Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Posting-Version: version B 2.10.1     9/27/83; site hplabsc.UUCP
Path: utzoo!watmath!clyde!cbosgd!ihnp4!houxm!mhuxr!ulysses!allegra!mit-eddie!godot!harvard!seismo!hao!hplabsc!dsmith
From: dsmith@hplabsc.UUCP (David Smith)
Newsgroups: net.micro.68k,net.micro
Subject: Re: MC68881 Floating-point performance times
Message-ID: <2312@hplabsc.UUCP>
Date: Thu, 27-Dec-84 15:11:55 EST
Article-I.D.: hplabsc.2312
Posted: Thu Dec 27 15:11:55 1984
Date-Received: Sat, 29-Dec-84 03:46:35 EST
References: <263@oakhill.UUCP> <896@utastro.UUCP>, <612@turtlevax.UUCP> <276@ist.UUCP>
Organization: Hewlett Packard Labs, Palo Alto CA
Lines: 15


>I remember in my student days using an IBM 370/165 and discovering that
>double was FASTER than single precision floating, since the microcode
>did everything in double precision and the single ops were done by padding
>the operands and truncating the results.....
>
>Maybe that is the rationale for C working in double....

C grew up on the Pdp-11/45 and /70, which had a mode bit to specify whether
floating point was to be done in single or double precision.  The C
implementation did everything in double to avoid forcing the compiler to
change and track the mode bit.

		David Smith
		Hewlett-Packard Laboratories