home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.arch
- Path: sparky!uunet!wupost!sdd.hp.com!news.cs.indiana.edu!umn.edu!sctc.com!smith
- From: smith@sctc.com (Rick Smith)
- Subject: No progress in parallelism? (was: History)
- Message-ID: <1992Aug26.153025.1147@sctc.com>
- Organization: SCTC
- References: <PCG.92Aug26005248@aberdb.aber.ac.uk>
- Date: Wed, 26 Aug 1992 15:30:25 GMT
- Lines: 27
-
- I wrote:
-
- >smith> I think the future of computer architectures is in various forms
- >smith> of parallelism not addressed by the von Neumann tradition.
-
- And pcg@aber.ac.uk (Piercarlo Grandi) replied:
-
- >Pious hope, I am afraid. Research in this field has been going on
- >forever, and without much progress. Architectures here seem wedded to
- >particular application shapes, and almost all variations have been tried
- >out, and only a few have been found cost effective. But some particular
- >application shapes are so important...
-
- It should be clear from von Neumann's writings that multiprocessing
- was never part of his model. However, I think it is fair to say that
- the cost effectiveness of multiprocessor configurations has been well
- established. I think it's also fair to say that many of the "big issues"
- these days (cache management comes immediately to mind) are driven
- by parallelism problems.
-
- Most programming languages (and programmers) are oriented towards
- program structures that fit the von Neumann mold. That may restrict
- instruction set architectures, but it doesn't eliminate other forms
- of parallelism at higher levels in the system.
-
- Rick.
- smith@sctc.com arden hills, minnesota
-