'Painter' supercomputer comes to life at Louisiana Tech

March 26, 2009
This is LONI's "Painter" supercomputer at Louisiana Tech University. Credit: Louisiana Tech University

The Louisiana Optical Network Initiative (LONI) gained another 4.77 teraflops of computing power recently with the activation of the "Painter" supercomputer housed in the Data Replication Center at Louisiana Tech University.

Painter is the fifth of six Dell Linux Clusters that comprise the LONI system, a state-of-the-art fiber optics network running throughout Louisiana, and connecting Louisiana and Mississippi research universities to one another as well as National LambdaRail and Internet2.

"This supercomputer will help support scientific calculations and data processing by several different disciplines on the Louisiana Tech campus," says Dr. Zeno Greenwood, associate professor of physics. "Painter will give us much, much more and incredibly faster computing than we ever had previously."

Painter's 4.77 teraflops will contribute to the 85 teraflops of total computing power LONI will have upon activation of all its state-wide nodes.

is an acronym meaning trillion floating point operation per second; a measure that describes how many multiplications can be performed within one second. To put it in perspective, Painter's performance power is nearly 500 times greater than that of an average desktop PC.

Louisiana Tech's research efforts, both on and off campus, will greatly benefit from the power and speed generated by Painter.

"[Tech's] high energy physics group will do theoretical simulations and perform large, complicated analyses with Painter," says Greenwood. "This will be in support of the giant coming on line this summer at CERN (European Organization for Nuclear Research)."

The is named in honor of Jack Painter, professor emeritus of civil engineering, who was instrumental in bringing the LGP-30, Louisiana Tech's very first computer, to the campus in the 1950's. With a clock rate of 120 kHz, the LGP-30 was a binary computer, performing without an operating system and at a rate of up to 400 additions per second, which is 12.5 billion times slower than the Painter supercomputer.

Source: Louisiana Tech University

Explore further: World's first teraflop supercomputer decommissioned

Related Stories

New computer does Windows 3,000 times faster

June 18, 2008

The most powerful Windows-based computer in Europe is being installed in Sweden's Umeå University. Nicknamed "Akka", the supercomputer incorporates IBM Power microprocessors, Cell Broadband Engines and Intel processors and ...

IBM To Build Supercomputer For U.S. Government

February 3, 2009

(PhysOrg.com) -- The U.S. Government has contracted out IBM to build a massive supercomputer bigger than any supercomputer out there. The supercomputer system, called Sequoia, will be capable of delivering 20 petaflops (1,000 ...

Recommended for you

Roboticists learn to teach robots from babies

December 1, 2015

Babies learn about the world by exploring how their bodies move in space, grabbing toys, pushing things off tables and by watching and imitating what adults are doing.

Xbox gaming technology may improve X-ray precision

December 1, 2015

With the aim of producing high-quality X-rays with minimal radiation exposure, particularly in children, researchers have developed a new approach to imaging patients. Surprisingly, the new technology isn't a high-tech, high-dollar ...

Making 3-D imaging 1,000 times better

December 1, 2015

MIT researchers have shown that by exploiting the polarization of light—the physical phenomenon behind polarized sunglasses and most 3-D movie systems—they can increase the resolution of conventional 3-D imaging devices ...


Adjust slider to filter visible comments by rank

Display comments: newest first

5 / 5 (1) Mar 27, 2009
"To put it in perspective, Painter's performance power is nearly 500 times greater than that of an average desktop PC."

Or 4 to 8 high end graphics cards, provided your algorithm is embarrasingly parallel enough to fully utilize them.
1 / 5 (1) Mar 30, 2009
Or just get two NVidia Tesla systems, each with 960 cores, and 250 times faster than a standard PC.

My system has two GTX280 GPU's, each with 240 cores,.. I may have to play with CUDA and PhysX.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.