Tuesday, August 10th 2010

NVIDIA-Led Team Receives $25 Million Contract From DARPA to Develop GPU HPC Systems

A team led by NVIDIA has been awarded a research grant of $25 million by the Defense Advanced Research Projects Agency (DARPA), the U.S. Defense Department's research and development arm, to address what the agency calls a "crisis in computing." The four-year research contract, awarded under DARPA's Ubiquitous High Performance Computing (UHPC ) program, covers work to develop GPU technologies required to build the new class of exascale supercomputers which will be 1,000-times more powerful than today's fastest supercomputers.

The team -- which also includes Cray Inc., Oak Ridge National Laboratory and six top U.S. universities -- is being funded by DARPA to address the challenge that conventional computing architectures are reaching the practical limits of energy usage and will not meet the challenges of exascale computing. The research team plans to develop new software and hardware technology to dramatically increase computing performance, programmability and reliability.

"This recognizes NVIDIA's substantial investments in the field of parallel processing and highlights GPU Computing's position as one of the most promising paths to exascale computing," said Bill Dally, NVIDIA's chief scientist and senior vice president of research, and the team's principal investigator. "We look forward to collaborating to develop programmable, scalable systems that operate in tight power budgets and deliver increases in performances that are many orders of magnitude above today's systems."

"The DARPA UHPC program is attacking technical issues that are key to the future of high performance computing, from the embedded terascale to the exascale," said Steve Scott, Cray's senior vice president and CTO, and the Cray principal investigator on the team. "We are excited to be working with this team, and we believe the directions we are pursuing will lead to radical improvements to the state-of-the-art in the coming decade."

In addition to the NVIDIA-led team, DARPA awarded contracts to three other teams to study UHPC systems. Prototype systems are expected to be completed by 2018. The names of those universities on the NVIDIA team will be available once details with them have been finalized. For more information on the DARPA UHPC program, please go here.
Add your own comment

39 Comments on NVIDIA-Led Team Receives $25 Million Contract From DARPA to Develop GPU HPC Systems

#1
bpgt64
But will it play Crysis.
Posted on Reply
#2
Konceptz
I see missile guidance systems with the "powered by nvidia" logo in the near future......
Posted on Reply
#3
$ReaPeR$
by: Konceptz
I see missile guidance systems with the "powered by nvidia" logo in the near future......
The way you are meant to be blown up! :D
Posted on Reply
#4
Konceptz
by: $ReaPeR$
The way you are meant to be blown up! :D
New US bombers SR-24 Blackbird...FTW LOL
Posted on Reply
#5
soryuuha
Power failures soon gonna be frequent around US
Posted on Reply
#6
Laurijan
by: $ReaPeR$
The way you are meant to be blown up! :D
Lol
Posted on Reply
#7
Laurijan
25 mill doesnt sound like much for me if this project is really as big as it seems.
Posted on Reply
#8
Kreij
Senior Monkey Moderator
It's not. That is just part of the funding to the research teams.
Cray is involved too. They are good at making things really fast. ;)
Posted on Reply
#9
$ReaPeR$
by: Konceptz
New US bombers SR-24 Blackbird...FTW LOL
GTX 880 ULTRA Bombers :D
Posted on Reply
#10
Cheeseball
by: DrPepper
I'm curious why AMD didn't get the contract since they're more efficient in everyway really ?
Because their Stream architecture is not as efficient as CUDA. The Stream SDK is a jumbled mess at the moment, even when indirectly using OpenCL APIs.

It's the only reason why I have a 8600GT (probably going to switch to a GT 240 soon) on my third PCI-E slot. :P If ATI would just properly document their technology correctly (and give appropriate help), maybe some of my (and my colleagues) projects would use Stream instead of CUDA in the future.
Posted on Reply
#11
Oprah(IE)
by: hat
Maybe we're going to take down the enemy by connecting this device full of hot, power hungry GPUs to thier power grid...
haha! true dat.
Posted on Reply
#12
Meizuman
At the moment "Nvidia" and "tight power budgets" just cant be fitted in the same sentence! They have nothing in that aspect.
Posted on Reply
#13
AsRock
TPU addict
by: $ReaPeR$
The way you are meant to be blown up! :D
lol, Although they might be going War Of The Worlds style with a heat ray :P.
Posted on Reply
#14
a_ump
um idk bout you guys but 2018....and just prototypes wow is all i can say. I would assume that 25million will be annually or every 6 months bc 25million won't go to far over 8yrs of research and testing.
Posted on Reply
Add your own comment