"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
RE: wonder why the 1 to 1
11/13/2012 10:58:08 PM
Here's my question on these computers with massive amounts of RAM.
Do they use traditional modules for memory or custom made, much larger pieces with far more memory on them? I mean that much memory even with 16GB modules is over 44,000 modules.
RE: wonder why the 1 to 1
11/14/2012 10:01:08 AM
just ran the numbers and it seems each blade is using 2 16GB dimms.. or 4 8GB modules, im guessing 4x8 due to price. so the CPU has 32 GB ram. to get their total they are also counting the 6GB ram on board the GPU to bring each blade up to 38GB ram x 18,688 blades.. and you get their 710TB memory.
RE: wonder why the 1 to 1
11/17/2012 6:19:35 PM
what if the system isn't maxed out currently? What if the boards on them are only using a 1 to 1 ratio, because of current budgets?
“Then they pop up and say ‘Hello, surprise! Give us your money or we will shut you down!' Screw them. Seriously, screw them. You can quote me on that.” -- Newegg Chief Legal Officer Lee Cheng referencing patent trolls
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
Seagate Senior Researcher: Heat Can Kill Data on Stored SSDs
May 13, 2015, 2:49 PM
How to Recover Most Apps After Your NVIDIA Driver Crashes in Windows 10
March 30, 2015, 12:54 PM
Tinkerer Gets Old School Mac Plus Running on the Modern Web
March 24, 2015, 6:41 PM
Facebook-Backed Oculus Rift's Release Date Slips to 2016; Valve and HTC Salivate
March 16, 2015, 5:58 PM
Hackers Steal Roughly $1 Billion From Banks Using Malware RAT
February 17, 2015, 9:30 AM
NVIDIA Kills Mobile GPU Overclocking, Robs Customers Who Paid For It
February 16, 2015, 8:59 AM
Most Popular Articles
America's Largest Cable Company, Comcast, Sees Internet Subscriptions Pass TV
May 4, 2015, 2:46 PM
Oculus Rift and Compatible Gaming Rig Will Likely Cost $1,000 or More
May 15, 2015, 3:50 PM
Can id Software's Doom Find Its Way Out of a 7+ Year Development Hell?
May 19, 2015, 7:38 PM
Microsoft Bricks the Xbox Ones of Gears of War Testers Responsible for Leaks
May 14, 2015, 5:26 PM
Oculus Rift Confirms "Pause" in OS X, Linux Development, Some Devs are Mad
May 18, 2015, 11:36 PM
Latest Blog Posts
Sceptre Airs 27", 120 Hz. 1080p Monitor/HDTV w/ 5 ms Response Time for $220
Dec 3, 2014, 10:32 PM
Costco Gives Employees Thanksgiving Off; Wal-Mart Leads "Black Thursday" Charge
Oct 29, 2014, 9:57 PM
"Bear Selfies" Fad Could Turn Deadly, Warn Nevada Wildlife Officials
Oct 28, 2014, 12:00 PM
The Surface Mini That Was Never Released Gets "Hands On" Treatment
Sep 26, 2014, 8:22 AM
ISIS Imposes Ban on Teaching Evolution in Iraq
Sep 17, 2014, 5:22 PM
More Blog Posts
Copyright 2015 DailyTech LLC. -
Terms, Conditions & Privacy Information