[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [oc] Beyond Transmeta...



On Wed, 2003-02-12 at 23:23, Holger Baxmann wrote:
Am Mittwoch, 12.02.03, um 17:17 Uhr (Europe/Budapest) schrieb Ivan 
Guzvinec:

> On Mon, 2003-02-10 at 22:03, Jim Dempsey wrote:
>> Quantum Computing, tertiary number base, optical processing
>> or existing (traditional) technology are all implimentation issues.
>> The problems for bit-stream processing is a routing problem of
>> the bitstreams to the proper combinatorial sections of the processor.
>> This is the same problem regardless of the implimentation.
>>
>> A few posts back in this thread I made the analogy of the newspaper
>> printing press. Popular microprocessor design is more like a sheet-fed
>> press ca-chunk, ca-chunk, ca-chunk. The bitstream processor would
>> be more like a web press, shhhhhhheeee data streaming through the
>> process being handled and redirected many times.
>>
>> Jim Dempsey
>
> As for the problems of bit-stream processing maybe this analogy mighy 
> be
> applied: I see something like "SimCity". Consisting of simple building
> blocks that build into a complex system such as one created in the 
> game.
> And you "view" the bits as "sims" moving along their "path of
> calculation". Traffic controller can then use statistics to generate
> "shortest/fastest path" between sections of the processor and route
> streams properly using switching/semaphores/etc (if destination of the
> stream is known??!?).
> ... again, just a thought.

But, in difference to 'sims': it is not necessary to keep the single 
identity for every bit while it is traveling the system, is it ?
Please, extrapolate.
--
Ivan Guzvinec <ivang@flextronics.si>
Flextronics d.o.o.