… and Rock gets canceled …

From the NYT, a blog post on the passing of Rock.

Sun has been working on the Rock project for more than five years, hoping to create a chip with many cores that would trounce competing server chips from I.B.M. and Intel. The company has talked about Rock in the loftiest of terms and built it up as a game-changing product. In April 2007, Jonathan Schwartz, the chief executive of Sun, bragged about receiving the first test versions of Rock.
But the two people familiar with Sun’s plans say Rock has met with an unceremonious end. The people requested anonymity, as they are not authorized to speak with the press about Sun’s plans.

Been there, done that. SGI’s Beast and Alien. Would have been interesting chips. Killed because Itanium was going to conquer all. No, wait, I am not kidding … It will … eventually … someday …
It appears little bits of hardware keep falling off the map. And HPC. Its gone. What does this mean to SGE, Lustre, the compiler groups …
Rock was an interesting chip. Sparc’s arent generally considered high performance or high power. This was a massively threaded chip. Some workloads would take to this well.
But the economics of chip building are the same as the economics of accelerators. Target ubiquity.

3 thoughts on “… and Rock gets canceled …”

  1. Lets not forget the Alpha either – a lovely architecture at the time of it’s death (disclaimer: I did work for DEC/Compaq/HP at the time). Intel is only implementing some of its features now (AMD have had some of them for a while, mostly because AFAIK at least of the Alpha guys were snapped up by AMD).

  2. Um, Itanium certainly conquered HP. And obviously SGI’s MIPS interest. Held up a ceiling over SPARC for x86 to squish it from below. Power’s ubiquity in other markets kept it going…

  3. @anon
    HP extended its 8×00 series a few times, as Itanium couldn’t quite do what it was being marketed to do. Eventually … years later … 8×00 died more due to lack of targeting it as a priority platform by ISVs, rather than by CPU-icide on the part of Itanium.
    Itanium conquered Forrest Basket at SGI. Alien and Beast would have been formidable chips well into the first half of this millenium had they not been killed. MIPS died in large part to a massive exodus after critical projects were killed. R12k and R14k were for the most part, die shrinks and respins of R10k. Very little new capability. The compiler is what won the day.
    I do remember being in meetings where I asked management what our “plan B” was. I got nothing but quizzical looks. Plan-B? Who needs a plan B? Itanium will sell millions according to some research firm.

    the art of the sale:  Itanium sales that is ...

    This is the bill of goods sold to SGI (and others). End result, lots of projects canceled. Good very competitive products axed. Itanium “won”.
    For the vendors that had this battle wage internally, this was nothing but a phyrric victory for them. The results of the commitment to Itanium were, in many ways, devastating to the ability of these groups to offer differentiated solutions.

Comments are closed.