Re: XMOS XC-1 kits are ****pping

>> There was nothing innovative about the design of the Transputer. The
>> device as it was supposed to be (i.e. separate comms and execution
>> planes), rather than the crippled one they ****pped, was similar to
>> designs several people in the UK (and presumably elsewhere) were
>> toying with at that time. The others did not proceed because the
>> economics looked so wrong.
>
>It was used very widely ar the time, because there wasn't anything
>comparable for sale. I even sold several of my modules to hobbyists
>and university students - at =A3500 each!
>
>Some of the customers for my 16 module system were prestigious outfits
>such as BAe, Plessey Roke Manor, GCHQ and Oxford University PRG. It
>delivered 320 MIPS with very good floating-point performance at a
>comparatively low price (about =A313,000 with T800 chips).
>
>I even had inquiries from Russia, indirectly, but it was embargoed
>because of the performance. I did once apply for an ex****t license for
>Russia, to see what happened, and actually got it! I contacted the DTI
>about it; they got very excited, admitted thay had made a mistake and
>insisted that I returned the do***ent. I'm quite sure that Russia did
>get the technology, though. I heard on the grapevine that there were
>companies in Finland that acted as intermediaries.

Selling development boards does not equate to widely used. I saw a number
of experimental machines full of Transputers, engaged in various
activities
from finger print analysis to deblurring number plates on getaway cars.
When I say "full" I mean generally no more than 16. Comms overhead killed
performance for serious array. The only real commercial product use I ever
saw was in the FPS Terreract, and it didn't do a lot for them. To make it
a
practical element in their machines they needed an ASIC to expand the 4
****ts, so a hypercube could be constructed. Then the comms overheads still
killed its ability to do any serious processing. The real processing was
handled by a bunch of Weitek floating point chips, and early video DRAMs.
The DRAMs allowed vectors to be streamed through the floating point units,
using the serial ****t originally intended for streaming pixels to a
display. By the time they'd finished burying the Transputer amongst that
lot I wonder how much value they thought it brought to the final product?
I
the FPS guys I talked to at that time indicated they probably would not
have used the Transputer if they were starting again.

Regards,
Steve