From: eugene@cse.ucsc.edu (Eugene Miya)
Newsgroups: comp.parallel
Subject: Re: What Ever Became of the "Transputer" ???
Date: 28 Apr 1999 21:28:13 GMT
Organization: UC Santa Cruz CIS/CE
Approved: eugene
Message-Id: <7g7uhd$ag4@darkstar.ucsc.edu>
References: <7g79dg$48i$1@goldenapple.srv.cs.cmu.edu>
Xref: ukc comp.parallel:15542


Basically, they got trounced by Intel.  Lack of software, too.
Could not keep up with the technology curve.  Some shortsightedness
on the part of Americans.  Certain proprietary things about the architecture.
Processors alone are not enough.

In article <7g79dg$48i$1@goldenapple.srv.cs.cmu.edu>,
j <nospam@null.net> wrote:
>About ten years or so ago, lots of people seemed very
>interested in a microprocessor-like device called a
>"Transputer". These were full CPUs, but also included

They have been in existence for longer than 10 years.
I do not know whom you refer to as "lots of people."
ICL, Meiko, IPM, Parsytec, and a few others at most.

>several ultra-highspeed "serial" links through which
>data could be exchanged between processors. If anything,

"ultra-high" is your term.

>the model resembled the current trick of getting many
>internetworked computers to work on parts of a problem.

What trick?  Mostly, I've seen people sweat and do hard work to
partition problems.  You mean virtual cut through?  If there's a useable trick,
hundreds of people reading this group want to know it.

>The big difference was that the "net" was all on the
>same backplane ... fast. 
>
>What ever became of these things ? For a short time they
>seemed full of promise for implementing inexpensive
>parallel solutions with an arbitary and expandable number
>of processing nodes. Then ... gone. 

You can go read comp.sys.transputer and use dejanews to find out their
past discussions why they failed.  A neat idea; ahead of its time;
they got run over by the Wintel juggernaut.  Inmos made practically no
inroads into the US market place.

What was neat was that Mitchell Lobell got one from Inmos as part of his
Parallel Processing Connection.  But I don't recall anyone using it.
I do recall chating with one of the women who had used a CM at the time.

Anyone else want to add anything?


I want to try to pick up a SUPRENUM machine for The Computer Museum.
I think there was also an Israeli machine also using Transputers.
We should try to pick one of those up, too.  


--
Articles to bigrigg+parallel@cs.cmu.edu (Admin: bigrigg@cs.cmu.edu)
Archive: http://www.hensa.ac.uk/parallel/internet/usenet/comp.parallel