From owner-freebsd-hackers  Thu Apr  2 21:04:06 1998
Return-Path: <owner-freebsd-hackers@FreeBSD.ORG>
Received: (from majordom@localhost)
          by hub.freebsd.org (8.8.8/8.8.8) id VAA17398
          for freebsd-hackers-outgoing; Thu, 2 Apr 1998 21:04:06 -0800 (PST)
          (envelope-from owner-freebsd-hackers@FreeBSD.ORG)
Received: from inet16.us.oracle.com (inet16.us.oracle.com [192.86.155.100])
          by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id VAA17390
          for <hackers@freebsd.org>; Thu, 2 Apr 1998 21:04:02 -0800 (PST)
          (envelope-from MOLAGAPP.IN.oracle.com.ofcmail@in.oracle.com)
Received: from dwarpal.in.oracle.com (dwarpal.in.oracle.com [152.69.176.11])
	by inet16.us.oracle.com (8.8.5/8.8.5) with SMTP id VAA08674
	for <hackers@freebsd.org>; Thu, 2 Apr 1998 21:03:31 -0800 (PST)
Received:  by dwarpal.in.oracle.com (8.6.13/37.8)
	id XAA04721; Thu, 2 Apr 1998 23:36:52 -0500
Message-Id: <199804030436.XAA04721@dwarpal.in.oracle.com>
Date: 03 Apr 98 08:21:25 +0330
From: "Muthu" <MOLAGAPP.IN.oracle.com.ofcmail@in.oracle.com>
To: hackers@FreeBSD.ORG
Subject: bcopy implementation
Cc: GLAKSHMI.IN.oracle.com.ofcmail@in.oracle.com,
        JTHERRAT.IN.oracle.com.ofcmail@in.oracle.com
MIME-Version: 1.0
X-Mailer: Oracle InterOffice (version 4.0.5.1.55)
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset="us-ascii"
Sender: owner-freebsd-hackers@FreeBSD.ORG
Precedence: bulk
X-Loop: FreeBSD.ORG

Hi, 
 
   I took a look at bcopy implementation inside the kernel(FreeBSD 2.2.5). If 
the number of bytes to copy is greater than 1024, it uses the floating point 
unit implementation else generic bcopy.  
 
   This kind of implementation is not used in libc. Only generic bcopy is used 
in all cases. On the assumption, that the system has pentium processor, the 
bcopy implementation of libc can be changed to floating point implementation 
as in kernel.  
 
   One reason of not changing implementation of bcopy in libc may be that 
applications will run at different speed on different processor. On pentium it 
will run faster and on 80386 it will run slow. Is there any other valid reason 
of not implementing this method in libc? 
 
 
 
Regards, 
 
Muthu. O.L. 
 

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message