Greg Lindahl writes "The Forecast Systems Laboratory, a divison of NOAA, selected HPTi, a Linux cluster integrator, to provide a $15 million supercomputing system during the next 5 years. The computational core of this system is a cluster of Compaq Alphas running Linux, using Myrinet interconnect. Check outwww.hpti.com for information on the company. "

Apple's G4, launched in a blizzard of savvy hype, heralds the second Age of Apple. Although this one is very different from the first (for one thing, Apple is a lot greedier), Apple's string of successes says a lot about the fact that individual creativity will beat out corporate marketers every single time.

Red Hat is now worth serious money. Exactly how much changes hour by hour. Check the Red Hat Wealth Monitor for up-to-date information. This page is by no means anti-Red Hat, and it has a bunch of commentary on it that's well worth reading. We also got some excellent comments about the Red Hat IPO from professional investors Jay Roseman and Frederick Berenstein of The Linux Fund, and a perceptive note from "an anonymous insider" (he'd lose his job if we published his name) that may help put Red Hat's IPO in perspective -- and serve as a cautionary tale for other Linux and/or Open Source-related companies that decide to sell stock to the public. (Lots more below.)

anaZ writes " SGI today announced that it will install the company's first 128-processor Linux(R) cluster at the Ohio Supercomputer Center." It seems SGI will be using 32 Quad Xeon boxes (1400L). I wonder (and hope!) it is just the first of many.

Colin Guillas writes "As we know, a single user posing as using a Russian supercomputer has been cracking distributed.net keys in the gigakeys range... but it turns out to be a hoax, as stated by nugget himself. Also, there are clues to the identity of this cracker, as written by Maxxim Kochegarov at this site . "

Sean Mooney writes "CNN is reporting that $1000 pc that is 60,000 times faster than a PII 350 may be on the market within 18 months. Star Bridge Systems is making the field programmable gate array (FPGA) computer. These are the same guys who are making HAL, reported earlier. " I'll believe that when I see it. Although I can't think of a better way to break Moore's Law.

Henry Pang writes "The New York Times has this interesting article. It seems like people of China will not be able to buy Playstation 2 next year. " It's The Times, so you need a free account to read it, but it talks about the Playstation being a supercomputer by US standards. Also notes that within 12 months, a $1200 Merced based PC would also be illegal.

An anonymous reader sent us a link to an InfoWorld story where you can read about IBM slapping together an Open Source Supercomputer capable of matching a Cray on PovRay benchmarks. It's basically just a cluster of Xeon based Netfinitys. Smooth.

VanL writes " A previously unknown company has come up with a supercomputer design using programmable logic components. If this is right, this might be another case of a garage inventor changing the computing paradigm. In the meantime, they are claiming incredible things from their demo computer: It is the worlds fastest computer (3-4x faster than IBM's Pacific Blue, and 10x faster than a Cray); it is fault-tolerant enough that you could shoot a bullet through it and it would keep on working; it will run any operating system out-of-the-box; and it is the size of a normal desktop computer and runs off household current. They call it HAL. ;) Check out the press release, a news story, and a more detailed description of the company and the technology here."

EngrBohn writes "They've changed the contents of the web page! This morning, Nicolai Langfeldt [janl@math.uio.no], a fellow subscriber to the Beowulf mailing list, informed me that they changed all references to Linux such that they now read Digital-UNIX: This is odd. The page appears to have been changed, it reads 'Digital-Unix' all over, instead of 'Linux'. The reference is still the same. :-("

Mr. Daemon not only has a cool nick, but he also writes "Compaq and Mitsubitshi are going to build a Beowulf of 130 Alphas to Japan's Institute of Physical and Chemical Research." It's cool because its Beowulf, and its cool because its good to see Compaq pushing Alphas forward.

PDG sent us a link to a zd article where you can read about the new Supercomputer that SGI is announcing. The article is thin on details. Presumably more will be released soon. Update: 11/10 03:45 by CT : SGI has released more information- you can read their little Press Release about BlueMountain- their beast that has taken the top spot on the big list of super computers.

Claes Månsson writes "While looking at faster super computers than the recently announced avalon, I came across this. The CPlant Cluster at Sandia National Laboratories (ranked #98 on the TOP500 list), is "using Linux as base OS. Each resource node runs a customized version of Linux." It seems that it is not only the beowulf style super computers that are making use of Linux... "

Kaos writes "IBM said it had been selected by the National Partnership for Advanced Computational infrastructure (NPACI), a leading U.S. academic computer consortium, to supply the first supercomputer capable of handling a trillion calculations per second." Sounds just the sort of thing we need to run Slashdot ! ;-)

There's a good story running at over news.com about a astrophysicist building his own supercomputer equivalent by using 140 Alpha boxes, and Linux. This has been mentioned-Avalon is the codename-but the price is so cheap (313,000$US) for this new verison of it that it warrants mentioning. The old cluster, 70 machines, was 315 on the supercomputer list. This might be in the top 100.

Several folks sent this in, but the first one was anonymous. Seems that IBM is working on a New Supercomputer that they are selling to the dept. of energy. 3.9 trillion ops per second. Has anyone ported an RC5 Client to this thing yet? Hello, Dept of Energy? We'd just like a few days please...

One part of the Los Alamos new supercomputer, Blue Mountain has shipped. SGI shipped the 512 processer module to Los Alamos. Currently Los Alamos is involved in a race with Lawrence Livermore and Sandia to build a 100 tflops machine by 2004. Los Alamos will be using their machine to accurately testing the United States' aging nukes. Sandia's box is out in front. It is an Intel-built machine equipped with 9,072 Pentium Pro processors capable of performing up to 1.8 Tflops. However, Intel has dropped out of the super-computer business, and eventually the SGI box at Los Alamos and the IBM box at Livermore will be in true competition.

India's built itself a new supercomputer, the Param 10 000, for $12.5 million. It'll be the main node of a fast network allowing research labs, academic institutions and companies to use it. There's no clear data as to the computational power it will first reach, but it could reach 1000 gigaflops... How large a Beowolf cluster would be needed to reach that?

Kevin Forge sent us a link to an InfoWorld story where you can read that IBM was fined $8M for selling RS6000 to Russia. How long before beowulf falls victim to the same restrictions? Soon we won't be able to export pentium chips because *gasp* if someone gets a thousand of them and Beowulf, they can build a supercomputer...

The NSCA has done some not-very-novel research: build a cluster of computers and solve a parallelisable problem on it. The novelty? Well it runs on NT, so now Microsoft is crowing that NT is wonderfully scalable. As contributor Mark Harrison points out: "I figure if this NT cluster is using NT Server, which it must if it it is using more than 10 TCP/IP connections per node (I know nothing about these parallel systems, but with 124 two-processor nodes, each node must communicate with more than ten other nodes). NT server costs a bunch (about $1,000 per licence, I believe), so the cost is $124,000 for the OS. So much for their tagline, "High-Performance Supercomputing at Mail-Order Prices." How about "Save $123,975 on your supercomputer -- Use Extreme Linux." " Well... it might be time to help Ben Elliston who presented his encapsulation of IP in SCSI in August's Linux Journal which has a higher throughput than ethernet.