Path: utzoo!attcan!uunet!decwrl!nsc!taux01!amos
From: amos@taux01.nsc.com (Amos Shapir)
Newsgroups: comp.arch
Subject: Re: int x int -> long for * (or is it 32x32->64)
Message-ID: <4617@taux01.nsc.com>
Date: 17 Sep 90 15:33:56 GMT
References: <3762@goanna.cs.rmit.oz.au>
Organization: National Semiconductor (IC) Ltd, Israel, Home of the Series 32000
Lines: 20
X-Hdate: 27 Elul 5750

[Quoted from the referenced article by ok@goanna.cs.rmit.oz.au (Richard A. O'Keefe)]
>
>Two very important numbers for this newsgroup are
>    --	what impact did inclusion of 32x32->64 multiplication have on
>	the rest of the architecture?  (It also has 64/32->32+32 division.)

Not much - since this is a CISC, this type of division (there are 4 more)
is just another entry of the division routine in the microcode.

>    --	how many NS32532 programs are actually likely to benefit from this
>	instruction?

Quite a few - the NS32532 doen't have a FPU on-board, so many implementations
emulate it in software; there are also many other uses which have been
listed in this thread before.

-- 
	Amos Shapir		amos@taux01.nsc.com, amos@nsc.nsc.com
National Semiconductor (Israel) P.O.B. 3007, Herzlia 46104, Israel
Tel. +972 52 522255  TWX: 33691, fax: +972-52-558322 GEO: 34 48 E / 32 10 N