NVIDIA Tesla GPUs now shipping with Dell 'personal supercomputers'

Been itching to get your hands on a personal supercomputer, as NVIDIA's ad wizards put it? The company has just announced that its CUDA-based Tesla C1060 GPU is now available in Dell's Precision R5400, T5500 and T7500 workstations. And just to put things into perspective, NVIDIA points out that a Dell workstation rockin' a single Tesla C1060 has enough going on under the hood to power the control system for the European Extremely Large Telescope project ("the world's largest," apparently). According to one of the developers, Jeff Meisel at National Instruments, a workstation "equipped with a single Tesla C1060 can achieve near real-time control of the mirror simulation and controller, which before wouldn't be possible in a single machine without the computational density offered by GPUs." Wild, huh? If you're curious about the workout that Tesla GPUs are getting on a wide range of projects, from Bio-Informatics to Computational Chemistry to Molecular Dynamics and more -- or if you're merely a glutton for long-winded PR -- check out the good stuff after the break.
Personal SuperComputing With DELL: NVIDIA Tesla GPUs Now Shipping In DELL Workstations
NVIDIA Tesla GPU Computing Solutions Become Mainstream as Number of GPU Optimized Applications Soars
For further information, contact:
Andrew Humber
NVIDIA Corporation
(408) 416 7943
ahumber@nvidia.com
FOR IMMEDIATE RELEASE:
SANTA CLARA, CA -MAY 6, 2009- NVIDIA Corporation, inventor of the GPU, today announced that the Tesla™ C1060 GPU Computing processor, based on the massively parallel CUDA™ architecture, is now available in Dell Precision R5400, T5500 and T7500 workstations.
"The Dell Precision R5400, T7500 and T5500 together with the Tesla GPU computing processors is putting the power of supercomputing on the desktop," said Greg Weir, senior manager, Dell Product Group. "We have seen early praise for the efforts of both Dell and NVIDIA to bring an economical high-performance computing solution to the most demanding customers."
"National Instruments is developing the control system for the European Extremely Large Telescope project, which upon completion will be the world's largest. To tackle this computational challenge, we developed a CUDA interface with LabVIEW to simulate and control the M1 mirror consisting of 984 individual segments," said Jeff Meisel product manager for LabVIEW at National Instruments. "A Dell workstation equipped with a single Tesla C1060, can achieve near real-time control of the mirror simulation and controller, which before wouldn't be possible in a single machine without the computational density offered by GPUs."
Another community sure to benefit from the mass market availability of this technology is the computational researcher. Based in the world's leading research schools such as Harvard, Cambridge or Tokyo Institute of Technology, these researchers fight for time on a shared supercomputing resource that consumes hundreds of kilowatts of power and costs millions of dollars to build and maintain. Dell Precision Workstations enabled with Tesla GPUs give each of these researchers their own "personal supercomputer" - the equivalent computing power of a cluster, at 1/100th of the price.
CUDA applications actively in use today by these researchers and organizations include:
Oil and gas
* Acceleware: Kirchoff Time Migration library
* ffA: 3D Seismic processing software
* Headwave: Prestack data processing
* Mercury Computer systems: 3D data visualization
* SeismicCity: 3D seismic imaging for prestack depth migration
* SMT: Kingdom – Seismic Processing
Computational Chemistry and Molecular Dynamics:
* GROMACS molecular dynamics
* HOOMD molecular dynamics
* NAMD molecular dynamics
* VMD visualization of molecular dynamics
Bio-Informatics and Life Sciences:
* GPU HMMER: CUDA version of HMMER
* LISSOM: Human neocortex modeling
* MUMmerGPU: High-throughput DNA sequencing
Financial Computing and Options Pricing:
* Aqumin: 3D Visualization of market data
* Exegy: Risk Analysis
* Hanweck: options pricing
* SciComp: derivatives pricing
Mathematical Computing
* Jacket CUDA plugin for MATLAB from Accelereyes
* LabVIEW from National Instruments
GeoSciences:
* Tsunami simulation – Tokyo Institute of Technology
* Weather Research and Forecast (WRF) model
* Geographical Information Systems - Manifold
Medical Imaging, CT, MRI:
* AxeRecon CT reconstruction library from Acceleware
* SnapCT tomographic reconstruction software from Digisens
Electrodynamics and Electromagnetics
* CST Microware Studio
* FDTD solver from Acceleware
Electronic Design Automation
* ADS SPICE simulator from Agilent EESof
* OmegaSim GX SPICE simulator from Nascentric
* Sentaraus TCAD from Synopsys
For more information on the Dell Precision Workstation line, visit www.dell.com. For more information on NVIDIA Tesla products, visit www.nvidia.com/object/tesla_computing_solutions and for more information on applications written for the CUDA architecture, visit www.nvidia.com/cuda.


















Yeah, but it doesn't want to.
@oneLove
but does your card do Buddha?
how did my comment end up here? damnit engadget fix your comment system
Okay, this might be a stupid question. But if this is a graphics card... Where are the outputs? Or is this just not designed for that?
its possible to have a GPU and still have the output on the mobo...i guess?
The card isn't a graphics card. Its a processing card. Its designed to let you use its crazy powerful GPU purely for CUDA applications.
it's not a graphics card it is made for data processing. GPU's are much more powerful than CPU's and after nvidia and ATI realised this they made their chips open enough for people to program code to take advantage of these processors.
Think of it as an alternate, additional CPU. It happens that the same architecture that enables high-speed rendering of 3D environments (games) can also be really, really good at crunching numbers for science. This card just happens to be optimized for crunching numbers, and is not intended to output anything to a display. Those duties can be left to something like a Quadro card, which I imagine this would happily SLI with.
As it has been pointed out, this is not a Graphics card. It's GPGPU (General Purpose GPU) It uses the CUDA language to perform operations on the GPU instead of the CPU. Imagine running CUDA operations across 3 of these. That's some REAL power!
'NOW you're playing with power!'
AMD must do something quick. NVidia has been kicking their asses lately, and I'm a ATi fanboy.
Can it send electricity wirelessly to the whole world??
Adorable. Someone wrap him up, I'm taking this one home.
In bubblewrap, per chance?
inb4 tesla. well just never know now.
Why does dell name their models like Intel CPUs?
Also, what exactly does this do, i understand its a $2000 GPU which has no video ports
http://en.wikipedia.org/wiki/CUDA rather than explain it. Your video card probably has CUDA so you can run the examples on Nvidia's site.
You would be run, i suck GMAs at the moment :(
I have an Ion Mini-ITX board on order though, that does CUDA :)
run? wrong
the new nvidia gpu's starting at the 8xxx series can now process things other than video. they can take care of physics in games and anything that a software manufacturer wants to run because the graphics processor is now open enough to accept many different types of operations. video cards have hundreds of stream processors which can be used for things other than graphics so if you are running a game that doesnt need all that much processing power 60 percent of the card can be dedicated to graphics while the rest can take care of ai or physics.
also gpus in many aplications are much more powerful than CPUs
CUDA is just a card that uses these new chips nvidia is making as the main processor in your computer, just think of it as the main processor.
My 295 GTX has CUDA, SUDA & WUDA.
Amen, OneLove.
Just buy a GT 285
A GT285 does not have anything to do with this.
Actually, it kinda does. The GTX cards use the same G200 architecture as the Tesla, and all G80 (8XXX+) and G200 GPUs are CUDA capable. AFAIK, the only really significant difference between a Tesla and a 285 is the number of cores.
This pushes a lot more computational horsepower than a GTX285
OH, it definitely does. I was just pointing out that you don't necessarily need a Tesla in order to do some serious stuff with CUDA. A couple of GTX's, or even 9800's, in SLI would be more than enough to get some interesting projects going. I'd generally think that, if you need a Tesla, there's a good chance you'll need more than one, which is is starting to move out of "workstation" territory.
Actually Steve is right. Both 285 and Tesla C1060 have the same number of cores. The 285 has higher clock rate and memory bandwidth, but the Tesla has 4 GB of RAM. Trust me, they would have comparable performance I have a Tesla s807, C1060 and a 9600 gtx.
hexydes wins this comment thread.
I'll take 3.
You're not hoping for SLI, are you...
:)
FUCK YEAH SEAKING
SEAKING, FUCK YEAH!
It so f'n powerful it beams the images directly into yer brain!
We need a new game already.
can it play mario?
That was even worse.
Not really, no. Notice there is no video out on it? It doesn't even have the stuff you need for games. It's for computations, not gaming.
Sooo...if GPUs are so much better than CPUs, how come we still got CPUs?
Edson didn't created the lamp in one day, young padawan.
Edson didn't create the lamp in one day, young padawan.
Well this isn't ideal for all applications yet. And I bet the price will be a *bit* over the roof.
There's certain things that each do better than the other. Aside from that, GPU's tend to have physically large cores, which would be cost-prohibitive for CPU manufacturers to compete with (think of making processors as baking a giant cookie. You then cut that cookie up into squares, each of which is a processor. The smaller the squares, the more you can fit in, and the less wasted space around the edges of the circle.
Powerful GPU's can get away with being expensive, since the kind of people who buy them tend to be picky, and have more of their budget devoted to the GPU than the CPU (power gamers, scientists, render farms, etc.). From there, you can also take the core architecture (no pun intended) of your chip, and use it as a northbridge on motherboards, where it provides integrated graphics for people who are unlikely to boot up anything more demanding than The Sims.
"Edson" didn't create the lamp at all
because CPUs use the X86 and X86-64 architecture that most applications are made to run on switching over to the architecture that GPUs use would mean throwing everything out. all operating systems would have to be thrown out no version of windows would run on them ( a new version would have to be made) all applications would have to be rewritten and any application made before this would have to be rewritten to run with these new architectures, also Nvidia and AMD (ATI) use different architectures so all of these programs would have to be written for each unless one of them gives up on their architecture and adopts the other's.
its exactly what Apple went through a couple years ago switching over from the PPC (power PC) architecture to intel's CPUs a completely new Operating system was needed, they spent alot of money to make sure that their old aps could run emulated on the new systems but most new apps made for intel will not run on the older PPC computers. my friend who still has a G4 powerbook has more and more applications all the time that she can no longer update.
and this was a switch that only involved less than 10% of the computer market. switching over now would be 100% of the market and would most likely kill intel since they would have to start from scratch.
intel would never let that happen
Who are the ad wizards that came up with that one?!
joker-pedobear?
run for the hills children!
uhh no thats my cousin ಠ_ಠ
So what OS will the workstation run to use this card? good luck with the nvidia vista drivers
Not sure what your talking about. Nividia is great with their driver support.