"In a climate-controlled room at the IBM Thomas J. Watson Research Center in Yorktown Heights, N.Y., one of IBM's newest supercomputers quietly cogitates. Blue Gene/W, or BGW, unveiled last June, boasts a processing speed of 91.29 teraflops (one teraflop is a quadrillion operations per second) and comes in second on the 25th annual Top 500 list of supercomputers compiled by the University of Tennessee. Number one on the list is Blue Gene/L, the famous massively parallel supercomputer located at Lawrence Livermore National Laboratory in Livermore, Calif. As its name implies, a Blue Gene computer is a bioinformatics machine. When the full power of those 91 teraflops are focused on a biological problem, its use is much like a telescope searching the skies as it probes the microscopic biological world."
News.Com Blue Gene/L tops its own supercomputer record
"Lawrence Livermore National Laboratory and IBM unveiled the Blue Gene/L supercomputer Thursday and announced it's broken its own record again for the world's fastest supercomputer.
The 65,536-processor machine can sustain 280.6 trillion calculations per second, called 280.6 teraflops, IBM said Thursday. That's the top end of the range IBM forecast and more than twice the previous Blue Gene/L record of 136.8 teraflops, set when only half the machine was installed."redux [09.07.05]
Bio-IT World Blue Gene Used to Examine Dewetting in Protein Folding
"Researchers at IBM’s Thomas J. Watson Research Center and Columbia University have used a small (single-rack) Blue Gene system from IBM to discover a new phenomenon having to do with the folding of a melittin protein in water.
Specifically, the Blue Gene system’s processing power allowed the researchers to perform simulations that were impractical to run on previously available high-performance computing systems."News.Com IBM's full-court supercomputer press
""It's a big game changer," says Ajay Royyuru, a computational biologist in charge of IBM's life science research. "We now have the ability to think about the whole system, not just parts. We can start to build a robust model of how a system is behaving or misbehaving and ask, 'How can I correct it?' If I knock a gene out, how will the whole system behave?"
The ability to simulate how an entire system behaves is the modus operandi of Blue Gene, which ties the brute strength of tens of thousands of processors with a sophisticated architecture that lets processors share information on the fly. The record-breaking versions are running in elite institutions such as the Lawrence Livermore Lab--its behemoth consists of 32 e-Servers lashed together--and Japan's Advanced Institute of Science and Technology, but the basic 5.7-teraflop "e-Server" system is available for roughly $2 million. IBM is also renting space on Blue Gene systems for about $10,000 a week."redux [08.19.05]
InternetNews.Com IBM Donates Supercomputer Resources
"IBM and Argonne have agreed to augment Argonne's Innovative and Novel Computational Impact on Theory and Experiment (INCITE) computer capacity with compute cycles on IBM's Blue Gene "BGW" supercomputer system at IBM T.J. Watson Research Center in Yorktown Heights, N.Y."
""What we're really talking about about is over 1 million CPU hours over the course of a year, running 24 x 7, minus maintenance and upgrades," Herb Schultz, a Blue Gene manager at IBM, told internetnews.com. "Depending on the project, the workload could take 10 racks at a time. We're trying to learn what these kinds of applications are all about, so it's a good exercise for us." Each of the twenty racks at the IBM facility has 2,048 CPUs."redux [06.21.04]
Bio-IT World IBM plans second Blue Gene supercomputer
"The latest list of the top 500 performing supercomputers in the world was released today and it shows IBM has placed two Blue Gene/L prototype systems in the top 10. Additionally, clusters are now the most common supercomputer architecture."
"Coming in at number four and eight were the Blue Gene/L DD1 and DD2 Prototype systems. The systems’ performance benchmarks were 11.68 teraFLOPS sustained speed and 16 teraFLOPS peak performance for the DD1 and 8.66 teraFLOPS sustained, 11.47 tearFLOPS peak for the DD2."redux [02.20.04]
News.Com IBM plans second Blue Gene supercomputer
"IBM will install a second Blue Gene/L supercomputer as part of a radio telescope project in the Netherlands, the company plans to announce Monday.
The supercomputer will be used for a new radio telescope project called Lofar, short for low frequency array, run by a Dutch organization called Astron. The system, which is expected to be complete in 2005, will run the Linux operating system, use about 12,000 processors and perform more than 30 trillion calculations per second, sources familiar with the plan said."redux [11.15.03]
News.Com IBM gives glimpse of Blue Gene performance
"IBM on Friday talked up its Blue Gene/L supercomputer, the first module of which is a relatively small, dishwasher-size machine that can perform 1.4 trillion calculations per second.
The performance is enough to make the machine the world's 73rd fastest supercomputer, according to a ranking of the top 500 to be released Sunday. By the time IBM has upgraded the box's 512 chips, each with two processors, and linked it with another 127 identical systems in 2005, Big Blue hopes to take the top spot."redux [09.19.03]
The Economist Soul of a newer machine
"WHATEVER happened to Blue Gene, IBM's ambitious attempt to build the world's fastest computer? The project, launched in 1999, called for the construction of a "massively parallel" computer with over 36,000 processing chips, each containing 32 processing cores roughly equivalent in power to a desktop PC. Harnessing all that computing horsepower--more than one petaflop, or 1,000 trillion floating-point calculations per second--would, it was hoped, allow scientists to simulate the folding of a protein, an extraordinarily demanding task which might help to streamline the discovery of new drugs. The idea was to achieve all of this within five years--something that even enthusiasts thought ambitious.
Four years on, the chips that will power the first Blue Gene computer are now being manufactured and tested. But the plans have changed somewhat."redux [05.08.03]
News.Com IBM details Blue Gene supercomputer
""Blue Gene is a completely oddball, you've-never-seen-anything-like-this-before design," said Illuminata analyst Jonathan Eunice. "It is not custom everything, (but) it is still very exotic compared to anything you can buy.""
"IBM already has spent more than the original $100 million budgeted for the project and won't meet its 2004 goal for the ultimate machine, but the company has made progress bringing its ideas to fruition."redux [02.11.03]
AustraianIT Blue Gene to crunch biotech's biggest numbers
"THE first version of IBM's revolutionary Blue Gene chip will roll off the production line this quarter, Ajay Royyuru, head of IBM's Computational Biology Centre, has revealed."
""We plan to build a 512-node prototype Blue Gene machine in our Watson Research Centre, in New York, where I am located, hopefully before the end of the year.
Then we will build a 64,000- node Blue Gene machine and deliver it to the Lawrence Livermore laboratory by late 2004, or early 2005."redux [10.24.02]
News.Com It's Linux for IBM supercomputer project
"Linux will be the main operating system for IBM's upcoming family of "Blue Gene" supercomputers--a major endorsement for the OS and the open-source computing model it represents."
""We had two choices of operating systems for the Blue Gene family, either use a special purpose system or Linux," Bill Pulleyblank, director of Exploratory Server Systems at IBM Research, said in a statement. "We chose Linux because it's open and because we believed it could be extended to run a computer the size of Blue Gene. We saw considerable advantage in using an operating system supported by the open-source community so that we can get their input and feedback.""redux [07.13.01]
Wired Magazine Gene Machine
""Ambuj Goyal, IBM Research's general manager for software, solutions, and strategy, was more ambitious than that. Why not build a machine to model molecular dynamics using general-purpose chips rather than specialized ones? That way you'd produce a prototype for a whole new family of supercomputers. Not only would it be great technology development, it would be great marketing, too. Whereas the Department of Energy has the greatest interest in top-end supercomputing - with its need to understand how nuclear weapons work - focusing on the life sciences rather than the death sciences could make supercomputing more widely appealing. What's more, a biology program would be a way of telling one of the newest markets for big iron - the post-genome biotech world - that IBM took its interests seriously. "We believe that the life sciences are going to be a rapidly growing area," says Blue Gene project manager Bill Pulleyblank, "a huge growth area for IBM.""
“Bioinformatics will be at the core of biology in the 21st century. In fields ranging from structural biology to genomics to biomedical imaging, ready access to data and analytical tools are fundamentally changing the way investigators in the life sciences conduct research and approach problems. Complex, computationally intensive biological problems are now being addressed and promise to significantly advance our understanding of biology and medicine. No biological discipline will be unaffected by these technological breakthroughs.”BIOINFORMATICS IN THE 21st CENTURY
the panda's thumb
bioinformatics.org / nodalpoint / flags and lollipops / on genetics / a bioinformatics blog / andrew dalke / the struggling grad student / in the pipeline / gene expression / free association / pharyngula / the personal genome / genetics and public health blog / the medical informatics weblog / linuxmednews / nanodot / complexity digest /
nsu / nyt science / bbc scitech / newshub / biology news net /
informatics review / stanford / bmj info in practice / bmj info in practice /
look snazzy and support the site at the same time by buying some snowdeal schwag !
valid xhtml 1.0?
This site designed by
Eric C. Snowdeal III .