China, NVIDIA Create World's Most Powerful Supercomputer

Daily Tech ^ | October 28, 2010 10:00 AM | Jason Mick (Blog)

[Ernest_at_the_Beach]

System has 2.507 petaflops of computer power, draws 4 MW

NVIDIA has plenty to worry about in the consumer segment as it find itself yet again a generation behind AMD's latest graphics cards.  However, the company may simply be quietly divesting itself of its consumer market share by instead focusing on commercial GPU computing sales.

The graphics processor maker revealed today at HPC 2010 China an incredible new supercomputer, built using NVIDIA's GPUs which support CUDA, a C-driven technology that allows for the implementation of parallel computing code on the GPU.  The new supercomputer is named Tianhe-1a.  It is located at the National University of Defense Technology (NUDT) in Tianjin, China and is fully operational.

With a total computing power of 2.507 petaflops, as determined by the LINPACK benchmark which solves a dense system of linear equations, China's new supercomputer is the most powerful one in the world.

And NVIDIA's real bragging rights come when the power consumption is discussed.  By using GPUs instead of purely CPUs to fuel its calculations, the installation's power footprint is cut from an estimated 12 MW to 4.04 MW, saving enough electricity to power 5,000 homes a year.

[Ernest_at_the_Beach]

The supercomputer uses 7,168 NVIDIA Tesla M2050 GPUs.  (Source: NVIDIA)

[Ernest_at_the_Beach]

fyi

[ShadowAce]

[Ernest_at_the_Beach]

Tesla M2050 / M2070 GPU Computing Module

**************************************EXCERPT************************************

Based on the next-generation CUDA™ architecture codenamed “Fermi”, the Tesla M2050 and M2070 Computing Modules enable seamless integration of GPU computing with host systems for high-performance computing and large data center, scale-out deployments. The 20-series Tesla GPUs are the first to deliver greater than 10X the double-precision horsepower of a quad-core x86 CPU and the first to deliver ECC memory. The Tesla M2050 and M2070 modules deliver all of the standard benefits of GPU computing while enabling maximum reliability and tight integration with system monitoring and management tools.

[DManA]

draws 4 MW

A friend of mine at IBM told me the first time Los Alamos Labs turned on their Blue Gene super computer it browned out the whole town. Got a furious call from the power company.

[ShadowAce]

By using GPUs instead of purely CPUs to fuel its calculations, the installation's power footprint is cut from an estimated 12 MW to 4.04 MW, saving enough electricity to power 5,000 homes a year.

They're not "saving" anything. They're using less than normal. I wish tech writers would learn to write--and think.

[ShadowAce]

A friend of mine at IBM told me the first time Los Alamos Labs turned on their Blue Gene super computer it browned out the whole town.

LOL!! I did something similar. Fired up a cluster for the Navy, and four buildings went down. The power they had supplied for me wasn't adequate for the job. :)

[DakotaGator]

They're not "saving" anything. They're using less than normal. I wish tech writers would learn to write--and think.

Bravo! Avoidance is not saving. If the article's author cannot write intelligently he certainly cannot think intelligently!

[rahbert]

Unlikely that nVidia would drop its consumer base. Theres
not enough buisness in this GPU computing sector to sustain it yet.

Are they even OpenCL compliant yet?

[Ernest_at_the_Beach]

No idea.

OT...was just looking at this Youtube:

CPU vs. GPU

Excellent demo for Novices.

[camle]

but-but-but Ahrnold was on ABC news last night tellign us that caleefornea had built a faster computer. he would n’t lie to us, would he?

[America_Right]

They're not "saving" anything. They're using less than normal. I wish tech writers would learn to write--and think.

Yeah, I agree. What is this crap about NVidia being a generation behind ATI? The GTX4xx series is the most advanced consumer GPU on the market right now. Sure, they were 6 months late getting them out there, but they did and now they are ahead. Yeah, I am a bit biased since I just spent over $1k on a pair of GTX 480s...

[Ernest_at_the_Beach]

If you only knew how much....he will shade his statements.

[Marine_Uncle]

I saw the video on the painting exercise a few months back. I believe you may have posted it in a post similar to this one, ex. CPU verse GPU.
But what the heck. It is a fun video to watch.