Grain-y-ness

Thread View: comp.sys.transputer

3 messages

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

3 total messages Started by CDRIW Tue, 10 Oct 1989 22:35

#315

Author: CDRIW
Date: Tue, 10 Oct 1989 22:35

25 lines
1731 bytes

Grain for thought:

Performance with programmability is the target.  Surely the point is to
keep the memory as busy as possible?  Cycles-per-instruction is not the
issue, but accesses-per-memory-location.  Microprocessors in general
are too big:  A 10 mip processor with 10 Meg of RAM accesses each
location only once per second.  What a waste of RAM!

The `grain-y-ness' of occam is great, with its 3 primative processes,
hierachical process structure and lack of shared memory.  When applied
to transputers however, the niceness begins to break down.
Distributing a program on transputers imposes a flat process structure,
with a limit of 4 channels per process.  Processes with internal
parallelism (i.e. communication) run time-sliced.  What is required is
transputers with internal transputers!

How about a (size 1) TRAM with 4 T2s arranged in a tetrahedral
structure, although RAM would be a big problem here.  Even more
interesting would be 4 (say) transputers on the same die.  In this case
the intra-die link engines need not be serial but 8- (or why not 32-)
bit parallel -- this would really get the data flowing.

We need systems with *much* higher processor-communication / RAM.  This
may require smaller processors with better communication (looks very
neural-nettish, eh?)

Re: Grain-y-ness

#317

Author: Lindsay Patten
Date: Wed, 11 Oct 1989 20:34

9 lines
982 bytes

CDRIW@cr83.staffordshire-polytechnic.ac.uk:
> Surely the point is to keep the memory as busy as possible? 

Why?  I would think that it would be do get as much done as possible. No?

Lindsay Patten            "People are package deals - No substitutions allowed"
Pattern Analysis & Machine Intelligence Group                   lindsay@watnext
Department of Systems Design Engineering           lindsay@watnext.waterloo.edu
University of Waterloo              {utai|decvax|uunet}!watmath!watnext!lindsay

Re: Grain-y-ness

#323

Author: Hubert Matthews
Date: Thu, 12 Oct 1989 11:13

19 lines
1423 bytes

In article <11873@watcgl.waterloo.edu> lindsay@watnext.waterloo.edu (Lindsay Patten) writes:
>CDRIW@cr83.staffordshire-polytechnic.ac.uk:
>> Surely the point is to keep the memory as busy as possible? 
>
>Why?  I would think that it would be do get as much done as possible. No?

Since the major cost in modern computers is memory, then this is not
an unreasonable viewpoint.  CPUs are cheap in comparison to memory.
Perhaps you might phrase your answer better as: "I would think that it
would be better to get as much done as possible for a given cost".
You can always throw more hardware at a problem and make it go faster,
but it may not be cost-effective.

In short, engineering is full of trade-offs.  Speed v. cost is just
one of the obvious ones.
-- 
Hubert Matthews      ...helping make the world a quote-free zone...

hjm@cernvax.cern.ch   hjm@vxomeg.decnet.cern.ch    ...!mcvax!cernvax!hjm

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