IT MIGHT no longer be the undisputed leader in graphics cards, but Nvidia has managed to power what is currently the fastest publicly known supercomputer.
The Tianhe-1A was revealed at the HPC 2010 China conference today with an operational performance 2.507 petaflops, easily surpassing the AMD Opteron shod Cray XT5 nicknamed Jaguar that currently heads the Top 500 list. Nvidia had already powered the Dawning Nebulae to second place on the list, with a theoretical peak performance that surpasses both the Jaguar and today's Tianhe-1A.
However the difference between operational and peak performance is significant, and to produce a 42 per cent increase over the Jaguar's operational performance is very impressive. Nvidia claims not only the performance crown but touts the energy efficiency of the Tianhe-1A machine, saying that it offers three times higher power efficiency compared to traditional CPU based clusters.
The supercomputer was designed at the National University of Defense [sic] Technology in China and is installed at the National Supercomputer Center in Tianjin. Nvidia says the Tianhe-1A is already fully operational and will be used as an open access system for scientific computation.
At present Nvidia has not disclosed the configuration of the nodes that make up Tianhe-1A, simply saying that there are Tesla GPUs inside.
Both AMD and Nvidia maintain that GPUs are the way towards attaining exascale computing, though this announcement will certainly hurt AMD. Not only will it lose the top spot on the prestigious Top 500 list, it will lose it to Nvidia, its principal rival in the GPGPU market.
It will be interesting to see whether Nvidia has managed to up the performance of Dawning Nebulae and possibly take the top two spots on the list. What is for certain, however, is that come November, the latest edition of the Top 500 list will have a new machine leading the pack. µ
Tags: Nvidia
and your point exactly? wiki supports that Intel powered the comp. Nvidia can't really take the credit from Intel in making it the fastest!!... even tho the GPU is Nvidia's!! The attempted comparison in this article b/w an AMD processor vs. Nvidia GPU is misleading at best.
people stop talking shiit already, it says the fastest computer not CPU. I am not sure how it was built, but it's not a bigger of deal at all. If it said China build the fastest CPU, i would be more surprise.
As I recall one of the capabilities of the fermi chip is full IEEE754-2008 com pliancy, and c/c++ too.
In fact it seems specifically designed with a focus on that stuff.
@s.
I quote good old wikipedia:
"Originally, Tianhe-I was powered by 4,096 Intel Xeon E5540 processors and 1,024 Intel Xeon E5450 processors, with 5,120 AMD GPUs which were made up by 2,560 dual-GPU ATI Radeon HD 4870 X2 GPUs. After the upgrade, it's equipped with 14,336 Xeon X5670 processors and 7,168 Nvidia Tesla M2050 general purpose GPUs."
What a shoddy piece of reporting ..... completely ignoring the fact that its Intel Xeons powering the device!!
First of all there is no more ati it's AMD. Nvidia is the company people love to hate, I guess no one cares about which card is the best for their dollar. I am sure I am going to get backlash for saying this. Who gives a shit, this round I bought 5870 next upgrade it's up to whoever has the faster/better card at the time. I have no brand loyalty. Comments like nvidia drivers are better, or nvidia is crap it's all BS.
I admit I get suckered into the inquirers biased articles. O well.
Nvidia's GPU are the best in class. They are the most innovative technology developed in the past 10 years. While Intel and AMD were trying to milk the clunky and obsolete x86 architecture, NVIDIA was investing in real innovation.
NVIDIA's drivers are excellent, stable and fast on Windows, Linux and BSD. ATI drivers are buggy under Windows and both unstable and slow under Linux, their GPUs are practically unsuitable for general purpose computing to begin with.
GO ATi!!!
According to the technical press, Tianhe-1A uses 7,168 Nvidia Tesla M2050 GPUs and 14,336 Intel Xeon CPUs.
I can understand why Nvidia didn't want to mention how many Intel CPUs were inside, but I'm surprised that this author didn't.
nVidia and AMD(ATI) leapfrog eachother all of the time. AMD can build a GPU based supercomputer once it secures an order for one. This eventuality will put AMD in a better position in the GPU vs CPU fight which puts it in a better position against Intel. Seems like it could actually help them.
...is that this new supercomputer can cook enough bacon, eggs, and pancakes for their entire country! And when its done cooking breakfast, it will heat the water for their showers!
Power to the People!
This "supercomputer" (if it could be called that) is only fast in a very small set of instructions. In real world computational needs, it's extremely slow.
Leave it to nVidia's market spin to crank up the lies. Inq, you fell for it.
When China manages to shrink it to the size of my iPhone, I will take one.