Project Larrabee

Intel describes project Larrabee as a “highly parallel, IA-based programmable architecture” that will be “easily programmable using many existing software tools, and designed to scale to trillions of floating point operations per second...” Intel goes on to say that “[the Larrabee architecture] will include enhancements to accelerate applications such as scientific computing, recognition, mining, synthesis, visualization, financial analytics and health applications.”

Intel would not say any more about project Larrabee, other than to confirm that it has begun planning products based around the architecture. Looking at the statements above, we can deduce one thing already.

Being based on IA, we expect Larrabee to implement some instance of the x86 ISA, but the real clue comes from the 3 TFLOPs performance target. Let’s get this straight: Larrabee is a super wide, FP powerhouse architecture that can do a better job at accelerating scientific computing applications than current Intel CPUs? Larrabee sure does sound a lot like a high end GPU.

Intel didn’t attach a timeframe to these Larrabee projects other than to say that they were in the initial planning stages now. It is highly unusual for Intel to come out and say that it is working on a very vague new architecture, we can only assume that there is some sort of political motivation behind the Larrabee disclosure.

Larrabee will be an important architecture to watch, we expect to hear more about it at this fall’s IDF back in the US.

More Vague Projects from Intel

Intel announced two other new projects that it’s working on, both of them less vague than the Larrabee announcement but still lacking in details. Pat Gelsinger unveiled Intel’s Tolapai project, a system on a chip (SoC) architecture for the enterprise market. The magic year for Tolapai is 2008, where Intel expects a high level of integration to reduce the footprint of the chip by up to 45% and power consumption by approximately 20% compared to “a standard four-chip design”. We can only assume that four chip design means CPU, North Bridge, South Bridge and Graphics. The 2008 introduction makes sense given that in 2008 Intel will introduce Nehalem which will offer configurations with integrated North Bridge and optional integrated graphics.

Intel will also be working on a SoC designed for the consumer electronics market in 2008, lending further credibility to many of AMD’s reasons for acquiring ATI. The real question is if Intel will be able to pull off market dominance in the CE market without acquiring an external graphics firm.

Final Words

We’re expecting more announcements out of Intel in the next two days, so stay tuned for continued coverage of IDF Beijing.

The Long Awaited Penryn Update
Comments Locked


View All Comments

  • Roy2001 - Tuesday, April 17, 2007 - link

    BTW, I am not fan of any brand. I just buy the best. I switched from P3 to Athlon, now I switched back to Core2.
  • DeepThought86 - Tuesday, April 17, 2007 - link

    Wow, this IDF is like deja vu - of AMD's plans that is. Torrenza ripped off, Quad FX ripped off, on-die mem controller ripped off, Fusion ripped off, GPGPU ripped off.

    Even if AMD dies, at least their ideas will live on. Looks like Intel just does a search/replace on AMD's plans and announces it 1-3 years later under a new name.
  • IntelUser2000 - Tuesday, April 17, 2007 - link


    Wow, this IDF is like deja vu - of AMD's plans that is. Torrenza ripped off, Quad FX ripped off, on-die mem controller ripped off, Fusion ripped off, GPGPU ripped off.

    Most of them, if not all aren't even AMD's idea. If you are an engineer at a CPU company such as Intel/AMD, they would think of the ideas long time ago. ALL AMD did was bring to market. Oh wait, they only brought two on the market, and one is completely useless(Quad FX). If Barcelona came before Conroe, people would think the architecture enhancements were copied by Intel. But since Conroe came first, people assume AMD copied Intel. Which does sound pretty stupid to assume.
  • DeepThought86 - Wednesday, April 18, 2007 - link

    Given your username and your comment, I'd say you switch your brain off when you hear the word Intel so there's no point arguing the facts. Intell...droool...goooood
  • Roy2001 - Tuesday, April 17, 2007 - link

    AMD is in real trouble as I can see.
  • Slaimus - Tuesday, April 17, 2007 - link


    The real question is if Intel will be able to pull off market dominance in the CE market without acquiring an external graphics firm

    Didn't Intel acquire 3DLabs? The 3DLabs Realizm line was pretty impressive in terms of features.
  • Missing Ghost - Tuesday, April 17, 2007 - link

    Quote from Wikipedia:
    "3Dlabs was previously a graphics card vendor that developed high-end graphics chip technology and marketed its Wildcat, Oxygen and Permedia computer graphics solutions to design professionals in the CAD and content creation industries. Formerly independent, it became a subsidiary of Creative Labs in 2002, but announced plans to spin in November 2006."
  • Visual - Tuesday, April 17, 2007 - link

    considering AMD were talking about their best k10 also having a 40% better performance than intel's best quad (and at the time that was at lower clocks, wasn't it) in some floating point benchmark, this performance preview of the penryn must sound scary to them...

    i wonder if AMD can implement this sse4 thing or their k10 is too far in development already, as it seems to have quite an effect.
  • wooter - Tuesday, April 17, 2007 - link

    Tolapai is an SoC designed for embedded markets that essentially combines CPU, north/south bridge, and network processor. No integrated graphics sorry.
  • DigitalFreak - Monday, April 16, 2007 - link

    I would hope that Intel would be smart enough to introduce a new workstation chipset that supports dual CPUs but does not require FB DIMMs for this project. Don't see why they'd need more than 4 DIMM slots on the boards.

Log in

Don't have an account? Sign up now