Lpc2000

Without a slightly more detailed description of what you're trying to
acheive via time synchronisation it's hard to give any advice, however I've
done quite a lot of work in the past in high accuracy embedded network time
sychronisation techniques in association with a number of switch
manufacturers: RuggedCom etc - although admittedly on a much more powerful
ARM 9 core.

If you're actually wanting to get a time synch across an ethernet network
down to better than 1ms then you'll definately need to bypass the ethernet
stack and deal with your ethernet controller directly. To be honest 1ms is
pretty much as low as you'll get purely in software and even then you'll
have to implement a fairly intensive version of NTP. There are papers out
there for companies (Siemens and ABB for example) that have done significant
research in this area as they helped define the relatively new IEC61850
standards for use in electricity substations - where real time control can
be required down to 10us.

If you can give us a little more info on what you're trying to achieve I may
well be able to point you in the direction of some helpful reading.

Andy

-----Original Message-----
From: lpc2000@yahoogroups.com [mailto:lpc2000@yahoogroups.com]On Behalf
Of Robert Adsett
Sent: 12 May 2006 05:21
To: lpc2000@yahoogroups.com
Subject: Re: [lpc2000] Interrupt function declaration


At 09:27 AM 5/11/06 +0100, Andy wrote:
>Robert,
>I am running a shared clock network over ethernet, so to reduce task jitter
>on the slave nodes the timer0 interrupt needs to be as close as possible.

Do you need to have your message sent as close to 1mS as possible?  If so
I'm surprised that ethernet uncertainties don't swamp any jitter from the
interrupt.  Never mind the additional uncertainties introduced by whatever
higher level protocol you are running on ethernet (probably TCP/IP consider
you are using WIZnet?)