Wednesday, January 28, 2015
Search
  
Submit your own News for
inclusion in our Site.
Click here...
Breaking News
Yahoo To Spin-Off Remaining Stake in Alibaba Group
Sony Mobile Reportedly Plans Massive Job Cuts
Apple Sells Record iPhones in Holiday Quarter, iWatch Coming in April
Microsoft Offers Power BI Business Intelligence Tools For Free
Apple Takes Top Spot in China's Smartphone Market
Dell M3800 Mobile Workstation Now Available With 4K Display
Twitter Gets Group Messaging and Video Recording
Microsoft Updates Xbox One Controller Firmware
Active Discussions
New match-3 puzzle game launch now!
Rimage 2000i
Sound card for my Laptop
full screen wide screen
Hi
About the restriction problem of chapter quantity in DVD
Booktype utilities for LiteON and OEM DVD Recorders
downgrade a nero vision 5 project to nero vision 2
 Home > News > General Computing > Improvi...
Last 7 Days News : SU MO TU WE TH FR SA All News

Friday, June 21, 2013
Improving Power and Programming Are Key Factors For Advancing To Exascale Computing


Key challenges the industry needs to overcome in order to reach exascale computing by the end of this decade are power and programming, according to Nvidia.

Theoretically, an exascale system - 100 times more computing capability than today's fastest systems - could be built with only x86 processors, but it would require as much as 2 gigawatts of power - the entire output of the Hoover Dam.

On the other hand, the GPUs in an exascale system built with NVIDIA Kepler K20 processors would consume about 150 megawatts. So, a hybrid system that efficiently utilizes CPUs with higher-performance GPU accelerators is the best bet to tackle the power problem.

However, the ndustry needs to look for power efficiencies in other areas.

Speaking at this week's 2013 International Supercomputing Conference (ISC) in Leipzig, Germany, NVIDIA's Chief Scientist, Bill Dally, said that reaching exascale, would require a 25x improvement in energy efficiency ? 50 gigaflops per watt vs. the 2 gigaflops per watt from today's most efficient systems.

And manufacturing process advances alone will not achieve this goal. At best, this will only deliver about a 2.2x improvement in performance per watt, leaving an energy efficiency gap of 12x that will need to be reached by other means.

Dally believes that a combination of more efficient circuit design and better processor architectures can help close the gap ? delivering 3x and 4x improvements in performance per watt, respectively.

Dally?s engineering team at NVIDIA is exploring a number of new approaches, including utilizing hierarchical register files, two-level scheduling, optimizing temporal SIMT, and other advanced techniques - all designed to maximize energy efficiency in every way possible.

Dally says that second big challenge to overcome is making it easier for developers to program these large-scale systems.

Although parallel computing is not hard - at least in Dally's view - programmers, programming tools and the architecture each need to 'play their positions.' For example, programmers should focus on designing better algorithms - and not worry about optimization or mapping. Leave that to the programming tools, which are much more effective at these types of tasks than humans.

And the architecture - well, it just needs to provide the underlying compute power, and otherwise "stay out of the way."

On top of this, Dally notes that tools and programming models need to continue improving, making it even easier for programmers to maximize both performance and energy efficiency.

Potential improvements Dally is investigating in this area include using collection-oriented programming methods, which will continue to make the process of programing large-scale machines quicker and easier.

By focusing on these areas, Dally believes that exascale computing is within our reach by the end of the decade.


Previous
Next
Facebook Bug Exposes Emails, Phone Numbers Of 6 million Facebook users        All News        Nano Research Technique Allows Petabyte Storage On A DVD
Facebook Bug Exposes Emails, Phone Numbers Of 6 million Facebook users     General Computing News      Apple Prevails In Legal Battle Against Samsung in Tokyo

Get RSS feed Easy Print E-Mail this Message

Related News
NVIDIA Comments On GeForce GTX 970 Memory Allocation Reports
Nvidia Introduces The $200 GeForce GTX 960
Audi to Use Nvidia Tegra X1 For Its Self-Piloted Cars
Nvidia Launches Tegra X1 Mobile Chip, Accelerates Move Into Smarter Automobiles
USITC To Allow Samsung's Case Against Nvidia To Proceed
Samsung Files ITC Complaint Against Nvidia
NVIDIA Unveils Tesla K80 Dual-GPU Accelerator For Data Analytics
Samsung Responds To Nvidia With Chip Patents Lawsuit
NVIDIA Releases VXGI Apollo 11 Demo
Nvidia Reports Increased Quarterly Revenue
Nvidia Pick Your Path Bundle Announced
New Nvidia Driver Enable DSR On Older Graphics Cards

Most Popular News
 
Home | News | All News | Reviews | Articles | Guides | Download | Expert Area | Forum | Site Info
Site best viewed at 1024x768+ - CDRINFO.COM 1998-2015 - All rights reserved -
Privacy policy - Contact Us .