Path: utzoo!mnetor!uunet!lll-winken!lll-tis!ames!oliveb!pyramid!prls!mips!mark
From: mark@mips.COM (Mark G. Johnson)
Newsgroups: comp.arch
Subject: Fast 432  (!?)
Message-ID: <2085@obiwan.mips.COM>
Date: 26 Apr 88 20:16:12 GMT
Reply-To: mark@mips.COM (Mark G. Johnson)
Organization: MIPS Computer Systems, Sunnyvale, CA
Lines: 40

In article <367@m3.mfci.UUCP>, colwell@m3.UUCP (Robert Colwell) writes
	> ... maybe it [the Intel 432] addressed issues that were just
	> too far in the future, and still are.  The basic goal of the
	> machine was to trade off basic performance for other things
	> that were felt to be more important at the time, like programmer
	> productivity ...

I don't quite agree.  When the chips were on 2nd-pass silicon in June 1980
they hadn't yet been Marketing-Renamed to "iAPX-432" (they were still
known as the Intel 8801, 8802, & 8803) and within Intel, they were felt
to provide high performance computing.  No `trade off performance for
other things' at all ... the 8800 (later 432) was supposed to be fast.
Here are some of the reasons that were being circulated within Intel:

 1. The 8802 Execution Unit was pipelined and contained a full IEEE
    standard Floating Point set of hardware.  This was rare indeed in 1980,
    and feeding data to/from the FP was pretty well thought out.  It was,
    for example, better than the 8087/8086 interface (which came _after_
    the 8800 / 432).

2.  The chipset supported multiprocessing.  Intel envisioned hooking up
    tens of 8800-sets to achieve high speeds.  The scheme closely resembled
    Unix `pipes' (e.g. cat foo | tbl | eqn | troff ) with each program
    running on a different processor.

3.  The 8803 was a dedicated hardware I/O processor, which was supposed to
    unburden the CPU(s).

Of course, one could argue that the 8800 / 432 didn't achieve the performance
goals that were desired.  "The market" did indeed vote with its dollars
on this point.  But Intel seems *not* to have thought that they were trading
away performance.

Many of the 8800 designers are net-readers; perhaps they would identify
themselves :-) and comment further.

Regards,
-- 
 -Mark Johnson	*** DISCLAIMER: Any opinions above are personal. ***	
 UUCP: {decvax,ucbvax,ihnp4}!decwrl!mips!mark   TEL: 408-991-0208
 US mail: MIPS Computer Systems, 930 E. Arques, Sunnyvale, CA 94086