"Titan" Supercomputer, Powered by NVIDA GPUs, Seizes Top500 Crown
November 13, 2012 10:24 AM
comment(s) - last by
U.S. institution recaptures title with 17.59 petaflop showing
NVIDIA Corp. (
) is bringing out the big guns in the GPU market, pushing special
"accelerator" hardware -- the big brother to
NVIDIA's market-leading consumer gaming hardware
. Targeted at large supercomputer deployments, the Tesla K20X accelerator offers 3.95 teraflops of peak floating point precision performance and 1.17 teraflops of peak double performance.
To put that in context, a top-of-the-line server CPU -- the
12-core, 2.4 GHz Xeon E7-8870 -- gets approximately 384 gigaflops of peak double performance [
]. With an average power performance of around 90 watts per core [
] when loaded, the Intel chip musters around 355 Megaflops per watt. By contrast, the NVIDIA card gets about 2,142.77 Megaflops per watt. In other words, it's not only more powerful in terms of pure number crunching; it's also more efficient.
Of course, that comparison is slightly misleading; there are significant differences between GPU-accelerated multi-threaded computing and CPU multi-core computing in terms of memory resources and data transfer.
The world's most powerful supercomputer is now driven by NVIDIA's Tesla K20X GPUs.
But the numbers do start to give you an idea of why so many data centers are jumping on the GPU train. NVIDIA announced on Monday that the completed "
" supercomputer at
Oak Ridge National Laboratory
in Oak Ridge, Tenn. just earned a "number one" ranking in the Top500 list of the world's most powerful supercomputers.
Powered by 18,688 NVIDIA Tesla cards, the installation posted a LINPACK score of 17.59 petaflops.
Titan shows NVIDIA's arch-nemesis CPU/GPU-maker Advanced Micro Devices, Inc. (
) some love as well, utilizing its
Opteron 6274 (
) 16-core chips
. Paired with 710 terabytes of memory, the machine is capable of performing 1,000 quadrillion calculations per second using 20 megawatts of electricity or less.
Titan unseats reigning champion Sequoia, a more traditional CPU-driven design from IBM.
Dr. Thomas Schulthess, professor of computational physics at
and director of the
Swiss National Supercomputing Center
cheers the record-setter, remarking, "We are taking advantage of NVIDIA GPU architectures to significantly accelerate simulations in such diverse areas as climate and meteorology, seismology, astrophysics, fluid mechanics, materials science, and molecular biophysics. The K20 family of accelerators represents a leap forward in computing compared to NVIDIA's prior Fermi architecture, enhancing productivity and enabling us potentially to achieve new insights that previously were impossible."
The previous record holder was
Lawrence Livermore National Laboratory
Blue Gene supercomputer
from International Business Machines, Inc. (
Sequoia is a more traditional CPU-based design
, which uses PowerPC A2 processor chips.
This article is over a month old, voting and posting comments is disabled
Why compare Tesle to a Xeon E7-8870?
11/13/2012 11:44:43 AM
Just curious as to the comparison between the new Tesla K20 and the Xeon E7-8870 seeing as how there's only one E7-2860 on the top500 list? The current favored chip from the Intel lineup are the SNB based E5 Xeons, of which the top machine using only Xeon for compute is in the #6 spot and achieves 846 Megaflops per watt.
Yeah, it's still ~2.5 times worse than the Tesla in terms of energy efficiency... but that's quite a bit better than the 5.5x worse that's portrayed in the article.
RE: Why compare Tesle to a Xeon E7-8870?
11/13/2012 3:45:38 PM
The chip is also unlikely to reach peak efficiency, but the article does say the numbers are misleading. The entire system is getting around ~ 900gflops per GPU, so it takes a substantial amount of CPUs and GPUs to obtain somewhere near the gpu's peak output. Power efficiency is basically in line with the last #1 supercomputer.
Does seem to require significantly less RAM, though.
"It seems as though my state-funded math degree has failed me. Let the lashings commence." -- DailyTech Editor-in-Chief Kristopher Kubicki
Tegra 3 Supercomputer Aims to be 3 Times as Efficient as IBM's Blue Gene
April 4, 2012, 1:00 PM
Worth the Wait: NVIDIA's Kepler GTX Geforce 680 is New Graphics Market King
March 23, 2012, 12:00 AM
AMD Launches 16 Core Interlagos Opteron Servers, Targets HPC, Cloud Computing
November 14, 2011, 10:00 AM
List of TOP500 Supercomputers Updated; IBM Supplies Half of Top Ten
June 23, 2009, 9:15 AM
Rosewill Releases 3 New Powerline Networking Adapters
May 21, 2013, 4:29 PM
German Researchers Test 40 Gbps Wireless Broadband
May 21, 2013, 11:01 AM
Qualcomm, Samsung Push AMD to Fourth Place in Processor Market
May 21, 2013, 7:50 AM
Supermicro Looks to Shake Up Server Market
May 20, 2013, 9:00 PM
HiPerGator Supercomputer is Florida's Most Powerful Supercomputer
May 17, 2013, 7:08 AM
5/7/2013 Daily Hardware Reviews
May 7, 2013, 12:02 PM
Most Popular Articles
High School Student Creates Storage Device that Can Charge in 20 Seconds
May 20, 2013, 6:51 AM
Apples Tries to Use Decade-Old Patents to Ban Samsung Galaxy S IV
May 22, 2013, 3:00 PM
NASA Awards $125,000 Grant for 3D Printed Food on Long-Term Space Travels
May 21, 2013, 1:32 PM
Microsoft Announces Voice-Controlled "Xbox One"
May 21, 2013, 12:55 AM
Seawater Cooling Saves Data Center Big Bucks, Energy, Despite Jellyfish Issues
May 17, 2013, 3:23 PM
Latest Blog Posts
Lumosity: Does it Work?
May 22, 2013, 8:20 PM
Quick Note: Sony "Teases" PS4 Ahead of Xbox Reveal in New Video
May 20, 2013, 12:33 PM
Nokia Introduces Instagram-Like App of Its Own to Help Lumia Sales
May 20, 2013, 7:10 AM
Parents of Pre-Teen Drivers Commonly Practice Distracted Driving Says Study
May 9, 2013, 7:16 AM
Apple's iOS 7 Running Into Internal Delays Due to Massive Overhaul
May 1, 2013, 4:26 PM
More Blog Posts
Copyright 2013 DailyTech LLC. -
Terms, Conditions & Privacy Information