practical to work with.</p></htmltext>
<tokenext>Oh , and by the way , I 'm wondering quite the opposite : why do we still see so many over-sized full ATX size cases being offered , when microATX motherboards have everything we ( most of us ) need ?
Indeed , even mini-ITX motherboards are often adequate for so many needs , and yet mini-ITX cases still seem to command a premium because they are relatively rare .
It 's easy ( and boring ) to design a big rectangular ATX box .
It 's an engineering challenge to make a good-looking small box that does everything you need and is still practical to work with .</tokentext>
<sentencetext>Oh, and by the way, I'm wondering quite the opposite: why do we still see so many over-sized full ATX size cases being offered, when microATX motherboards have everything we (most of us) need?
Indeed, even mini-ITX motherboards are often adequate for so many needs, and yet mini-ITX cases still seem to command a premium because they are relatively rare.
It's easy (and boring) to design a big rectangular ATX box.
It's an engineering challenge to make a good-looking small box that does everything you need and is still practical to work with.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30468968</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466160</id>
	<title>Easy money to be made?</title>
	<author>Darkness404</author>
	<datestamp>1259669460000</datestamp>
	<modclass>Redundant</modclass>
	<modscore>0</modscore>
	<htmltext>It sounds like there might be easy money to be made buying these components, putting them in a computer case and then reselling them for profit at various universities. Just wait for the "Dell" of supercomputers.</htmltext>
<tokenext>It sounds like there might be easy money to be made buying these components , putting them in a computer case and then reselling them for profit at various universities .
Just wait for the " Dell " of supercomputers .</tokentext>
<sentencetext>It sounds like there might be easy money to be made buying these components, putting them in a computer case and then reselling them for profit at various universities.
Just wait for the "Dell" of supercomputers.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30503700</id>
	<title>Re:Silly</title>
	<author>drinkypoo</author>
	<datestamp>1261321800000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p><div class="quote"><p>There are two major reasons... the first is they use GeForce cards. That's not a good idea, since GeForces are held to much lower quality standards than Teslas and Quadros.</p></div><p>Tell that to the Quadro FX1500M that was in my HP/Compaq "professional workstation" laptop, that had a well-known die bonding problem that caused overheat failures across an entire production line. Neither HP nor nVidia recalled the defective parts and I ended up spending literally <em>days</em> on the phone with HP support before they sent me a new laptop. Higher quality, <em>my ass</em>. Quadro chips are marked differently, period the end.</p></div>
	</htmltext>
<tokenext>There are two major reasons... the first is they use GeForce cards .
That 's not a good idea , since GeForces are held to much lower quality standards than Teslas and Quadros.Tell that to the Quadro FX1500M that was in my HP/Compaq " professional workstation " laptop , that had a well-known die bonding problem that caused overheat failures across an entire production line .
Neither HP nor nVidia recalled the defective parts and I ended up spending literally days on the phone with HP support before they sent me a new laptop .
Higher quality , my ass .
Quadro chips are marked differently , period the end .</tokentext>
<sentencetext>There are two major reasons... the first is they use GeForce cards.
That's not a good idea, since GeForces are held to much lower quality standards than Teslas and Quadros.Tell that to the Quadro FX1500M that was in my HP/Compaq "professional workstation" laptop, that had a well-known die bonding problem that caused overheat failures across an entire production line.
Neither HP nor nVidia recalled the defective parts and I ended up spending literally days on the phone with HP support before they sent me a new laptop.
Higher quality, my ass.
Quadro chips are marked differently, period the end.
	</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466902</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469458</id>
	<title>It really runs Linux</title>
	<author>Anonymous</author>
	<datestamp>1259692020000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext>Nice try at humor. But as almost always with these types of multi-processor machines, it runs <a href="http://fastra2.ua.ac.be/?page\_id=55#custombios" title="ua.ac.be" rel="nofollow">Linux</a> [ua.ac.be].</htmltext>
<tokenext>Nice try at humor .
But as almost always with these types of multi-processor machines , it runs Linux [ ua.ac.be ] .</tokentext>
<sentencetext>Nice try at humor.
But as almost always with these types of multi-processor machines, it runs Linux [ua.ac.be].</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466392</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466902</id>
	<title>Silly</title>
	<author>jpmorgan</author>
	<datestamp>1259673180000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>This isn't a huge achievement. Nobody else has done it because it's silly.</p><p>There are two major reasons... the first is they use GeForce cards. That's not a good idea, since GeForces are held to much lower quality standards than Teslas and Quadros. They're intended for gaming graphics, where a minor error here or there isn't the end of the world. "Sorry we missed your cancer, since our supercomputer miscalculated that region of the reconstruction." The second problem is, that's one bandwidth starved machine. It's based on a pretty nice motherboard, but with 13 GPUs that's not a lot of bandwidth to go around.</p><p>The more popular layout for a GPU supercomputer of that size is a small cluster of 2-GPU blades, with a hypertransport interconnect. It's a little bit trickier to work with, but there are fewer bottlenecks.</p></htmltext>
<tokenext>This is n't a huge achievement .
Nobody else has done it because it 's silly.There are two major reasons... the first is they use GeForce cards .
That 's not a good idea , since GeForces are held to much lower quality standards than Teslas and Quadros .
They 're intended for gaming graphics , where a minor error here or there is n't the end of the world .
" Sorry we missed your cancer , since our supercomputer miscalculated that region of the reconstruction .
" The second problem is , that 's one bandwidth starved machine .
It 's based on a pretty nice motherboard , but with 13 GPUs that 's not a lot of bandwidth to go around.The more popular layout for a GPU supercomputer of that size is a small cluster of 2-GPU blades , with a hypertransport interconnect .
It 's a little bit trickier to work with , but there are fewer bottlenecks .</tokentext>
<sentencetext>This isn't a huge achievement.
Nobody else has done it because it's silly.There are two major reasons... the first is they use GeForce cards.
That's not a good idea, since GeForces are held to much lower quality standards than Teslas and Quadros.
They're intended for gaming graphics, where a minor error here or there isn't the end of the world.
"Sorry we missed your cancer, since our supercomputer miscalculated that region of the reconstruction.
" The second problem is, that's one bandwidth starved machine.
It's based on a pretty nice motherboard, but with 13 GPUs that's not a lot of bandwidth to go around.The more popular layout for a GPU supercomputer of that size is a small cluster of 2-GPU blades, with a hypertransport interconnect.
It's a little bit trickier to work with, but there are fewer bottlenecks.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30477372</id>
	<title>Re:GPU accuracy</title>
	<author>LeadSongDog</author>
	<datestamp>1261081440000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>Sounds great, but where can I buy a matching 4000 Euro MRI machine to go with it? Seriously, spending less than 1\% of the system price on processing power for the images is daft, especially when in most cases the bottleneck in getting patients in and out is the limited supply of radiologists. These guys need to think a little more deeply about their architecture.</htmltext>
<tokenext>Sounds great , but where can I buy a matching 4000 Euro MRI machine to go with it ?
Seriously , spending less than 1 \ % of the system price on processing power for the images is daft , especially when in most cases the bottleneck in getting patients in and out is the limited supply of radiologists .
These guys need to think a little more deeply about their architecture .</tokentext>
<sentencetext>Sounds great, but where can I buy a matching 4000 Euro MRI machine to go with it?
Seriously, spending less than 1\% of the system price on processing power for the images is daft, especially when in most cases the bottleneck in getting patients in and out is the limited supply of radiologists.
These guys need to think a little more deeply about their architecture.</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466752</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30481490</id>
	<title>Re:times less</title>
	<author>Nalgas D. Lemur</author>
	<datestamp>1261055520000</datestamp>
	<modclass>Funny</modclass>
	<modscore>2</modscore>
	<htmltext><p><nobr> <wbr></nobr></p><div class="quote"><p>...consuming 300 times less power.

*sigh*</p></div><p>Oops.  Sorry.  300 times <em>fewer</em>.</p></div>
	</htmltext>
<tokenext>...consuming 300 times less power .
* sigh * Oops. Sorry .
300 times fewer .</tokentext>
<sentencetext> ...consuming 300 times less power.
*sigh*Oops.  Sorry.
300 times fewer.
	</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466510</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469554</id>
	<title>Re:Cramped cases...</title>
	<author>CityZen</author>
	<datestamp>1259692680000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext><p>Oh, and here's your mini-fridge size case with 10 slots:</p><p><a href="http://www.mountainmods.com/computer-cases-c-21.html" title="mountainmods.com" rel="nofollow">http://www.mountainmods.com/computer-cases-c-21.html</a> [mountainmods.com]</p></htmltext>
<tokenext>Oh , and here 's your mini-fridge size case with 10 slots : http : //www.mountainmods.com/computer-cases-c-21.html [ mountainmods.com ]</tokentext>
<sentencetext>Oh, and here's your mini-fridge size case with 10 slots:http://www.mountainmods.com/computer-cases-c-21.html [mountainmods.com]</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30468968</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30468990</id>
	<title>Re:Not sure how fast it is, but I know it is hot..</title>
	<author>Anonymous</author>
	<datestamp>1259688240000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>I don't think anyone on<nobr> <wbr></nobr>/. actually "leaves" their computer...</p></htmltext>
<tokenext>I do n't think anyone on / .
actually " leaves " their computer.. .</tokentext>
<sentencetext>I don't think anyone on /.
actually "leaves" their computer...</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467572</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467572</id>
	<title>Re:Not sure how fast it is, but I know it is hot..</title>
	<author>thedarknite</author>
	<datestamp>1259677260000</datestamp>
	<modclass>Funny</modclass>
	<modscore>2</modscore>
	<htmltext><blockquote><div><p>I've got a pair of 9800gx2 in my rig. The cards turn room temperature air into ~46C air. Without proper ventilation, these things will turn a chassis into an easy bake oven.</p></div></blockquote><p>

That's a brilliant idea, now people can make snacks without ever leaving the computer.</p></div>
	</htmltext>
<tokenext>I 've got a pair of 9800gx2 in my rig .
The cards turn room temperature air into ~ 46C air .
Without proper ventilation , these things will turn a chassis into an easy bake oven .
That 's a brilliant idea , now people can make snacks without ever leaving the computer .</tokentext>
<sentencetext>I've got a pair of 9800gx2 in my rig.
The cards turn room temperature air into ~46C air.
Without proper ventilation, these things will turn a chassis into an easy bake oven.
That's a brilliant idea, now people can make snacks without ever leaving the computer.
	</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466624</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30470106</id>
	<title>Re:Not sure how fast it is, but I know it is hot..</title>
	<author>Anonymous</author>
	<datestamp>1259697360000</datestamp>
	<modclass>None</modclass>
	<modscore>0</modscore>
	<htmltext><p>I also have two GX2s in a box for use with CUDA programming.  (You don't use SLI with CUDA, in fact it's a disadvantage in that if you do you'll only be able to actually use one of the GPUs, so you won't see SLI bridges in a CUDA box.)  The power consumption of the 9800gx2s is indeed fearsome even at idle.  I measured it, but don't have the numbers on hand.  BUT: Newer nvidia cards apparently use *much* less power at idle, and probably less at full blast as well (like a 45nm CPU vs. a 90nm CPU at the same GHz will use less power for the exact same work).</p><p>Since I only need one GX2 to test most programs, I keep the power unplugged to the second one most of the time to keep from wasting so much energy (and producing so much heat).</p></htmltext>
<tokenext>I also have two GX2s in a box for use with CUDA programming .
( You do n't use SLI with CUDA , in fact it 's a disadvantage in that if you do you 'll only be able to actually use one of the GPUs , so you wo n't see SLI bridges in a CUDA box .
) The power consumption of the 9800gx2s is indeed fearsome even at idle .
I measured it , but do n't have the numbers on hand .
BUT : Newer nvidia cards apparently use * much * less power at idle , and probably less at full blast as well ( like a 45nm CPU vs. a 90nm CPU at the same GHz will use less power for the exact same work ) .Since I only need one GX2 to test most programs , I keep the power unplugged to the second one most of the time to keep from wasting so much energy ( and producing so much heat ) .</tokentext>
<sentencetext>I also have two GX2s in a box for use with CUDA programming.
(You don't use SLI with CUDA, in fact it's a disadvantage in that if you do you'll only be able to actually use one of the GPUs, so you won't see SLI bridges in a CUDA box.
)  The power consumption of the 9800gx2s is indeed fearsome even at idle.
I measured it, but don't have the numbers on hand.
BUT: Newer nvidia cards apparently use *much* less power at idle, and probably less at full blast as well (like a 45nm CPU vs. a 90nm CPU at the same GHz will use less power for the exact same work).Since I only need one GX2 to test most programs, I keep the power unplugged to the second one most of the time to keep from wasting so much energy (and producing so much heat).</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466624</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466752</id>
	<title>Re:GPU accuracy</title>
	<author>Beardo the Bearded</author>
	<datestamp>1259672400000</datestamp>
	<modclass>Interestin</modclass>
	<modscore>3</modscore>
	<htmltext><p>First, a gaming card is going to get fast firmware. A workstation card is going to get accurate firmware. I imagine that supercomputer cards would get specialized firmware. (I only skimmed the summary.)</p><p>GPUs are excellent at solving certain types of problems and excel at solving matrices. (That's what your video card is doing while it's rendering.) The best part of that is that most, if not all, mathematical problems can be expressed as a matrix, meaning that your super-fast GPU can solve most math problems super-fast.</p><p>Next, GPUs love working together since they don't care about what the OS is doing. All they do is take raw data and respond with an answer. Usually we're putting that answer onto the display, since otherwise wtf are we doing with a GPU? In this case, the results are returned instead of using the flashy display. So what you end up with is a set of really fast, specialized, parallel engines solving broken down matrices.</p><p>They're also not subject to the marketing whims of Moore's Law, so you can often get faster cards sooner than faster CPUs. To break down a supercomputer so that you get this kind of performance for 4000 EURO is a fantastic achievement. It's almost, but not quite, hobby range. (I'd still put money on someone trying to evolve this into a gaming rig...)</p></htmltext>
<tokenext>First , a gaming card is going to get fast firmware .
A workstation card is going to get accurate firmware .
I imagine that supercomputer cards would get specialized firmware .
( I only skimmed the summary .
) GPUs are excellent at solving certain types of problems and excel at solving matrices .
( That 's what your video card is doing while it 's rendering .
) The best part of that is that most , if not all , mathematical problems can be expressed as a matrix , meaning that your super-fast GPU can solve most math problems super-fast.Next , GPUs love working together since they do n't care about what the OS is doing .
All they do is take raw data and respond with an answer .
Usually we 're putting that answer onto the display , since otherwise wtf are we doing with a GPU ?
In this case , the results are returned instead of using the flashy display .
So what you end up with is a set of really fast , specialized , parallel engines solving broken down matrices.They 're also not subject to the marketing whims of Moore 's Law , so you can often get faster cards sooner than faster CPUs .
To break down a supercomputer so that you get this kind of performance for 4000 EURO is a fantastic achievement .
It 's almost , but not quite , hobby range .
( I 'd still put money on someone trying to evolve this into a gaming rig... )</tokentext>
<sentencetext>First, a gaming card is going to get fast firmware.
A workstation card is going to get accurate firmware.
I imagine that supercomputer cards would get specialized firmware.
(I only skimmed the summary.
)GPUs are excellent at solving certain types of problems and excel at solving matrices.
(That's what your video card is doing while it's rendering.
) The best part of that is that most, if not all, mathematical problems can be expressed as a matrix, meaning that your super-fast GPU can solve most math problems super-fast.Next, GPUs love working together since they don't care about what the OS is doing.
All they do is take raw data and respond with an answer.
Usually we're putting that answer onto the display, since otherwise wtf are we doing with a GPU?
In this case, the results are returned instead of using the flashy display.
So what you end up with is a set of really fast, specialized, parallel engines solving broken down matrices.They're also not subject to the marketing whims of Moore's Law, so you can often get faster cards sooner than faster CPUs.
To break down a supercomputer so that you get this kind of performance for 4000 EURO is a fantastic achievement.
It's almost, but not quite, hobby range.
(I'd still put money on someone trying to evolve this into a gaming rig...)</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466494</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466742</id>
	<title>Stability problem solved...</title>
	<author>gsgriffin</author>
	<datestamp>1259672340000</datestamp>
	<modclass>Funny</modclass>
	<modscore>2</modscore>
	<htmltext>Duh!  Look at the number of GPU's...13...try 12 or 14 and your luck will change.</htmltext>
<tokenext>Duh !
Look at the number of GPU 's...13...try 12 or 14 and your luck will change .</tokentext>
<sentencetext>Duh!
Look at the number of GPU's...13...try 12 or 14 and your luck will change.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467706</id>
	<title>Re:Silly</title>
	<author>CityZen</author>
	<datestamp>1259678160000</datestamp>
	<modclass>Insightful</modclass>
	<modscore>2</modscore>
	<htmltext><p>It's not silly:  (1) this is a research project, not production medical equipment, meaning that the funds to buy Tesla cards were probably not available, and they aren't particularly worried about occasional bit errors.  (2) Their particular application doesn't need much inter-GPU communication, if any, so that bandwidth is not an issue.  They just need for each GPU to load datasets, chew on them, and spit out the results.</p><p>How much does your proposed GPU supercomputer cost for 13 GPUs?</p></htmltext>
<tokenext>It 's not silly : ( 1 ) this is a research project , not production medical equipment , meaning that the funds to buy Tesla cards were probably not available , and they are n't particularly worried about occasional bit errors .
( 2 ) Their particular application does n't need much inter-GPU communication , if any , so that bandwidth is not an issue .
They just need for each GPU to load datasets , chew on them , and spit out the results.How much does your proposed GPU supercomputer cost for 13 GPUs ?</tokentext>
<sentencetext>It's not silly:  (1) this is a research project, not production medical equipment, meaning that the funds to buy Tesla cards were probably not available, and they aren't particularly worried about occasional bit errors.
(2) Their particular application doesn't need much inter-GPU communication, if any, so that bandwidth is not an issue.
They just need for each GPU to load datasets, chew on them, and spit out the results.How much does your proposed GPU supercomputer cost for 13 GPUs?</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466902</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466392</id>
	<title>News Flash</title>
	<author>RandomUsr</author>
	<datestamp>1259670540000</datestamp>
	<modclass>Funny</modclass>
	<modscore>2</modscore>
	<htmltext>Blazing Fast Pron Machine running Windows Vista. Don't forget to pick a copy of the latest memory intensive Anti-Virus, as this machine will handle it just fine.</htmltext>
<tokenext>Blazing Fast Pron Machine running Windows Vista .
Do n't forget to pick a copy of the latest memory intensive Anti-Virus , as this machine will handle it just fine .</tokentext>
<sentencetext>Blazing Fast Pron Machine running Windows Vista.
Don't forget to pick a copy of the latest memory intensive Anti-Virus, as this machine will handle it just fine.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466494</id>
	<title>GPU accuracy</title>
	<author>tbischel</author>
	<datestamp>1259670960000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>It used to be that GPUs would sacrifice accuracy for speed in floating point calculations, making them unsuitable for scientific computing.  Is this still the case?</htmltext>
<tokenext>It used to be that GPUs would sacrifice accuracy for speed in floating point calculations , making them unsuitable for scientific computing .
Is this still the case ?</tokentext>
<sentencetext>It used to be that GPUs would sacrifice accuracy for speed in floating point calculations, making them unsuitable for scientific computing.
Is this still the case?</sentencetext>
	<parent>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466160</parent>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466422</id>
	<title>How fast is this really?</title>
	<author>Ziekheid</author>
	<datestamp>1259670660000</datestamp>
	<modclass>Insightful</modclass>
	<modscore>3</modscore>
	<htmltext>"the compact FASTRA II is four times faster than the university's supercomputer cluster, while consuming 300 times less power"

And the original supercomputer was how fast? 512 cores doesn't say THAT much.
I could compare my computer to supercomputers from the past and they'd say the performance of my system was amazing too.</htmltext>
<tokenext>" the compact FASTRA II is four times faster than the university 's supercomputer cluster , while consuming 300 times less power " And the original supercomputer was how fast ?
512 cores does n't say THAT much .
I could compare my computer to supercomputers from the past and they 'd say the performance of my system was amazing too .</tokentext>
<sentencetext>"the compact FASTRA II is four times faster than the university's supercomputer cluster, while consuming 300 times less power"

And the original supercomputer was how fast?
512 cores doesn't say THAT much.
I could compare my computer to supercomputers from the past and they'd say the performance of my system was amazing too.</sentencetext>
</comment>
<comment>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466796</id>
	<title>lol</title>
	<author>MacGyver2210</author>
	<datestamp>1259672580000</datestamp>
	<modclass>None</modclass>
	<modscore>1</modscore>
	<htmltext>The guy in the video on that page looks exactly like the stereotype of the guy I'd expect to do this sort of thing.</htmltext>
<tokenext>The guy in the video on that page looks exactly like the stereotype of the guy I 'd expect to do this sort of thing .</tokentext>
<sentencetext>The guy in the video on that page looks exactly like the stereotype of the guy I'd expect to do this sort of thing.</sentencetext>
</comment>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_4</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467754
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466510
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_8</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30468096
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466190
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_12</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30468990
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467572
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466624
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_10</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469458
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466392
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_1</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30503700
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466902
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_13</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469304
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30468968
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_5</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30481490
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466510
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_9</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30470106
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466624
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_11</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469840
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466390
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466190
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_3</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466822
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466644
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_2</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469554
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30468968
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_7</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467706
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466902
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_6</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469290
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466510
</commentlist>
</thread>
<thread>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#thread_09_12_16_2255259_0</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30477372
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466752
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466494
http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466160
</commentlist>
</thread>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.9</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30473474
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.7</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466326
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.1</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466742
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.8</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467322
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.5</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466474
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.6</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466644
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466822
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.3</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466902
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467706
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30503700
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.12</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466510
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30481490
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467754
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469290
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.0</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466972
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.10</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466624
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30470106
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467572
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30468990
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.13</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466422
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.4</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466190
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30468096
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466390
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469840
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.14</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466160
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466494
--http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466752
---http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30477372
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.11</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30467786
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.2</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30468968
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469304
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469554
</commentlist>
</conversation>
<conversation>
	<id>http://www.semanticweb.org/ontologies/ConversationInstances.owl#conversation09_12_16_2255259.15</id>
	<commentlist>http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30466392
-http://www.semanticweb.org/ontologies/ConversationInstances.owl#comment09_12_16_2255259.30469458
</commentlist>
</conversation>
