2 Comments

Summary:

IBM has taken the storied Cell processor and amped up both the processing capacity and production. IBM says it will produce the Cell processor at 65 nanometers and start popping it into servers to create a “supercomputing experience for the masses.” That is, if the masses […]

IBM has taken the storied Cell processor and amped up both the processing capacity and production. IBM says it will produce the Cell processor at 65 nanometers and start popping it into servers to create a “supercomputing experience for the masses.” That is, if the masses can afford the $10,000 price tag for an adapter card and have a need to perform high-end analytical functions or lots of video transcoding.

What’s cool for consumers (and a real death knell for startups) comes from IBM’s Jim Comfort, a VP in IBM’s systems and technology group, who told EETimes, “IBM plans to continue to use videogame consoles as the vehicle for driving the first iterations of new high-end chips in large volumes that later become available to high-end computing systems in lower volume uses.”

Like software, chips are now sneaking from consumer’s living rooms into the enterprise. Funny what you can learn from Web 2.0. But it also raises the barriers to entry for anyone with a chip startup. Consumers won’t pay the margins enterprise gear makers will, so the way to make profits is on volume — hard for a startup to hit without a lot of cash upfront.

You’re subscribed! If you like, you can update your settings

  1. Supercomputers: Now Less Super, More Computer – GigaOM Tuesday, June 17, 2008

    [...] One of the reasons Roadrunner is so unique is that IBM had to develop special software that would work with both types of processors. The Cell architecture was designed for the PlayStation and is now morphing into a performance chip for other applications, a process that IBM is likely to follow in the future. [...]

  2. Nvidia to Offer Its Chips in the New Cray Desktop – GigaOM Tuesday, September 16, 2008

    [...] chips trying to muscle in on its scientific computing turf in the high and low end. Chips such as IBM’s cell processor or GPUs from AMD or Nvidia are being dolled up with programming tools to take on scientific [...]

Comments have been disabled for this post