From owner-freebsd-arch  Tue May 22  2:59: 0 2001
Delivered-To: freebsd-arch@freebsd.org
Received: from johnson.mail.mindspring.net (johnson.mail.mindspring.net [207.69.200.177])
	by hub.freebsd.org (Postfix) with ESMTP
	id 5FD5E37B422; Tue, 22 May 2001 02:58:57 -0700 (PDT)
	(envelope-from tlambert2@mindspring.com)
Received: from mindspring.com (pool0077.cvx21-bradley.dialup.earthlink.net [209.179.192.77])
	by johnson.mail.mindspring.net (8.9.3/8.8.5) with ESMTP id FAA29245;
	Tue, 22 May 2001 05:58:49 -0400 (EDT)
Message-ID: <3B0A3871.1BA0C0DB@mindspring.com>
Date: Tue, 22 May 2001 02:59:13 -0700
From: Terry Lambert <tlambert2@mindspring.com>
Reply-To: tlambert2@mindspring.com
X-Mailer: Mozilla 4.7 [en]C-CCK-MCD {Sony}  (Win98; U)
X-Accept-Language: en
MIME-Version: 1.0
To: Chuck Youse <chuck@newsscope.com>
Cc: Terry Lambert <tlambert@primenet.com>,
	Peter Pentchev <roam@orbitel.bg>, Ruslan Ermilov <ru@FreeBSD.ORG>,
	Nik Clayton <nik@FreeBSD.ORG>, arch@FreeBSD.ORG
Subject: Re: [PATCH] syscons ioctl() to grab text mode buffer
References: <Pine.BSF.4.21.0105191306460.38086-100000@warsaw.newsscope.com>
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Sender: owner-freebsd-arch@FreeBSD.ORG
Precedence: bulk
List-ID: <freebsd-arch.FreeBSD.ORG>
List-Archive: <http://docs.freebsd.org/mail/> (Web Archive)
List-Help: <mailto:majordomo?subject=help> (List Instructions)
List-Subscribe: <mailto:majordomo?subject=subscribe%20freebsd-arch>
List-Unsubscribe: <mailto:majordomo?subject=unsubscribe%20freebsd-arch>
X-Loop: FreeBSD.ORG

Chuck Youse wrote:
> > On a practical note, the code generated merely inverts the sense
> > of the same cmpl at default optimization, and at -O2 ends up being
> > either:
> >
> >         testl %eax,%eax
> >         jge .L3
> >
> > or:
> >
> >         cmpl $-1,%eax
> >         jne .L3
> >
> > So the number of instruction cycles is identical.  Off the top of
> 
> Well, the second sequence is longer by a byte.  I don't have the data
> sheets handy, it probably also takes another cycle as it involves an
> immediate operand sign-extended to 32-bits instead of just a
> register-register compare.
> 
> Just nitpicking

If we want to nitpick, we should probably generate the
same test cases for the Alpha...

-- Terry

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