Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Posting-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!henry
From: henry@utzoo.UUCP (Henry Spencer)
Newsgroups: net.arch
Subject: Re: B1700
Message-ID: <5713@utzoo.UUCP>
Date: Thu, 20-Jun-85 13:48:52 EDT
Article-I.D.: utzoo.5713
Posted: Thu Jun 20 13:48:52 1985
Date-Received: Thu, 20-Jun-85 13:48:52 EDT
References: <1452@ecsvax.UUCP> <290009@acf4.UUCP> <5694@utzoo.UUCP>, <2557@wateng.UUCP>
Organization: U of Toronto Zoology
Lines: 20

> Myers (see below), quotes a performance comparison of the B1700, a general-
> purpose (sort of) machine against the IBM System 3 Model 10,
> a contemporary machine designed to run RPG II exclusively.
> While the B1700 cost 75% more, as the Sys 3, it ran compute-bound
> RPG programs EIGHT TIMES AS FAST. ...

I have been told (I have not confirmed this) that when you used a decent
programming language, and compared against a decent machine (the System 3
series were real turkeys), the B1700 showed a strong tendency to come out
second best.

Speaking from only the vaguest memories, RPG and friends are well-suited
to microcode implementations:  a small set of relatively high-level
primitives.  Snobol would probably be another favorable case.  But when
the language primitives get low-level (C, Pascal, Ada) so that one does
not get as much mileage out of mapping lots of ordinary-machine instructions
into one customized-machine instruction, then things fall down badly.
-- 
				Henry Spencer @ U of Toronto Zoology
				{allegra,ihnp4,linus,decvax}!utzoo!henry