🚀 go-pugleaf

RetroBBS NetNews Server

Inspired by RockSolid Light RIP Retro Guy

Article View: comp.sys.transputer
Article #2611

I860's and transputer clones

#2611
From: Patrick Van Renterghem / Transpu...
Date: Mon, 10 Apr 1989 12:59
45 lines
2398 bytes
 
Intel's new device, the I860, will again get a lot of attention in the
magazines. Most of these articles will be written by Intel employees and
are not always very realistic, to say the least. Messages from people who
have used and benchmarked this processor are highly appreciated.
 
I have a question for the network:
 
David Moody told me that Intel would introduce a transputer-like processor
on the market, with a much higher performance and bandwith. Does anyone
know if this is going to be a new chip, or something like this:
 
                   _________
                   | IC012 |
                   ---|-|---
   _________       ___|_|___       _________
   | IC012 |-------|       |-------| IC012 |
   ---------       | I 860 |       ---------
   _________       |       |       _________
   | IC012 |-------|       |-------| IC012 |
   ---------       ---|-|---       ---------
                   ___|_|___
                   | IC012 |
                   ---------
 
where IC012's are comparable with the IMS C012, but interface to a 100 Mbit/s
serial, byte acknowledged, point-to-point link. And manufactured by Intel
of course. Remark that I have given it 6 links.
 
Apart from the design of the IC012's, how difficult would the design around
the 860 be ? All by all, a full-blown version of the I860 would give it a
performance of 5 to 10 times the performance of an T801-30 and a little bit
more for vectorizable applications.
 
Any remarks on the 860, comparing it to transputers ?
 
I personally think plugging 10 transputers together would be a lot easier
than the Intel design, and more cost-effective, reliable, scalable, ...
 
But it pushes Inmos to develop and market their T810 (with a 2-4 times
performance increase in real applications, with 50 % faster links and
with 16 kB SRAM) just a little bit faster.
 
Patrick
Technical Details
Message-ID: <8904101212.AA05679@uk.ac.ox.prg>
Path: arc1-ca.pugleaf.net!utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!ucbvax!NSS.CS.UCL.AC.UK!PVR%bgerug51.earn

Show Full Headers
Complete Article Headers
Path: arc1-ca.pugleaf.net!utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!tut.cis.ohio-state.edu!ucbvax!NSS.CS.UCL.AC.UK!PVR%bgerug51.earn
From: PVR%bgerug51.earn@NSS.CS.UCL.AC.UK (Patrick Van Renterghem / Transputer Lab)
Newsgroups: comp.sys.transputer
Subject: I860's and transputer clones
Keywords: >     B-9710 Ghent-Zwijnaarde, Belgium, Europe. Fax: +32 91 22 85 9
Message-ID: <8904101212.AA05679@uk.ac.ox.prg>
Date: 10 Apr 89 12:59:00 GMT
Sender: daemon@ucbvax.BERKELEY.EDU
Organization: The Internet
Lines: 45