From owner-freebsd-chat  Sun Mar  2 13:03:02 1997
Return-Path: <owner-chat>
Received: (from root@localhost)
          by freefall.freebsd.org (8.8.5/8.8.5) id NAA02657
          for chat-outgoing; Sun, 2 Mar 1997 13:03:02 -0800 (PST)
Received: from rah.star-gate.com (rah.star-gate.com [204.188.121.18])
          by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id NAA02652
          for <freebsd-chat@freebsd.org>; Sun, 2 Mar 1997 13:02:58 -0800 (PST)
Received: from rah.star-gate.com (localhost.star-gate.com [127.0.0.1]) by rah.star-gate.com (8.8.5/8.7.3) with ESMTP id NAA06453; Sun, 2 Mar 1997 13:02:50 -0800 (PST)
Message-Id: <199703022102.NAA06453@rah.star-gate.com>
X-Mailer: exmh version 1.6.9 8/22/96
To: Charles Henrich <henrich@crh.cl.msu.edu>
cc: jmb@freefall.freebsd.org (Jonathan M. Bresler), ejs@bfd.com,
        jkh@time.cdrom.com, taob@risc.org, freebsd-chat@freebsd.org
Subject: Re: 2.2 Compiler slower than 2.1? (was RSA 56-bit key challenge) 
In-reply-to: Your message of "Sun, 02 Mar 1997 15:29:01 EST."
             <199703022029.PAA10351@crh.cl.msu.edu> 
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Date: Sun, 02 Mar 1997 13:02:49 -0800
From: Amancio Hasty <hasty@rah.star-gate.com>
Sender: owner-chat@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk


Cool!

I got hold of a 2.1 machine and recompiled the binary
this is what I am getting:

{hasty} ./client -m
rc5-56-client: Performance testing with 1000000 crypts
rc5-56-client: Complete in 2.614 seconds. (382627.93 keys/sec)
{hasty} ./client -m
rc5-56-client: Performance testing with 1000000 crypts
rc5-56-client: Complete in 2.566 seconds. (389699.01 keys/sec)
{hasty}

Now a client compiled on my 3.0 box:

{hasty} ./client -m
rc5-56-client: Performance testing with 1000000 crypts
rc5-56-client: Complete in 4.449 seconds. (224788.41 keys/sec)


It looks like we may have to look at the assembly output of the 
program to sort out what the hell is going on .
>From The Desk Of Charles Henrich :
> Here is an interesting tidbit, Eric J. Schwertfeger compiled the client on a
> 2.1 machine (as did I now) and I get 385k/sec instead of 350k/sec on my PP200
.
> Why is the 2.1 compiler that much faster?  Any ideas?
> 
> -Crh
> 
>        Charles Henrich     Michigan State University     henrich@msu.edu
> 
>                          http://pilot.msu.edu/~henrich