Weber's Thoughts on Cell

Ever since its official introduction, we've been going around asking everyone we ran into about their thoughts on IBM/Sony/Toshiba's Cell microprocessor, and Fred Weber was no different.  Surprisingly enough, Weber's response to the Cell question was quite similar to Justin Rattner's take on Cell.  Weber saw two problems with Cell:
  1. Cell is too far ahead of its time in terms of manufacturing, and
  2. Cell is a bit too heterogeneous in its programming model, referring to Cell's approach as both asymmetric and heterogeneous (we'll explain this in a bit).
As we concluded in our Cell investigation, the approach to microprocessor design of having one general purpose core surrounded by several smaller cores is not one that is unique to Cell.  Intel has now publicly stated that this heterogeneous multi-core approach is, at a high level, something that they will be pursuing in the next decade.  The problem is that to be produced on a 90nm process, the individual cores that make up Cell has to be significantly reduced in complexity, which Weber saw as an unreasonable sacrifice at the current stage. 

The next problem that Weber touched on was the Cell approach to a heterogeneous multi-core microprocessor.  To Fred Weber, a heterogeneous multi-core microprocessor is one that has a collection of cores, each one of which can execute the same code, but some can do so better than others - the decision of which to use being determined by the compiler.  Weber referred to his version of heterogeneous multi-core as symmetric in this sense.  Cell does not have this symmetric luxury; instead, all of their cores are not equally capable and thus, in Weber's opinion, Cell requires that the software needs to know too much about its architecture to perform well.  The move to a more general purpose, symmetric yet heterogeneous array of cores would require that each core on Cell must get bigger and more complex, which directly relates back to Weber (and our) first problem with Cell that it is too far ahead of its time from a manufacturing standpoint. 

Index The K8 is here to stay


View All Comments

  • ceefka - Sunday, April 03, 2005 - link

    I assume this wafer and die stacking will also be used for increasing the GB's per RAM-stick. What else when 64-bit OSs and apps have become the standard? Is there any word from memory manufacturers on that? Reply
  • Athlex - Saturday, April 02, 2005 - link

    AMD seems to be missing the point of pitting Turion against Centrino. Intel's Centrino package requires a P-M, Intel chipset, and Intel wireless. Since most people don't know the diff between P-M and Centrino it's a brilliant way for Intel to move more silicon.

    Also confusing why AMD is using the same packaging for Turion CPUs as they do for normal A64 CPUs. The lowest-power XP-Ms use the smaller socket 563 (Sharp and Averatec systems for example). AMD already has a spec for a smaller 'socket 638' A64, seems like that should be the thin and light version.. C'mon AMD, let's see a real thin and light K8 notebook!
  • suryad - Friday, April 01, 2005 - link

    I agree...I cant wait for a dual core FX proc with each core clocked @ 3 GHz...think what a monster system that would be...yikes!! Reply
  • ceefka - Friday, April 01, 2005 - link

    #23 What exactly is ILP/TLP ?

    ILP Instruction Level Parallism
    TLP Thread Level Parallism

    It is explained in one of the CPU articles here on AT.

    Happy surfing.
  • BlvdKing - Friday, April 01, 2005 - link

    #26 - I would be torn between an IBM notebook and Turion too. IBM notebooks are amazing - full of features and so durable. Reply
  • cryptonomicon - Thursday, March 31, 2005 - link

    incredibly interesting article by anand.

    it seems like this is the kind of stuff you can only find at anantech.. the info is so in depth right from the source.
  • Regs - Thursday, March 31, 2005 - link

    Thank's Anand. With all this Intel news running about, it's good to see AMD isn't just planning to be a bench warmer. Reply
  • Xunilla - Thursday, March 31, 2005 - link

    #25 -- I agree, that is making a generalization that doesn't necessarily apply across the board. Reply
  • Xunilla - Thursday, March 31, 2005 - link

  • phaxmohdem - Thursday, March 31, 2005 - link

    I really want to see what kind of Turion notebooks spring forth. It will take a lot though to change my decision on the IBM T42 as my next notebook though. Reply

Log in

Don't have an account? Sign up now