Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

NVIDIA's $10K Tesla GPU-Based Personal Supercomputer

timothy posted more than 5 years ago | from the plugs-into-standard-power-strip dept.

Supercomputing 236

gupg writes "NVIDIA announced a new category of supercomputers — the Tesla Personal Supercomputer — a 4 TeraFLOPS desktop for under $10,000. This desktop machine has 4 of the Tesla C1060 computing processors. These GPUs have no graphics out and are used only for computing. Each Tesla GPU has 240 cores and delivers about 1 TeraFLOPS single precision and about 80 GigaFLOPS double-precision floating point performance. The CPU + GPU is programmed using C with added keywords using a parallel programming model called CUDA. The CUDA C compiler/development toolchain is free to download. There are tons of applications ported to CUDA including Mathematica, LabView, ANSYS Mechanical, and tons of scientific codes from molecular dynamics, quantum chemistry, and electromagnetics; they're listed on CUDA Zone."

Sorry! There are no comments related to the filter you selected.

But who needs all that power? (-1, Flamebait)

Anonymous Coward | more than 5 years ago | (#25863345)

"Most people use computers for web and email! Who needs all that power?"

I DO, NIGGA!

Ooooooo! Ahhhh! (1)

itsybitsy (149808) | more than 5 years ago | (#25863361)

Sweet. I got myself a tesla board... now what the heck to do with it... no kidding... I got one of these beasties... any suggestions?

Re:Ooooooo! Ahhhh! (2, Interesting)

Surreal Puppet (1408635) | more than 5 years ago | (#25863383)

Port john the ripper/aircrack-ng? Buy a few terabyte drives and start generating hash tables?

FTFL (2, Informative)

mangu (126918) | more than 5 years ago | (#25863659)

now what the heck to do with it...

All you need to do is follow the fscking link [nvidia.com] . Plenty of examples there.

Re: Is that all you got? (1)

itsybitsy (149808) | more than 5 years ago | (#25863981)

wow, as if I didn't do that before plunking down the money for the darn card...

I was asking for innovative ideas... not their existing boring ones...

So, who's got some cool ideas of what to do with Tesla?

Re: Is that all you got? (0)

Anonymous Coward | more than 5 years ago | (#25864319)

how about go outside and grow up...

Re:FTFL (1, Funny)

Anonymous Coward | more than 5 years ago | (#25864061)

Now why haven't they developed anything on it which has use for the common Jack like me. There were practically NO examples of it's applications in watching porn!

Penguins' Got One Liquid Cooled! (1)

Koensayr (136309) | more than 5 years ago | (#25863369)

Perhaps the coolest Personal Super Computer was the one shown by the good folks at Penguin Computing. It was rumored to be over-clocked and featured liquid cooling for silent operation!

http://www.penguincomputing.com/products/linux/workstations

Weird options (3, Insightful)

mangu (126918) | more than 5 years ago | (#25863691)

I went to the site and tried to configure one. The disk partition options are: "General Purpose, Internet Server, Developer's Workstation, File Server". I wonder, who needs three Tesla cards in a file server or an internet server?

Re:Weird options (0)

Anonymous Coward | more than 5 years ago | (#25863889)

Drawball.com?

Re:Penguins' Got One Liquid Cooled! (2, Informative)

BOFHelsinki (709551) | more than 5 years ago | (#25864053)

BTW, TFS makes a mistake calling this Tesla rig a supercomputer. Nvidia correctly just calls it a cluster replacement. A cluster is not a supercomputer, the interconnect makes all the difference, no matter how much FP crunching power there is. See NEC NX-9 or Cray's Seastar for a real supercomputer interconnect. Can't be arsed to check (this is Slashdot after all) but that Penguin Computing system likely has only InfiniBand or 10GbE for the switch network, making it "only" a cluster. :-)

Graphics (5, Funny)

Anonymous Coward | more than 5 years ago | (#25863373)

Wow, that's some serious computing power! I wonder if anyone has thought of using these for graphics or rendering? I imagine they could make some killer games, especially with advanced technology like Direct 3D.

Re:Graphics (2, Funny)

GigaplexNZ (1233886) | more than 5 years ago | (#25863581)

I wonder if anyone has thought of using these for graphics or rendering?

These are effectively just NVIDIA GT280 chips with the ports removed. Their heritage is gaming.

I imagine they could make some killer games

If you can find some way to get the video out to a monitor... but then you effectively just have Quad SLI GT280.

especially with advanced technology like Direct 3D

Uh... what? Direct 3D has been commonly used for years, you make it sound like some new and exotic technology. It is also effectively Windows only, whereas this hardware is more likely to use something like Linux.

Re:Graphics (4, Funny)

404 Clue Not Found (763556) | more than 5 years ago | (#25863591)

Whoosh. Sorry.

Re:Graphics (-1, Flamebait)

Anonymous Coward | more than 5 years ago | (#25863675)

as apposed to opengl, which no one uses because it's shit.

Re:Graphics (4, Funny)

Gnavpot (708731) | more than 5 years ago | (#25863697)

"I wonder if anyone has thought of using these for graphics or rendering?"

These are effectively just NVIDIA GT280 chips with the ports removed. Their heritage is gaming.

We need a "+1 Whoosh" moderation option.

No, I do not mean "-1 Whoosh". I want to see those embarrassingly stupid postings. But perhaps this moderation option should subtract karma.

Re:Graphics (4, Funny)

GigaplexNZ (1233886) | more than 5 years ago | (#25863909)

I suppose I'm one of those guys now. Hook, line and sinker.

Re:Graphics (1)

Provocateur (133110) | more than 5 years ago | (#25863757)

If you can find some way to get the video out to a monitor

Yup, time to break out those ol' CGA monitors out from the garage...knew they'd come in handy again one day, and with Linux' oh-so-retro CLI mode, I'm set!

Re:Graphics (2, Informative)

evilbessie (873633) | more than 5 years ago | (#25863985)

In much the same way that the current Quadro FX cards are based on the same chip as the gaming gforce cards. But still the most expensive gaming card is ~£400, but you'll pay ~£1500 for the top of the line FX5700.

It's because workstation graphics cards are configured for accuracy above all else, where as gaming cards are configured for speed. Having a few pixels being wrong does not affect gaming at all, getting the numbers wrong in simulations is going to cause problems.

Mostly the people who use these cards care about OpenGL support, but some people do use them under Windows and DirectX.

This type of computing came in with the gforce 8 range when CUDA (Computer Unified Device Architecture) brought C programming to the massively parallel graphics chips. Which has allowed nVidia to port the Ageia PhysX technology to the gforce cards so a separate addin card is not necessary.

I believe that ATi are doing something similar with their FireGL cards, which again are based on the same chip as their Radeon cards. This is why they have both moved from Shader/Vertex to Unified Stream processors. This is a really interesting development if you happen to work in a research establishment, otherwise please move along nothing to see here.

Heartening... (2, Interesting)

blind biker (1066130) | more than 5 years ago | (#25863381)

...to see a company established in a certain market, to branch out so aggressively and boldly into something... well, completely new, really.

Does anyone know if Comsol Multiphysics can be ported to CUDA?

Re:Heartening... (0)

Anonymous Coward | more than 5 years ago | (#25863651)

Can you imagine a Beowulf cluster of these?

Re:Heartening... (4, Interesting)

mangu (126918) | more than 5 years ago | (#25863719)

Can you imagine a Beowulf cluster of these?

Yes, I can. My first thought when I saw the article was to calculate how many of them one would need to simulate a human brain in real time. The answer is: with 2500 of these machines one could simulate a hundred billion neurons with a thousand synapses each, firing a hundred times per second, which is the approximate capacity of a human brain.

People have paid $20 million to visit the space station, now who will be the first millionaire hobbyist to pay $25 million to have his own simulated human brain?

Re:Heartening... (3, Interesting)

swamp_ig (466489) | more than 5 years ago | (#25863801)

Would the interconnects be fast enough? There's a lot of non-locality in the synaptic connections, so you're going to need some pretty heavy comms between the cores.

Also a selection of neurons are far more heavily connected than 1000s of synapses, and they're fairly essential ones. Might these be a critical path?

Sure would be cool to build such a beast, do some random connections, and see what happens...

Re:Heartening... (1, Interesting)

Anonymous Coward | more than 5 years ago | (#25863877)

Would the interconnects be fast enough?

Short answer: no.

Long answer: there is no direct interconnect between the cards, so any data would have to go down the PCIe bus to the host and then back up to an interconnect card, across the network and back across the PCIe bus twice to get to the other. With a specially designed PCIe root complex you could probably eliminate some of the overhead and allow the card to send direct to the interconnect without having to share the bus with the host, but you couldn't do that currently. Even then, there isn't any interconnect currently available that even comes close to the bandwidth you'd need.

Re:Heartening... (1, Insightful)

Anonymous Coward | more than 5 years ago | (#25863849)

It would take a hell of a lot more than 25 mil to program the brain simulator.

Re:Heartening... (4, Interesting)

smallfries (601545) | more than 5 years ago | (#25863971)

Your figures are off by several orders of magnitude. 2500 of these is roughly 10,000T/flops. As a Tflop is 10^12 operations, and we have 10^11 neurons that leaves 10^5 floating point operations per neuron. If each has 1000 synapses to process then we are down to 100 operations per connection, per second.

At this point it seems obvious that you've assumed a really simplistic model of a neuron that can compute a synaptic value in a single floating point operation. These simple neuron models don't behave like a real brain, and scaling up simulations of them doesn't produce anything interesting. Real neurons are capable of computing much more complex functions than these models. The throughput on the interconnect is going to be a major factor, and simulating each neuron will require from 10s to 1000000s of operations depending on the level of biological realism that is required. The Blue Brain project has a lot of interesting material on different models of the neuron and the tradeoff between performance and realism.

Their end goal is to dedicate a large IBM Blue Gene to simulating an entire column within the brain (roughly 1,000,000 neurons) using a biologically-realistic model.

4 TFLOPS? (5, Insightful)

Anonymous Coward | more than 5 years ago | (#25863385)

A single Radeon 4870x2 is 2.4 TFLOPS. Some supercomputer, that.

Seriously, why is this even news? nVidia makes a product, which is OK, but nothing revolutionary. The devaluation of the "supercomputer" term is appalling.

Also, how much of that 4 TFLOPS you can get on actual applications? How's FFT? Or LINPACK?

Re:4 TFLOPS? (4, Informative)

GigaplexNZ (1233886) | more than 5 years ago | (#25863599)

A single Radeon 4870x2 is 2.4 TFLOPS.

A single Radeon 4870x2 uses two chips. This Tesla thing uses 4 chips that are comparable to the Radeon ones. It should be obvious that they would be in a similar ballpark.

Seriously, why is this even news?

It isn't. Tesla was released a while ago, this is just a slashvertisement.

Re:4 TFLOPS? (0)

Anonymous Coward | more than 5 years ago | (#25864103)

I can think of one... weather modeling. Weather models are math intensive and if you can take a forecast run down from 3 hours to 15 minutes, that's a huge deal.

But.. (1)

D_Blackthorne (1412855) | more than 5 years ago | (#25863397)

..will it run Vista? ;-)

Re:But.. (2, Funny)

itsybitsy (149808) | more than 5 years ago | (#25863407)

Not yet.... darn NVidia, no Vista Drivers yet...

Come on NVidia GET WITH IT!!!

Re:But.. (0)

Anonymous Coward | more than 5 years ago | (#25863471)

To heck with vista. I just need to know if it runs Linux.

Re:But.. (1)

angelwolf71885 (1181671) | more than 5 years ago | (#25863545)

i think the real question is can it run crysis running on vista...and play a bluray movie at 1080P at the same time...

What, no coil? (5, Funny)

dgun (1056422) | more than 5 years ago | (#25863409)

What a rip.

Nor turbine. (2, Interesting)

BOFHelsinki (709551) | more than 5 years ago | (#25864063)

Shameless exploitation of the good name of one of the greatest inventors of all time. :-)

Re:What, no coil? (3, Funny)

geekmux (1040042) | more than 5 years ago | (#25864233)

What a rip.

Yeah, no shit. First bastard that tries to put a "Tesla Capable" sticker on the front, I'm gonna sue.

Louis Savain will be all over this one! (0)

Anonymous Coward | more than 5 years ago | (#25863411)

Can't wait for him to come and tell us how Nvidia, ATI, Intel and all are idiots, and this is completely and totally unusable and we're in a parallel crisis!

What a disappointment (2, Interesting)

dleigh (994882) | more than 5 years ago | (#25863413)

At first glance I thought these used actual Tesla coils [wikipedia.org] in the processor, or the devices were at least powered or cooled by some apparatus that used Tesla coils.

Turns out "Tesla" is just the name of the product.

Drat. I demand a refund.

Re:What a disappointment (1)

rhyder128k (1051042) | more than 5 years ago | (#25863749)

They should at least come up with a "mad scientist lab pack" that includes some Tesla coils. Perhaps they presume that mad scientists will have their own gear.

I just spent an entire morning trying out massive single throw switches.

"Now, we'll SEE who's mad! [thunk]"

"Now, we'll see who's MAD! [thunk]"

In all fairness, these things can be pretty personal.

Your probably right about the "mad scientist" ... (2, Insightful)

PolygamousRanchKid (1290638) | more than 5 years ago | (#25864361)

. . . that's probably exactly the person who would buy one of these.

Folks who are professionally working on mainstream problems that require supercomputers, well, they probably have access to one already. (Maybe one of the supercomputing folks might want to chime in here; do you have enough access/time? Would a baby-supercomputer be useful to you?)

But there is certainly someone out there who was denied access, because his idea was rejected by peer review. He is considered a loopy nut bag, because he wants to prove that the Higg's boson is made of cottage cheese, or something like that.

Yep, look for rejected supercomputing program proposals, and you have a list of potential customers.

Re:What a disappointment (1)

David Gerard (12369) | more than 5 years ago | (#25863881)

I thought of the car first. I figured that's how much battery you'd need to run it in a laptop.

Binary-only toolchain (5, Informative)

Anonymous Coward | more than 5 years ago | (#25863421)

The toolchain is binary only and has an EULA that prohibits reverse engineering.

Re:Binary-only toolchain (5, Informative)

FireFury03 (653718) | more than 5 years ago | (#25863561)

has an EULA that prohibits reverse engineering.

Not really a big deal to those of us in the EU since we have a legally guaranteed right to reverse engineer stuff for interoperability purposes.

Sorry nVidia, but this isn't gaming anymore (0)

Anonymous Coward | more than 5 years ago | (#25863595)

Scientific and rendering outfits don't work to the same M.O. as gamers, ie. "it works, I'll use it, game on".

Open-source has become the name of the game over the last few years, and vendor tie-in has become the arse-end of the computing world, especially for this particular customer base.

While you may like the smell at the arse end, those who need HPC don't. Your blind attachment to the concept of closed-source accelerator solutions is so myopic that it's in danger of becoming an Internet joke meme.

I predict the worst possible outcome for a company with its head in the sand and a chip up its arse.

Re:Sorry nVidia, but this isn't gaming anymore (1)

Gorgonzolanoid (1394311) | more than 5 years ago | (#25863673)

Cray just announced a new closed-source $25K supercomputer two months ago [wired.com] .
IBM is going open source on its supercomputers, but last August [zdnet.co.uk] is not what I would call "the last few years".

Re:Binary-only toolchain (1)

JamesP (688957) | more than 5 years ago | (#25863733)

The toolchain is binary only and has an EULA that prohibits reverse engineering.

Show me a non-free EULA that doesn't.

Re:Binary-only toolchain (1)

oneofthose (1309131) | more than 5 years ago | (#25863811)

I haven't heard of anyone who reverse engineered the toolchain but there's an awesome tool that helps you reverse engineer your own binaries: http://www.cs.rug.nl/~wladimir/decuda/ [cs.rug.nl] This is relevant because the compiler creates device specific binaries that you can't get the assembler code for. So if you want to know exactly what your kernel is doing disassemble it with decuda. Unfortunately the tool is a bit outdated but it still might be useful to some.

Re:Binary-only toolchain (1)

janwedekind (778872) | more than 5 years ago | (#25864383)

Thanks for raising awareness of that! Stream processing could be great for machine vision. However the situation seems to be almost as bad as with most FPGA boards where you need proprietary compilers and proprietary libraries to compile and run your programs (not to talk about firmware and hardware design). Not hacker-friendly at all :( If anyone has time and money to spend please join and support something like the Open Graphics Project [wikipedia.org] instead.

And the worst timing ever award goes to... (2, Insightful)

CryptoJones (565561) | more than 5 years ago | (#25863435)

While the inner nerd in me screams to take out a loan against my house to buy one, I can't imagine this being very popular outside academia. Most users don't use the power of their crappy computers, let alone this. And then there is the whole "ECONOMY" thing.

Re:And the worst timing ever award goes to... (2, Insightful)

Yetihehe (971185) | more than 5 years ago | (#25863491)

It IS marketed for academia. Normal users don't really need to fold proteins or simulate nuclear weapons at home.

Re:And the worst timing ever award goes to... (2, Informative)

palegray.net (1195047) | more than 5 years ago | (#25863529)

I'm perfectly normal, and I fold proteins all the time [webshots.com] .

Re:And the worst timing ever award goes to... (2, Interesting)

Anonymous Coward | more than 5 years ago | (#25863579)

according to http://folding.stanford.edu/English/Stats about 250.000 "normal" users are folding proteins at home.

Personally, I would use it as a render farm, but Blender compatibility could take a while if Nvidia keeps the drivers and specification locked up.

What they don't seem to mention is the amount of memory/core (at 960 cores). I'd guess about 32 MB/core, and 240 cores sharing the same memory bus...

Re:And the worst timing ever award goes to... (1)

evilbessie (873633) | more than 5 years ago | (#25864037)

err, you seem to have missed something fairly major in your understanding. Specifically about what constitutes a 'core'. These cards are based on the same chip in the GT280, so they have 240 stream processors, which are very good at specific types of calculation (If I was wiser I could tell you what types but I'm sure you can use google yourself). I believe that each of the chips has a 512 bit wide bus to 4GiB of memory. I'm not sure what the memory allocation per stream processor is but I think the other parts of the chip control what goes where. There probably are some bottlenecks but I don't know enough about it to be able to give useful information on the subject. There is something like 102GB/s memory bandwidth per 240 core chip.

Yes but (2, Funny)

Colin Smith (2679) | more than 5 years ago | (#25863643)

And then there is the whole "ECONOMY" thing.

The whole reason the ECONOMY is in the tank is because there are not enough people like you taking loans out against their house to buy random stuff like this.

Basically... IT'S ALL YOUR FAULT!

 

The question here is... (0)

Anonymous Coward | more than 5 years ago | (#25863447)

But will it run Crys- ...

Oh.

Only in C? Oh dear. (0, Flamebait)

Viol8 (599362) | more than 5 years ago | (#25863499)

That'll frighten a lot of the OO fanboys who have to have a friggin inheritance tree and a factory based abstracted class design before they can write Hello World.

Sorry , its early , I'm feeling grouchy.

Re:Only in C? Oh dear. (1, Insightful)

GigaplexNZ (1233886) | more than 5 years ago | (#25863607)

OO is very good for graphical interfaces, but it isn't particularly well suited for algorithms and other maths oriented stuff. Why should we care if OO fanboys are scared off? Decent developers know to use the right tool for the job, not try to shoehorn whatever their personal favourite is into every situation.

Re:Only in C? Oh dear. (1)

Joce640k (829181) | more than 5 years ago | (#25863669)

"...isn't particularly well suited for algorithms and other maths oriented stuff"

Yeah, all that operator overloading is a real pain in the ass for numerical work.

Re:Only in C? Oh dear. (5, Informative)

xororand (860319) | more than 5 years ago | (#25863765)

OO is very good for graphical interfaces, but it isn't particularly well suited for algorithms and other maths oriented stuff.

The term OO is too general to make a statement about its usefulness for mathematics oriented problems. The powerful templating features of modern C++ are indeed very useful for numerical simulations:

It's called C++ Expression Templates, an excellent tool for numerical simulations. ETs can get you very close to the performance of hand optimized C code while they're much more comfortable to use than plain C. Parallelization is also relatively easy to achieve with expression templates.

A research team at my university actually uses expression templates to build some sort of meta compiler which translates C++ ETs into CUDA code. They use it to numerically simulate laser diodes.

Search for papers by David Vandevoorde & Todd Veldhuizen if you want to know more about this. They both developed the technique independently.

Vandevoorde also explains ETs to some degree in his excellent book "C++ Templates - The Complete Guide".

Re:Only in C? Oh dear. (0)

GigaplexNZ (1233886) | more than 5 years ago | (#25863901)

As a C++ programmer myself I generally agree with what you said. But when I say "isn't particularly well suited" I mean it isn't necessarily the best solution even though it may work. I was also referring to the typical inheritance and dynamic polymorphism style of OO that the "fanboys" tend to love.

PS: Thanks for the references, I'll look into them.

Re:Only in C? Oh dear. (1)

Fred_A (10934) | more than 5 years ago | (#25864143)

OO is very good for graphical interfaces, but it isn't particularly well suited for algorithms and other maths oriented stuff.

Absolutely, that's what Fortran is for !

Re:Only in C? Oh dear. (1)

VoidCrow (836595) | more than 5 years ago | (#25864223)

> but it isn't particularly well suited for algorithms and other maths oriented stuff.

STL? Discrete math up the wazooo? Well, maybe not up the *wazoo*...

It also runs Python (3, Informative)

mangu (126918) | more than 5 years ago | (#25863729)

Look, there's Python here [nvidia.com] . You can do the low-level high-performance core routines in C, and use Python to do all the OO programming. This is how God intended us to program.

Taken from bash.org (1)

Artuir (1226648) | more than 5 years ago | (#25863955)

someone speak python here?
  HHHHHSSSSSHSSS
  SSSSS
  the programming language

http://www.bash.org/?400459 [bash.org]

Re:It also runs Python (2, Funny)

BOFHelsinki (709551) | more than 5 years ago | (#25864079)

Ah, Parseltongue. So you are of the Slytherin school of programmers?

Re:It also runs Python (3, Funny)

OriginalArlen (726444) | more than 5 years ago | (#25864113)

This is how God intended us to program.

Then why did he write Perl?

Re:Only in C? Oh dear. (1)

MROD (101561) | more than 5 years ago | (#25863747)

Actually, OOP is a bit rubbish for number crunching, far too much overhead.

What is disappointing is that there isn't a high performance FORTRAN compiler. That's where most scientific number crunching is done. (After all, that's what the language was designed for.)

Re:Only in C? Oh dear. (2, Informative)

cnettel (836611) | more than 5 years ago | (#25863793)

OOP with virtual and all, yes. OOP with template magic to allow the compiler to do specializations can beat the heck out of even quite tediously hand-written C or FORTRAN, with much superior readability.

Re:Only in C? Oh dear. (1)

ardin,mcallister (924615) | more than 5 years ago | (#25863893)

offtopic, but i actually know someone who writes everything in fortran. my boss and i have seen the man write opengl calls in fortran... its a tad unsettling.

Let me be the first to say... (5, Funny)

rdnetto (955205) | more than 5 years ago | (#25863503)

4 Terraflops should be more than enough for anybody...

Re:Let me be the first to say... (-1, Flamebait)

Anonymous Coward | more than 5 years ago | (#25864295)

Being that it uses nvidia drivers, at 4 teraflops, it should BSOD in 200-some miliseconds.

Wow. (1)

osir (1402743) | more than 5 years ago | (#25863515)

Well cool. I dunno why people have such a tendency to start commenting on slashdot posts with ridicule. This is laudable, not laughable.

Re:Wow. (0)

Anonymous Coward | more than 5 years ago | (#25863551)

Because a person is smart. People are dumb panicky animals, and you know it.

Nah. (1)

osir (1402743) | more than 5 years ago | (#25863609)

No, I don't, and thats a piss poor plea (theirs' not your) for mod points. People are generally smart, they just lower themselves for social reasons, in groups or otherwise. You may or may not know that, but I think its more accurate than saying groups are inherently stupid.

Re:Nah. (0)

Anonymous Coward | more than 5 years ago | (#25863791)

That was a stupid Men in Black quote.

Re:Nah. (0)

Anonymous Coward | more than 5 years ago | (#25864011)

>People are generally smart

So, you're saying that on average people are smart?

nerdgasm (0)

Anonymous Coward | more than 5 years ago | (#25863521)

If this can be enabled to work for Digital Audio Workstations, to offer massive processing for VST/RTAS away from the CPU, I can still see a thriving market for this in multimedia...or even with real-time video processing.

Who remembers BionicFX? This will certainly make up for their vaporware...

I would save up for this

---
actual CAPTCHA:
costed

I want one... (1)

frictionless man (1140157) | more than 5 years ago | (#25863537)

No wait, I want one of these and the skills to be able to write something cool in c that would actually use it.

Scientist speak (2, Interesting)

jnnnnn (1079877) | more than 5 years ago | (#25863575)

So many scientists use the word "codes" when they mean "program(s)".

Why is this?

Re:Scientist speak (3, Interesting)

Anonymous Coward | more than 5 years ago | (#25863665)

It's cultural.

You're not even allowed to say that you're "coding", but only that you produce "codes".

Maybe it's because analytic science is basic on equations which become algorithms in computing, and you can't say that you're "equationing" nor "algorithming".

In practice it's actually dishonest, because the algorithms don't have the conceptual power of the equations that they represent (they would if programmed in LISP, but "codes" are mostly written in Fortran and C), so the computations are often questionable. Even worse, it's almost impossible for one research group to compare the "codes" that yielded their results against those produced by another group when numerical computing is used, whereas equations are universally portable.

The theoretical half of the scientific method has lost some of the firm foundations upon which it used to build in recent years, as a result of theorizing through numerical simulation. Fortunately it doesn't matter too much in most sciences because experiment soon demolishes any incorrect predictions. However, those sciences which deal with long-term or historic or otherwise untestable areas are suffering, as a fair bit of unsubstantiated nonsense is popping out of poorly approximated simulations and being claimed as "fact", even though reality hasn't agreed yet.

Things are probably going to get worse in this area before they get better.

More than 1 (1)

rdnetto (955205) | more than 5 years ago | (#25863629)

Imagine a Beowolf cluster of these!

Re:More than 1 (1)

Provocateur (133110) | more than 5 years ago | (#25863771)

Owooooo.... (at the full moon)

weak DP performance (5, Informative)

Henriok (6762) | more than 5 years ago | (#25863655)

I supercomputing circles (i.e. Top500.org) double precision floating point operations seems to be what is desired. 4 TFLOPS single precision, while impressive, is overshadowed by the equally weak 80 GFLOPS double precision, beaten by a single PowerXCell 8i (successor to the Cell in PS3) or the latest crop of Xeons. I'm sure tesla will find its users but we won't see them on the Top500 list anytime soon.

Re:weak DP performance (1, Interesting)

Anonymous Coward | more than 5 years ago | (#25863705)

> Each Tesla GPU has 240 cores and delivers about 1 Teraflop single precision and about 80 Gigaflops double-precision floating point performance.

The 80GFlops are per card. So you end up with 320GFlops total.

Not much better, but still better than nothing ;)

Re:weak DP performance (0)

Anonymous Coward | more than 5 years ago | (#25864067)

> I supercomputing circles (i.e. Top500.org) double precision floating point operations seems to be what is desired.

That depends. In many cases, memory bandwidth is what is most desired, and compared to ordinary CPUs (as soon as your problem is larger than the cache), GPUs deliver very well here.
Either way GPUs are still very much special-purpose, so they sure will not be interesting for everyone.

Re:weak DP performance (1)

timeOday (582209) | more than 5 years ago | (#25864311)

I'm just amazed that the performance loss from single to double precision is more than a factor of 10! It's only 2x the bits, what's the holdup?

boring apps... let's have some realtime raytracing (3, Insightful)

Lazy Jones (8403) | more than 5 years ago | (#25863679)

there were a lot of early efforts trying to implement realtime rayracing engines for games (e.g. at Intel recently [intel.com] ), let's port that stuff and have some fun.

Developement Platform (2, Insightful)

dreamchaser (49529) | more than 5 years ago | (#25864179)

On that note, it would be a good development platform for realtime raytraced game engines. That way the code would be mature when affordable GPU's come out that can match that level of performance.

Can I have a smaller version? (1)

Fuzuli (135489) | more than 5 years ago | (#25863709)

Is it possible to build a smaller version of this configuration? I do not have 10K, but I can come up with something smaller for my PhD research. In that case, is this a package that can be replicated via off the shelf nvidia hardware, or do I need to wait for NVidia to release a smaller version?

Re:Can I have a smaller version? (1)

JamesP (688957) | more than 5 years ago | (#25863745)

Well, buy any card that supports CUDA (pretty much all offers by nVidia today - except you probably want to stay off the cheapest stuff)

You can also try running a PS3 + Linux or try the similar offers from AMD/ATI

Re:Can I have a smaller version? (1)

Fuzuli (135489) | more than 5 years ago | (#25864239)

Sorry, I should have been clearer. I'm aware of those solutions, but would it be the same in terms of processing power, software support (cuda, related libraries etc..)
I mean is this a convenient repackaging of what is already out there, or does it have something extra?

Re:Can I have a smaller version? (3, Informative)

SpinyNorman (33776) | more than 5 years ago | (#25864379)

From NVidia's CUDA site, most of their regular display cards support CUDA, just with less cores (hence less performance) than the Tesla card. The cores that CUDA uses are what used to be called the vertex shaders on your (NVidia) card. The CUDA API is designed so that your code doesn't know/specify how many cores are going to be used - you just code to the CUDA architecture and at runtime it distrubutes the workload to the available cores... so you can develop for a low end card (or they even have an emulator) then later pay for th hardware/performance you need.

FLOPS not FLOP! (1)

91degrees (207121) | more than 5 years ago | (#25863713)

The S stands for "seconds". The singular is therefore "FLOPS".

Re:FLOPS not FLOP! (4, Funny)

TeknoHog (164938) | more than 5 years ago | (#25864191)

What's the plural of FLOPS then? My preciouss FLOPSes?

Erlang (2, Interesting)

Safiire Arrowny (596720) | more than 5 years ago | (#25863763)

So how do you get an Erlang system to run on this?

And in other news... (5, Funny)

bsDaemon (87307) | more than 5 years ago | (#25863841)

... AMD has annouced today it new Edison Personal Supercomputer technology.

The game is on.

cold hard facts about cuda (2, Interesting)

Gearoid_Murphy (976819) | more than 5 years ago | (#25863913)

it's not about how many cores you have but how efficiently they can be used. If your CUDA application is any way memory intensive you're going to experience a serious drop in performance. A read from the local cache is 100 times faster than a read from the main ram memory. This cache is only 16kb. I spend most of my time figuring out how to minimise data transfers. That said, CUDA is probably the only platform that offers a realistic means for a single machine to tackle problems requiring gargantuan computing resources.

Re:cold hard facts about cuda- unbalanced (4, Insightful)

anon mouse-cow-aard (443646) | more than 5 years ago | (#25864025)

People are always coming out of the wood work to claim supercomputer performance with such and such a solution, go back and look at GRAPE (which is really cool.) http://arstechnica.com/news.ars/post/20061212-8408.html [arstechnica.com] or a lot of other supercomputer clusters. When you want something flexible, you look for "balance" that means a good relationship between memory capacity, latency & bandwidth, as well as computer power. in terms of memory capacity, the number people talk about is: 1 byte/flop... that is 1 Tbyte of memory is about right to keep 1 TFLOP flexibly useful. this thing has 4 G of memory for 4 TF... in other words: 1 byte / 1000 flops. it's going to be hard to use in a general purpose way.

BrookGPU (1)

Skinkie (815924) | more than 5 years ago | (#25864027)

In the paste I was not very impressed by things as http://www-graphics.stanford.edu/projects/brookgpu/ [stanford.edu] because of the latency that is involved in actually transferring data back and forth from CPU to GPU memory. Thus I observed the same thing. But now it seems to the actual latency for transfer is reduced because of PCI-e, one might wonder if decent compiler technology is able to optimise 'normal' code for GPU instructions.

Patmos International (3, Interesting)

Danzigism (881294) | more than 5 years ago | (#25864197)

ahh yes the idea of personal supercomputing. Back in '99 I worked for Patmos International. We were at the Linux Expo for that year as well if some of you might remember. Our dream was to have a parallel supercomputer in everyone's home. We used mostly Lisp and Daisy for the programming aspect. The idea was wonderful, but eventually came to a screeching halt when nothing was being sold. It was ahead of it's time for sure. you can find out a little more about it here. [archive.org] I find the whole ideal of symbolic multiprocessing very fascinating though.
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?