Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 31 Oct 2005 03:51:18 +0100
From:      Daniel Rock <freebsd@deadcafe.de>
To:        "M. Warner Losh" <imp@bsdimp.com>
Cc:        Alexander@Leidinger.net, gurney_j@resnet.uoregon.edu, freebsd-current@freebsd.org, davidxu@freebsd.org
Subject:   Re: TSC instead of ACPI: powerd doesn't work anymore (to be expected?)
Message-ID:  <436586A6.4090907@deadcafe.de>
In-Reply-To: <20051030.161606.65680605.imp@bsdimp.com>
References:  <20051030093718.GE39253@dragon.NUXI.org>	<4364D90F.3090205@samsco.org> <20051030195936.GZ4115@funkthat.com> <20051030.161606.65680605.imp@bsdimp.com>

next in thread | previous in thread | raw e-mail | index | archive | help
M. Warner Losh schrieb:
> Actually, ioport reads can be faster than the 1us that's widely
> quoted.  ioport reads can be as fast as ~125ns (2 cycles at 16MHz).
> However, experience has shown that they are rarely this fast.  I've
> seen 8MB/s pio over the pci bus on some custom hardware we have, which
> 2Mreads/sec which is about 500ns per read.  I think that the pci
> hardware that I was reading had a few extra wait states...


According to "Software Optimization Guide for AMD64 Processors":
http://www.amd.com/us-en/assets/content_type/white_papers_and_tech_docs/25112.PDF
the "in" machine instructions have a latency of ~180 clock cycles.
But this will be only the lower theoretical limit.


Daniel



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?436586A6.4090907>