Re: shared memory

Thread View: comp.sys.transputer

3 messages

[T] Back to Threads [V] Tree View [G] Group Articles

3 total messages Started by Andy Pfiffer Thu, 30 Jun 1988 15:28

#2113

Author: Andy Pfiffer
Date: Thu, 30 Jun 1988 15:28

26 lines
1176 bytes

 +---- Douin Jean Michel in "Subject: shared memory" - Fri Jun 3  @ 3:17pm
 | Yet another funny idea :
 | 
 |    Does anybody know about using shared bus memory 
 |    with transputer?
 +----

I met an Australian fellow at the recent Boston Supercomputer Show and the
company he works for has a proprietary box chock full of Transputers, a
large percentage of which are tied together with shared memory and with
links.

I *believe* he said that there was a sum total of about 40 MB
of total shared memory, scattered about the machine.

My impression is that it is a digital effects generator for broadcast
video.

	Andy


--
Andy Pfiffer			  Topologix, Inc. (303) 421-7700
Trillium Diving Team              4860 Ward Road / Denver, CO 80033
            "...that's the way a Transputer works, right?"

Re: shared memory

#2138

Author: Bill O
Date: Fri, 15 Jul 1988 02:09

23 lines
1406 bytes

In article <8806301528.AA01029@snowwhite.com> andy@snowwhite.UUCP (Andy Pfiffer) writes:
> +---- Douin Jean Michel in "Subject: shared memory" - Fri Jun 3  @ 3:17pm
> |    Does anybody know about using shared bus memory 
> |    with transputer?
>I met an Australian fellow at the recent Boston Supercomputer Show and the
>...
>I *believe* he said that there was a sum total of about 40 MB
>of total shared memory, scattered about the machine.
>Andy Pfiffer			  Topologix, Inc. (303) 421-7700
                                  ***************

I had heard that Topologix had plans for a shared-memory transputer
board, (that is, the transputers sharing memory with each other, not
just the host). Is this 

1) true
2) hogwash
3) not necessarily either of the above?

Has anyone else heard this rumor (fact?)?

Bill O'Farrell, Northeast Parallel Architectures Center at Syracuse University
(billo@cmx.npac.syr.edu)

Pathological Behaviour of Inmos Routine SINP

#2142

Author: S Tett
Date: Tue, 19 Jul 1988 11:22

4 lines
586 bytes

Does anyone have any idea why the Inmos Routine SINP has pathological
behaviour at 12.5Pi.
For values very close (12.5+/- 0.0000001)*Pi it returns the value -1.0 ?
Simon

Thread Navigation

This is a paginated view of messages in the thread with full content displayed inline.

Messages are displayed in chronological order, with the original post highlighted in green.

Use pagination controls to navigate through all messages in large threads.

Back to All Threads