From owner-freebsd-hackers  Mon Sep 29 01:52:02 1997
Return-Path: <owner-freebsd-hackers>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.7/8.8.7) id BAA28387
          for hackers-outgoing; Mon, 29 Sep 1997 01:52:02 -0700 (PDT)
Received: from bugs.us.dell.com (bugs.us.dell.com [143.166.169.147])
          by hub.freebsd.org (8.8.7/8.8.7) with SMTP id BAA28348
          for <hackers@FreeBSD.ORG>; Mon, 29 Sep 1997 01:51:55 -0700 (PDT)
Received: from ant.us.dell.com (ant.us.dell.com [198.64.66.34]) by bugs.us.dell.com (8.6.12/8.6.12) with SMTP id DAA01030; Mon, 29 Sep 1997 03:50:48 -0500
Message-Id: <3.0.2.32.19970929034452.006ff1c0@bugs.us.dell.com>
X-Sender: tony@bugs.us.dell.com
X-Mailer: QUALCOMM Windows Eudora Light Version 3.0.2 (32)
Date: Mon, 29 Sep 1997 03:44:52 -0500
To: Mike Smith <mike@smith.net.au>
From: Tony Overfield <tony@dell.com>
Subject: Re: INB question 
Cc: hackers@FreeBSD.ORG
In-Reply-To: <199709280920.SAA05505@word.smith.net.au>
References: <Your message of "Sun, 28 Sep 1997 02:00:01 EST."             <3.0.2.32.19970928020001.006ce080@bugs.us.dell.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Sender: owner-freebsd-hackers@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

At 06:50 PM 9/28/97 +0930, Mike Smith wrote:
>> 16-bit ISA I/O cycles are not only wider but also faster than 8-bit ISA 
>> I/O cycles.  Back when IDE drives were still attached to the ISA bus, a 
>> fast drive could transfer about 3.5MB/sec, but 2.5MB/sec or 2MB/sec was 
>> more typical.  The speed depends on the chipset and the way that the 
>> BIOS programs the ISA timing options.
>
>Gotcha.  Hmm, does this mean that you can read an 8-bit peripheral 
>faster by using 16-bit cycles,

No.

>or will the sizing signals trip you up?

Yes.  Unless IOCS16# is asserted, the ISA controller will split
the cycle into two slower 8-bit cycles.  If IOCS16# is asserted, 
the cycle will be 16-bits wide and will complete faster.