Path: utzoo!utgpu!news-server.csri.toronto.edu!mailrus!cs.utexas.edu!uunet!mcsun!hp4nl!nikhefh!t68
From: t68@nikhefh.nikhef.nl (Jos Vermaseren)
Newsgroups: comp.sys.atari.st.tech
Subject: Re: Floating Pt. Math with a 68881 not always faster
Message-ID: <989@nikhefh.nikhef.nl>
Date: 3 Sep 90 16:29:00 GMT
References: <8379@ncar.ucar.edu> <2271@atari.UUCP>
Sender: t68@nikhef.nl (Jos Vermaseren)
Reply-To: t68@nikhefh.nikhef.nl (Jos Vermaseren)
Organization: Nikhef-H, Amsterdam (the Netherlands).
Lines: 21

Some years ago a wrote my own set of floating point routines.
Then a little later I got the chance to test a 68881.
My findings were that single precision addition was not any faster
on the 68881, but all others were. And those were very good
floating point routines. On the whole however the speed increase
with the floating point chip wasn't realy spectacular.
Over the original Absoft library I measured on one of my calculational
programs a factor 4 with the 68881 (and a factor 2 with the home made
library).
Most of the time is lost in the transmission and the negotiations
with the chip. This won't be the case so much on the TT as it has a
directer channel.
A compiler that can use the floating point registers will also make
an enormous difference, because then nearly all transmission delays
are reduced by a factor 4 to 5.

If you find that multiplication is faster without the chip you have
either an incredibly fast FP library, or an inefficient link to the
68881.

Jos Vermaseren