Message-ID: <347C86AC.7AAC@seanet.com>
Date: Wed, 26 Nov 1997 12:29:32 -0800
From: "Alan M. Doerhoefer" <aland AT seanet DOT com>
MIME-Version: 1.0
To: Eli Zaretskii <eliz AT is DOT elta DOT co DOT il>
CC: djgpp AT delorie DOT com
Subject: Re: binutils 2.8.1 performance = slow
References: <Pine DOT SUN DOT 3 DOT 91 DOT 971126132246 DOT 960H-100000 AT is>
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Precedence: bulk

Eli Zaretskii wrote:
> 
> On Tue, 25 Nov 1997, Alan M. Doerhoefer wrote:
> 
> > using binutils 2.8.1 instead of 2.7 caused a remarkable
> > slowing of my program.
> 
> Did you consider the possibility of different alignment of the functions
> in the version linked with 2.8.1?  What processor did you run your
> program on?
> 

Indeed, since I only compared the performance using one (large) 
program, I don't think that's a very good measure of the overall
speed of 2.8.1. I was surprised enough to inquire if anyone else
had seen this sort of thing, but I will now study this in depth
and report back.

The processor I used for both tests was a 100Mhz Pentium with 48MB
RAM.

> What compile/link switches did you use in both cases to compile and
> link your program?
> 

In both cases, I used the same makefile, with these compile/link
switches:	-v -s -m486 -O3 -ffast-math


> Does the slow-down happen on plain DOS (no Windows) also?

I have not had a chance to test this yet. I will do so ASAP.