From owner-freebsd-hackers  Tue Aug 20 09:09:39 1996
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.5/8.7.3) id JAA09865
          for hackers-outgoing; Tue, 20 Aug 1996 09:09:39 -0700 (PDT)
Received: from Campino.Informatik.RWTH-Aachen.DE (campino.Informatik.RWTH-Aachen.DE [137.226.225.2])
          by freefall.freebsd.org (8.7.5/8.7.3) with SMTP id JAA09860
          for <freebsd-hackers@freefall.freebsd.org>; Tue, 20 Aug 1996 09:09:35 -0700 (PDT)
Received: from gilberto.physik.rwth-aachen.de (gilberto.physik.rwth-aachen.de [137.226.31.2]) by Campino.Informatik.RWTH-Aachen.DE (RBI-Z-5/8.6.12)
	with ESMTP id SAA09624; Tue, 20 Aug 1996 18:04:58 +0200
Received: (from kuku@localhost) by gilberto.physik.rwth-aachen.de (8.6.11/8.6.9) id SAA02640; Tue, 20 Aug 1996 18:17:47 +0200
From: Christoph Kukulies <kuku@gilberto.physik.rwth-aachen.de>
Message-Id: <199608201617.SAA02640@gilberto.physik.rwth-aachen.de>
Subject: Re: max math performance - how?
To: bde@zeta.org.au (Bruce Evans)
Date: Tue, 20 Aug 1996 18:17:46 +0200 (MET DST)
Cc: freebsd-hackers@freefall.freebsd.org, kuku@gilberto.physik.rwth-aachen.de
In-Reply-To: <199608201445.AAA32287@godzilla.zeta.org.au> from Bruce Evans at "Aug 21, 96 00:45:39 am"
Reply-To: Christoph Kukulies <kuku@gilberto.physik.rwth-aachen.de>
X-Mailer: ELM [version 2.4ME+ PL16 (25)]
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: owner-hackers@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

> >I digged out a scientific test I compiled some time back in 386bsd times.
> >At that time I hacked around with different libms and I had a binary
> >lying around (statically linked) which outperforms every newly linked
> >version of that benchmark. (It is a bunch of fortran programs, the
> >so called 'Lund' benchmark from Lund University - a program that
> >physicists are mainly interested in seeing perform fast). 
> 
> >Now I have no idea what I did at that time - maybe I took some
> >early verrsion of the libmsun or was there something different
> >in 386bsd days (Bruce?)
> 
> 386BSD used libm, which is slow.  -current uses msun, which is
> slower, except possibly if it is compiled with option HAVE_FPU.

That's what I did before these measurements:
/etc/make.conf HAVE_FPU,
cd /usr/src/lib/msun,
make cleandir depend all install

> 
> Bruce
> 

--Chris Christoph P. U. Kukulies kuku@gil.physik.rwth-aachen.de