Path: utzoo!utgpu!water!watmath!clyde!cbosgd!ihnp4!inuxc!iuvax!pur-ee!uiucdcs!uxc.cso.uiuc.edu!ccvaxa!aglew From: aglew@ccvaxa.UUCP Newsgroups: comp.arch Subject: Re: Single tasking the wave of the futu Message-ID: <28200077@ccvaxa> Date: 17 Dec 87 03:02:00 GMT References: <3445@hoptoad.uucp> Lines: 25 Nf-ID: #R:hoptoad.uucp:3445:ccvaxa:28200077:000:1250 Nf-From: ccvaxa.UUCP!aglew Dec 16 21:02:00 1987 (I'm not quite so pessimistic as my manager, who has a previous post, about parallel processing. But that's another story... By the way, I'm collecting information about superlinear speedups, as reported for ELXSI et al. I'd appreciate it if anybody can send me reports of superlinear speedups, both single process and workload.) Just read the latest Communications of the ACM, with the example of the Michael Jackson style of programming in "Literate Programming". Now, when I first heard of Jackson, I thought "what is this crap" and moved on. But now I'm not so sure. Especially since the Jackson methodology seems to promote a "pipelined" sense of dataflow. On present machines he has an implementation technique that "inverts" a pipeline into normal code; but, a pipeline might be able to make better use of multiprocessors than many other parallel programming techniques. Andy "Krazy" Glew. Gould CSD-Urbana. 1101 E. University, Urbana, IL 61801 aglew@mycroft.gould.com ihnp4!uiucdcs!ccvaxa!aglew aglew@gswd-vms.arpa My opinions are my own, and are not the opinions of my employer, or any other organisation. I indicate my company only so that the reader may account for any possible bias I may have towards our products.