Return to the archive index

Re: Crusoe versus StrongArm, Super H, etc.

They can develop software that will turn this chip into a JVM, a
Java Virtual Machine. (Hear the cash registers now? :-)

Unless this chip is considerably faster/cheaper than a Sparc/Alpha
or Intel processor, I would not consider buying it - I'd just buy
the native product. (Okay, there may be a reason why I would want
one mutable chip in place of three or more native chips.) Java has
a ton of support from developers and from several major corporations.
Its biggest obstacle is speed: Speech into the Java Media Something-
orother is appallingly slow, adding half a second or so to latency
before it gets into the processing stream. A hardware JVM chip is best
but this is a good alternative, or so it seems to me.

In article <200001222040.MAA10646@coraki.stanford.edu>,
Vaughan Pratt  <pratt@CS.Stanford.EDU> wrote:
>
>>I would say the "initial Crusoe processors have been tuned..."  The two 
>>processors announced have significant hardware differences (implied by 
>>the white paper, anyway).  I see no reason to believe that future 
>>processors won't also have significant hardware differences. 
>
>Right, I talked about that possibility at the end of my message.  But now
>that I think about it, I can't decide what the next architecture for
>them to take on should be.  PPC?  Sparc?  Alpha?  Which would make the
>most sense financially for Transmeta?
>
>It is quite conceivable that any effort they might put in that direction
>might make them more money if spent instead on broadening and otherwise
>improving their line of x86-targetted processors.
>
>Vaughan
>

-- 
Alex Vrenios
Ph.D. Student
Computer Science Dept.
Vrenios@enuxsa.eas.asu.edu