• On BNET: Online porn struggles for profits

Business Tech

Read all 'performance' posts in Business Tech
November 16, 2009 1:35 PM PST

Intel unveils supercomputer chip, NEC partnership

by Brooke Crothers
  • 8 comments
Share

Intel on Monday disclosed a version of its Xeon processor line optimized for supercomputers and announced a partnership with NEC to develop future supercomputers.

At Supercomputing 2009 in Portland, Ore., Intel unveiled a future version of its "Nehalem-EX" processor optimized for supercomputers. The six-core chip will run at higher speeds than eight-core versions of the Nehalem-EX processors and will offer advantages for supercomputer specific tasks, Intel said in a statement. Intel also refers to supercomputing as high-performance computing, or HPC.

The chip architecture will offer greater memory speeds and capacity and will allow customers to build single computers or "nodes" with up to 256 such processors, according to Intel. This will be available next year, Intel said.

Intel said Monday that four out of every five supercomputers on the Top500 list published Monday are powered by Intel processors.

Intel also announced that it is partnering with Japan's NEC--that country's largest supercomputer vendor--to jointly develop technologies "that will push the boundaries of supercomputing performance," according to a joint statement.

NEC will use the technologies in future supercomputers based on the Intel Xeon processor and other technologies such as AVX (Advanced Vector Extensions), an extension to Intel's x86 instruction set architecture.

AVX will be used with Intel's upcoming Sandy Bridge microarchitecture due in 2011, according to Intel.

"With NEC further innovating on Intel Xeon processor-based systems, Intel is poised to bring Intel Xeon processor performance to an even wider supercomputing audience, " said Richard Dracott, general manager of Intel's High Performance Computing Group, in a statement.

Fumihiko Hisamitsu, general manager of HPC Division at NEC, said: "NEC's substantial experience in the development of vector processing systems...is a natural fit for taking Intel architecture further into new markets."

A vector processor design can perform operations on multiple data elements simultaneously. Intel Xeon chips are good at scalar processing, which handles one data item at a time.

The initial focus of the collaboration will be the development of technology to boost the memory speed and scalability--the latter refers to expanding a system to increase performance or capacity. "Such enhancements are intended to benefit systems targeting not only the very high end of the scientific computing market segment, but also to benefit smaller HPC installations," the two companies said.

NEC will also continue to sell its existing SX vector processor-based products. NEC, for example, currently markets the SX-9 supercomputer.

Originally posted at Nanotech - The Circuits Blog
Brooke Crothers has served as an editor at large at CNET News, an editor at Dow Jones' Asian Wall Street Journal Weekly, and a senior editor at InfoWorld. His CNET blog covers chip technology and computer systems, and how they define the computing experience. He also contributes to The New York Times' Bits and Technology sections. He is a member of the CNET Blog Network and is not an employee of CNET. Disclosure. Follow Brooke on Twitter @mbrookec.
October 30, 2009 7:15 AM PDT

Why iStockphoto embraced Google's Gears

by Stephen Shankland
  • 17 comments
Share
iStockphoto's Kelly Thompson

iStockphoto's Kelly Thompson

(Credit: Stephen Shankland/CNET)

Google's Gears technology may not have caught on widely in the world of Web programming, but operators of the iStockphoto photo sales site have become believers.

Among other things, Gears enables browsers to store data on a local computer, which most notably means that Web applications can be adapted to work even while offline. But for iStockphoto's purposes, it primarily means better performance for people using the site and secondarily lower operating costs for the Getty Images photo sales subsidiary.

"We're not requiring anyone to install Google Gears," the company said on an explanatory Web site. "If you do install Google Gears, though, iStock will work much faster."

Google launched the open-source Gears software in 2007, but so far, the sites that use it--among them Gmail, Google Reader, WordPress, and MySpace--are the exception rather than the rule.

Speed and money
The main motivation for the change was getting a faster site, which benefits iStockphoto's financial results, said Kelly Thompson, iStockphoto's chief operating officer.

"It was 95 percent performance and end-user experience, but let's face it: if I can get more pictures pumped out faster, with more searches, we sell more," Thompson said. "Cutting down a page load time for a user is more valuable to me than the money I'll save on bandwidth."

The company adopted Gears with no prompting from Google, he added. "We did this on our own," with Web programmers jumping on the project because "it's sexy for them to work on it."

iStockphoto activated its Gears support September 30, Thompson said. In the first 16 days of use, Gears saved the company from paying for the transfer of 132GB of data over the network and lightened its Web servers by 8.7 million communication requests--and that's with only 19,000 Gears-installed users, a "tiny portion of our traffic," he said. Those without Gears benefit, too, since iStock's Web servers are unburdened somewhat by those who do use it.

The technology works by locally storing various Web page ingredients--photo thumbnails, JavaScript program code, Cascading Style Sheet formatting files, for example. Older files are flushed periodically so the users' hard drives don't get too cluttered.

"It's a pretty basic implementation right now: the second time a user sees any image or requests a JavaScript file, it loads instantly," Thompson said. One of his developers described it as "the opposite of a drug dealer: the first hit isn't free, (but) every subsequent hit is."

Google is trying to propagate Gears, which is available as a browser plug-in. In a more aggressive move, it built Gears into its Chrome browser. And in the longer term, the HTML5 standard under development reproduces the local storage abilities of Gears, a move that stands to spread the technology more widely.

HTML5 good, IE 6 bad
Thompson is a fan of another HTML5 technology: built-in video. iStock licenses video content, as well as photos and other content, and currently streams it with Adobe Systems' Flash technology.

"We'd love to be able to ditch Flash on the video side, but it's probably a ways out," Thompson said, citing widespread use of Internet Explorer.

IE is widely loathed among Web developers for its slow performance and lack of standards compliance, and even Microsoft wishes that people would upgrade from IE 6, but it's still the single most widely used browser out there, even though Microsoft released it in 2001, just before Windows XP arrived. Microsoft released IE 7 in 2006, and it tried to improve standards compliance and security with the release of IE 8 this March.

People are gradually shifting away from IE 6, but not fast enough for Thompson's taste--or plans.

"We announced we'd drop official support for IE 6 in 2010 back at the beginning of the year. I'm not sure we're going to be able to it: the percentage of users is dropping--just not quite fast enough," he said.

From August 2009 to September 2009, Internet Explorer lost a bit of usage share, compared to rival browsers.

From August (top) to September (below), Internet Explorer lost a bit of usage share, compared with rival browsers.

(Credit: Net Applications)

According to Net Applications statistics, IE 6 is used by 24.4 percent of people on the Web today, followed by IE 7, IE 8, Firefox 3.5, and Firefox 3, in descending order of popularity. Overall, IE has 65.7 percent share of usage.

iStockphoto has more early adopters in its population and therefore different browser preferences. The top five browsers on the site are Firefox, with 37.8 percent; IE, with 34.4 percent; Apple's Safari, with 22.3 percent; Google's Chrome, with 3.4 percent; and Opera, with 1.7 percent.

Among iStockphoto's IE traffic, the majority of people use version 7, but the tide is turning.

"We've seen an almost 2 percent migration of (IE) 6 to 8 in the last 60 days alone. We're hoping Windows 7 will push it even more quickly," Thompson said. "For us, even though it's a shrinking percentage, it still represents over 1 million visits per month, so I can't cut them off at the knees."

"I think we're dominated by geeks, designers, and small businesses, all who move more quickly than the enterprise--not to mention we're 35 percent Mac, with the iPhone about to overtake Linux for third place" among operating systems, Thompson said.

Originally posted at Deep Tech
advertisement
 
Business supplies and services can get expensive. Get smart spending tips and learn about new cost-saving opportunities for your business
October 21, 2009 9:05 PM PDT

Speed and image quality core to Lightroom 3 beta

by Stephen Shankland
  • 7 comments
Share
The Lightroom 3 beta will look familiar to current users, but there are changes under the hood. In addition, Lightroom catalogs can be synchronized with Flickr.

The Lightroom 3 beta will look familiar to current users, but there are changes under the hood. In addition, Lightroom catalogs can be synchronized with Flickr.

(Credit: Adobe Systems)

With the release of its first beta version of Photoshop Lightroom 3.0 on Wednesday night, Adobe Systems is trying to improve the heart of the photographic editing and cataloging software.

"With Lightroom 3, we're looking at a performance and image quality rearchitecture," said Product Manager Tom Hogarty. Those two goals are in opposition, since better image quality demands more computing horsepower. But Hogarty said the software is more responsive when moving among photos, and images look better with new noise reduction and sharpening abilities.

There are other changes, too, though: a revamped import process for importing photos into the software catalog; built-in connections to upload photos to online services and keep them in sync; a more flexible mechanism for laying out photos to be printed; new abilities for stamping watermarks onto photos; and the ability to export photos and music as a video file.

... Read more
Originally posted at Deep Tech
July 15, 2009 7:46 AM PDT

Adobe: why Lightroom image export isn't faster

by Stephen Shankland
  • 12 comments
Share
Updated 3:04 p.m. PDT with further Adobe remarks. I misunderstood the company's position: Lightroom's export behavior reflects engineering priorities.

Earlier this month, I encountered an Adobe Photoshop Lightroom analysis by consultant Lloyd Chambers that expressed surprise with a facet of the image editing and cataloging software: it didn't export photos as fast as possible.

Chambers found that if a photographer wants to produce JPEG or TIF images from the originals in the program, the fastest way is to divide the batch into thirds and export each third separately. Using a modern Mac Pro system, exporting a test set of photos took 351 seconds as one batch and 189 seconds divided into three batches running at the same time.

"The big disappointment is the sluggish performance importing and exporting files, which are tasks that are key to efficient workflow--tasks one has to do over and over. Most of the 'juice' of a Mac Pro goes untapped," Chambers concluded. "You have to load it up with more than one job to force more of the available CPU cores to be used. Lightroom should do this automatically!"

The study caught the attention of others, including Scott Kelby, head of the National Association of Photoshop Professionals. I was intrigued, too, because although many programming chores are difficult to spread across multiple processor cores, exporting photos is trivially easy since it breaks conveniently into independent bite-sized pieces. So I thought I'd see what Adobe had to say for itself.

... Read more
Originally posted at Underexposed
April 1, 2009 10:22 AM PDT

Needs of big firms foretell Intel, Nvidia battle

by Brooke Crothers
  • Post a comment
Share

As Intel prepares to invade Nvidia turf, large companies at the Intel server chip rollout Monday stated--in some cases quite objectively--what graphics chip suppliers need to do to make this technology more palatable for high-performance computing.

Lincoln Wallen, head of research and development at DreamWorks Animation

Lincoln Wallen, head of research and development at DreamWorks Animation

(Credit: Screen capture by Brooke Crothers)

Besides competing in the gaming graphics market, Intel is eying large high-performance computing customers such as Dreamworks Animation (whose "Monsters vs. Aliens" opened last weekend to large box office numbers) for its future Larrabee graphics chip.

Nvidia is already a player in the so-called General Purpose GPU space, which applies graphics processing units (GPUs) to high-performance computing. As described by Nvidia, high-performance computing on the GPU uses a CPU and GPU together in a heterogeneous computing model, with the "sequential" part of the application running on the CPU and the computationally-intensive part running on the hundreds of processing cores built into the GPU.

Application developers have to modify their application to take the compute-intensive kernels (core components of an operating system) and map them to the GPU. The rest of the application remains on the CPU.

At the Intel "Nehalem" server chip event on Monday, a panel of representatives from large companies addressed the issue of CPU versus GPU. Currently, these customers are using CPUs to do their data crunching.

Keith Gray, manager, high performance and technical computing at oil giant BP, spelled out why he has hesitated to use GPUs to date while expressing interest in adopting them in the future. "Our business is about accelerating our development of new seismic imaging research algorithms. At this point we actually believe the level of programming difficulty (and) lack of standardization of application development tools make the move to accelerated computing a bit risky," he said.

CPU (left) versus GPU

CPU (left) versus GPU

(Credit: Nvidia)

Gray continued. "We are watching the evolution of the programming interfaces. Once those are better standardized, once the issues of moving data back and forth from the general purpose system to an accelerator is addressed, we'll be very interested in taking advantage of it," he said.

Lincoln Wallen, head of research and development at DreamWorks Animation, is also looking into exploiting power of the GPU for tasks such as rendering. "We're looking forward to exploit more flexible compute models, perhaps involve more of the graphics processing functionality but tightly coupled with very powerful CPUs to address the particular way in which we generate images, very soft body, lots of geometry generation," he said.

Wallen continued that, as he sees it, Larrabee offers an advantage because of its tight coupling between the CPU and GPU. "The promise of Larrabee with that tight coupling and the programming model offers a great opportunity to start to explore that type of architecture for our particular workloads," he said.

Originally posted at Nanotech - The Circuits Blog
Brooke Crothers is a former editor at large at CNET News.com, and has been an editor for the Asian weekly version of the Wall Street Journal. He writes for the CNET Blog Network, and is not a current employee of CNET. Contact him at mbcrothers@gmail.com. Disclosure.
advertisement
 
Business supplies and services can get expensive. Get smart spending tips and learn about new cost-saving opportunities for your business
March 18, 2009 2:06 PM PDT

Google project promotes Chrome, JavaScript

by Stephen Shankland
  • 13 comments
Share
A fractal tree explorer is one application at Chrome Experiments.

A fractal tree explorer is one application at Chrome Experiments.

(Credit: screenshot by Stephen Shankland/CNET)

Ever since Google launched Chrome in September 2008, Google has been touting how fast its browser can run Web-based programs written in JavaScript. Now the company has launched a site called Chrome Experiments designed to show off what fast JavaScript can enable and to encourage adoption of the browser.

Browser benchmark performance scores make for nice bar charts, but they can be detached from real-world computing needs. Chrome Experiments--which don't require Chrome but sometimes break without it--are a collection of taxing applications written in JavaScript that are designed to be more engaging.

Among the 19 examples so far available: beach balls bouncing from one browser window to another, control-tab animations, fractal trees, and 3D image modeling.

"To build these experiments, we reached out to a number of well-known Web designers and JavaScript developers including REAS, Mr. Doob, Ryan Alexander, Josh Nimoy, and Toxi, who have posted their creations on the site. We are also looking to constantly update the site with new submissions, so developers and designers are encouraged to build their own experiments and submit them through the site," Google said of the site.

JavaScript is used for many mundane features on the Web, but it's also the foundation of more sophisticated Web applications such as Google Docs. Unsurprisingly, given Google's Web application ambitions, the company wants to advance its maturity.

Google wants people to use Chrome.

Google wants people to use Chrome.

(Credit: screenshot by Stephen Shankland/CNET)

So it should be no surprise also that when visiting the site with a non-Chrome browser, you're presented with a warning: "We highly recommend you launch this experiment in Google Chrome. It may run slower, or not at all, in other browsers," then offers a handy Chrome download link.

Google has been advertising Chrome, too, which is unusual for the company. Clearly it has high hopes for the browser.

Of course, all the experiments worked for me in Chrome, but I tried them in several other browsers as well, with mixed results. One of my favorites, Ball Pool, which lets you spray patterned circles that stack up, then shake the window to make them slosh around, was illustrative. On Firefox 3.1 beta 3, it worked fine. On the Safari 4 beta, it worked, but sometimes with edges of balls sliced off. With Opera, the balls moved smoothly, but shaking the window didn't work. With the Internet Explorer 8 release candidate, it didn't work at all.

The "Monster" application at Chrome Experiments performs 3D modeling with JavaScript.

The "Monster" application at Chrome Experiments performs 3D modeling with JavaScript.

(Credit: screenshot by Stephen Shankland/CNET)
Originally posted at Webware
February 5, 2009 2:55 PM PST

Chrome takes new tack for faster JavaScript

by Stephen Shankland
  • 5 comments
Share

Chrome programmers have switched out a third-party software package in favor of their own as part of Google's attempt to speed its open-source browser up more.

The change came with a key component for processing JavaScript text called regular expressions. "As we've improved other parts of the language, regexps started to stand out as being slower than the rest. We felt it should be possible to improve performance by integrating with our existing infrastructure rather than using an external library," according to a Chromium blog post by programmers Erik Corry, Christian Plesner Hansen, and Lasse Reichstein Holst Nielsen.

Thus was born Google's own project, Irregexp, the headline feature in the new developer preview version of Chrome, 2.0.160.0 (release notes). Check the blog post if you're curious about the technical details of Google's choices about native code generation, backtracking avoidance, and intermediate automaton representation.

Previously, Chrome used a supporting software package, or library, called JPCRE, a variation by the Webkit browser project of the PCRE package. That eased compatibility issues by making Chrome behave more like Apple's Safari, which is based on Webkit, but Google thinks it's got the compatibility issue in hand.

"During development we have tested Irregexp against one million of the most popular Web pages to ensure that the new implementation stays compatible with our previous implementation and the Web," the programmers said.

Separately, the programmers said they created a new third version of their JavaScript benchmark. This version specifically exercises regular expressions taken from 50 of the Web's most popular pages.

JavaScript is increasingly widely used to build sophisticated Web applications, including Google Docs and Gmail, for example.

Speed is particularly important because JavaScript is used for interactive aspects of Web pages, where fast response or annoying lags are noticeable by people controlling the application. But it's also widely used for many more mundane aspects of Web pages, so JavaScript speedup helps improve Web browsing performance broadly.

Chrome's JavaScript engine is called V8. Mozilla's Firefox has TraceMonkey, and WebKithas Squirrelfix Extreme. Opera hopes to outdo all those with its own new JavaScript engine, called Carakan.

More changes are coming to V8, though, and Google will detail some at its May developer conference, Google I/O. One session there will focus on the software, including "initiatives that will propel V8 to the next performance level," according to the session notes.

Separately, Google also released the new version 1.0.154.46 of Chrome for both its stable and beta version users on Wednesday. That version fixed a security problem and an issue with Chrome's incognito mode.

Originally posted at Webware
December 9, 2008 11:40 AM PST

Firefox, Chrome virtually tied for JavaScript speed

by Stephen Shankland
  • 31 comments
Share

The latest version of Google's Chrome is only a smidgen slower than Mozilla's Firefox on the SunSpider test of JavaScript performance.

Google's Chrome now is only a smidgen slower than Mozilla's Firefox on the SunSpider test of JavaScript.

(Credit: CNET News)

On Tuesday, Mozilla released Firefox 3.1 beta 2 and Google released Chrome 0.4.154.33, so it's time for the latest installment of JavaScript performance testing.

Here's the highlight: Though Firefox remains the leader on the SunSpider test, with a score of 2,110, Chrome edged very close with 2,140. A lower score is better; because of some variation in results, the numbers I quoted are an average of several runs.

Firefox and Chrome aren't the only browsers out there, but they're interesting to compare for a few reasons. First, they're both open-source projects launched to shake up the establishment with new ideas about the browsing experience. Second, given that philosophical alignment, they're likely to appeal to the same early-adopter crowd. Finally, both have new JavaScript engines, Chrome's V8 and Mozilla's TraceMonkey, which in the new beta is switched on by default.

JavaScript is used to build sophisticated Web sites such as Gmail or Google Docs, but it's also widely used for more ordinary operations, so faster JavaScript performance is desirable. One interesting possibility Google has raised for Web applications though is to bypass JavaScript altogether and use Google's new Native Client software, a research project that lets Web-based software run closer to the speeds of regular software on a computer.

Chrome is making steady gains in Google's JavaScript test; Firefox has a mixed record.

Chrome is making steady gains in Google's JavaScript test; Firefox is much slower and has a mixed record.

(Credit: CNET News)

SunSpider is only one test, though; Google has its own JavaScript benchmark on which Chrome wins hands-down. A glitch in the first Firefox beta kept me from testing it on Google's benchmarks, but the new beta runs again, yielding a score of 182. That's lower than the earlier Firefox 3.1 beta's 235 score, so perhaps something is still amiss. Either way, it's a far cry from Chrome 0.4.154.33's score of 2,635.

The usual caveats: your mileage may vary; I ran these tests on a dual-core Lenovo T61 laptop with 3GB of memory and Windows XP. JavaScript is only one aspect of Web browsing performance, and indeed of browsers overall. Also, this software is still in beta, Chrome in particular a developer beta. Finally, I apologize to those who've been asking, but time constraints have kept me from trying the latest WebKit builds and Opera.

According to Mark Larson, Google's Chrome program manager, Chrome 0.4.154.33 fixes a crash when opening the Options dialog box on 64-bit Windows and some issues using Hotmail. "Hotmail still does not properly recognize Google Chrome," though, Larson said in his announcement of the new version, though it can be fooled into thinking it's using a more mainstream browser. For details, check the instructions on the release notes.

November 18, 2008 9:30 PM PST

Dell brings up the 80-core chip

by Brooke Crothers
  • 16 comments
Share

A Dell slide shown Tuesday was a reminder that a future 80-core processor is still in sight.

Flash back two years to the Intel Developer Forum when CEO Paul Otellini pledged to deliver an 80-core processor in five years.

Otellini said at the time that the chips will be capable of exchanging data at a terabyte a second and that the company hopes to have these chips ready for commercial production within a five-year window.

Michael Dell referred to a slide showing an 80-core chip Tuesday at SC08, a conference in Austin, Texas, focused on high-performance computing.

The trend of packing more compute power into small supercomputing enclosures "is really driven by what's going on in microprocessors. The x86 revolution continues. You see more and more cores. Increased performance. But also without more power required," he said, speaking during the keynote.

Dell slide shown Tuesday at SC08

Dell slide shown Tuesday at SC08

(Credit: Dell Computer)

In various venues, Intel has spelled out its intention to bring out many-core processors including its upcoming Larrabee graphics chip and future server processors that may reach 32 cores. Currently, Intel's Dunnington processor gets the prize (at Intel) for the most cores: six. Sun Microsystem's "Rock" processor will have 16 cores.

Originally posted at Nanotech - The Circuits Blog
Brooke Crothers is a former editor at large at CNET News.com, and has been an editor for the Asian weekly version of the Wall Street Journal. He writes for the CNET Blog Network, and is not a current employee of CNET. Contact him at mbcrothers@gmail.com. Disclosure.
November 18, 2008 11:55 AM PST

Dell taps game box, Nvidia for supercomputing

by Brooke Crothers
  • Post a comment
Share
The 'Stallion' Visualization Cluster

The 'Stallion' Visualization Cluster.

(Credit: Dell)

Democratize IT. A banal catch phrase until you see off-the-shelf gaming boxes from PC maker Dell being used for visual supercomputing.

CEO Michael Dell showed the "Stallion" Visualization Cluster at the Texas Advanced Computing Center (TACC) running on standard Dell XPS gaming machines during his keynote Tuesday at SC08, a conference in Austin, Texas, focused on high-performance computing. (The keynote was streamed over the Web.)

The Stallion "visualization wall" uses XPS boxes to power 30-inch Dell displays. "The largest display of its kind in the world, at 307 million pixels," Michael Dell said.

"Literally these are gaming systems. We just leverage what was going on the commodity technology market," said Kelly Gaither, associate director at TACC, speaking as part of Dell's keynote address.

Dell is also looking to Nvidia to democratize supercomputing and bring it down to the desktop. "Advances in graphics technology are actually creating some new opportunities in supercomputing," Dell said. "We announced today that we're extending our partnership with Nvidia to advance their CUDA architecture in Dell's precision workstations," he said.

"So this really is the supercomputer on your desk. Adding one (Nvidia) Tesla card to Dell Precision workstations delivers a theoretical performance of 1 teraflop," he said. "That's seven times higher than (a high-end) Thinking Machines (supercomputer) back in 1993." (A teraflop is one trillion floating point operations per second.)

Dell also announced Tuesday that it has teamed up with Intel and Lawrence Livermore National Laboratory (LLNL) to build the Hyperion hyperscale computing environment at LLNL. The National Nuclear Security Administration's Advanced Simulation and Computing Program at the facility expects Hyperion to speed the development and reduce the cost of powerful high-performance computing clusters vital to U.S. Department of Energy and National Nuclear Security Administration missions, including climate change, and other global challenges.

"Hyperion is a test bed that will share those breakthroughs with the entire open-source community," Dell said.

Dell Precision workstation becomes supercomputer with Nvidia Telsa technology

Dell Precision workstation becomes supercomputer with Nvidia Telsa technology

(Credit: Dell)

But Dell's big message was how mass-market and standard commercial computing technologies have invaded the supercomputing space. "429 of the top 500 supercomputers are based on the x86 architecture," Dell said, referring to the computing architecture being used in laptops and desktops today. "What you see here is some of the things from the commercial world in managing large data centers really penetrating very heavily (into high-performance computing)."

"Three years ago, using our blade chassis, we put 240 cores in a full-size 42U rack with 2.8GHz CPUs, and that was 1.3 teraflops of theoretical peak performance per rack. Today, we get 512 cores in a 42U rack with 3.3GHz CPUs, and that's 6.82 teraflops per rack," Dell said. ("U" is a unit of measure that describes the height of equipment used in a rack computer. Typically, 1U equals 1.75 inches.)

More addressable memory space--critical for high performance computing--will come with Intel's Nehalem processor, he said. Nehalem will support memory spaces of up to 1 terabyte (trillion bytes) of system memory, Dell said. Most PCs today support 4 gigabytes (billions of bytes).

In related news, Nvidia announced that Tokyo Institute of Technology (Tokyo Tech) will use Nvidia Tesla GPUs to boost the computational horsepower of Tokyo Tech's Tsubame supercomputer.

Through the addition of 170 Tesla S1070 1U systems, the supercomputer now delivers nearly 170 teraflops of theoretical peak performance, placing it among the world's Top 500 Supercomputers.

"Tokyo Tech is constantly investigating future computing platforms and it had become clear to us that to make the next major leap in performance, Tsubame had to adopt GPU computing technologies," said Satoshi Matsuoka, division director of the Global Scientific Information and Computing Center at Tokyo Tech in a statement.

Originally posted at Nanotech - The Circuits Blog
Brooke Crothers is a former editor at large at CNET News.com, and has been an editor for the Asian weekly version of the Wall Street Journal. He writes for the CNET Blog Network, and is not a current employee of CNET. Contact him at mbcrothers@gmail.com. Disclosure.
advertisement

The yogurt makers of tech: Gadgets to avoid

Don't buy these one-trick ponies--unless you like gizmos that gather dust.

Google wants to unclog Net's DNS plumbing

The Net giant, ever eager for a faster Internet, debuts its Google Public DNS service. With it, Google could become even more central to the Net.

advertisement

About Business Tech

Your destination for the latest news on enterprise-level information technology, from chip research and server design to software issues including programming, open source and patents.

Add this feed to your online news reader

Business Tech topics

Most Discussed



advertisement

Inside CNET News

Scroll Left Scroll Right