[Discuss-gnuradio] Re: synchronizing sound cards in a cluster (fwd)

Thu Mar 13 13:20:34 PST 2003

---------- Forwarded message ----------
Date: Thu, 13 Mar 2003 13:03:36 -0800
From: Matthew Kaufman <matthew at eeph.com>
To: 'Eugen Leitl' <eugen at leitl.org>, discuss-gnuradio at gnu.org
Subject: RE: [Discuss-gnuradio] Re: synchronizing sound cards in a cluster
    (fwd)

This isn't really the hard part. The hard part is getting multiple sound
cards to share the same sample clock. IF the same clocks all ran at the
same rate, then you could fairly easily use known inputs to synchronize
up the results, but the sample clocks aren't nearly close enough
together for that. In fact, the sample clocks in most sound cards are
*terrible*.

Even synchronizing multiple sound cards inside the same PC is a
difficult problem for this reason.

So, for starters, go get some sound cards that have an external clock
input for the sampling. (If you can find such a thing)

Matthew

> -----Original Message-----
> From: discuss-gnuradio-bounces+matthew=eeph.com at gnu.org 
> [mailto:discuss-gnuradio-bounces+matthew=eeph.com at gnu.org] On 
> Behalf Of Eugen Leitl
> Sent: Thursday, March 13, 2003 1:02 PM
> To: discuss-gnuradio at gnu.org
> Subject: [Discuss-gnuradio] Re: synchronizing sound cards in 
> a cluster (fwd)
> 
> 
> ---------- Forwarded message ----------
> Date: Thu, 13 Mar 2003 14:32:52 -0500 (EST)
> From: Robert G. Brown <rgb at phy.duke.edu>
> To: Jim Lux <James.P.Lux at jpl.nasa.gov>
> Cc: beowulf at beowulf.org
> Subject: Re: synchronizing sound cards in a cluster
> 
> On Thu, 13 Mar 2003, Jim Lux wrote:
> 
> > Anybody have any good ideas on how to synchronize the sampling from
> > multiple sound cards in a cluster using Ethernet as the 
> interconnect. The 
> > application would grab data from the sound card (notionally at 100 
> > ksamples/second total, for two channels) and do a ton of signal 
> > processing.  At some point in the processing, the streams 
> of data need to 
> > be shared between processors (i.e. to do beamforming), and 
> so, needs to be 
> > time registered.
> > The bandwidth isn't a real challenge here (with, say, 16 
> processors, that's 
> > only about 32 Mbps total), nor is latency, but synchronization is.
> > 
> > One can fairly easily synchronize to a millisecond over 
> Ethernet, but 
> > this
> > application needs sync to, at worst, 1 sample time (20 
> microseconds) 
> > although order of a microsecond would be nice.
> 
> a) Check out the documentation on 
> http://www.ntp.org/documentation.html.
> >From what it says, you can synchronize at roughly the level 
> of network
> latency with ntp alone, so you can (I would expect) get an 
> otherwise quiet LAN sync'd to a millisecond or even less.  
> NTP does correction over a long time and damps to a common 
> clock, so you MIGHT get down below the 1 ms mark over time.  
> I doubt that ntp alone would make 10 usec.
> 
> b) Do you get to spend money?  Can you purchase each node its 
> own GPS clock?  The ntp docs suggest that if you have any 
> sort of reference clock (atomic, GPS, time pulse) your 
> resolution is limited only by the reference (and, probably 
> things like gettimeofday, which are no better than 2 usec as 
> it is and can easily be worse).
> 
> c) If you don't get to spend money then you could TRY to use 
> the onboard tsc instead of coarsely adjusting the system 
> clock per se.  I'm using it as a timer in my benchmark code 
> and can give you a wrapped assembler fragment for reading it. 
>  This clock is accurate to an inverse clock (typically 
> sub-nanosecond these days) BUT by the time you add the 
> overhead of reading it you diminish to perhaps 40-60 
> nanoseconds. Still, in principle you have access to a clock 
> with sub-usec resolution (you can even measure and correct on 
> average for the time required for the wrapped call).
> 
> This clock is not configured for computing anything like 
> absolute systems time, so you'd have to do things like 
> pingpong between systems on the network a million times or so 
> making slow adjustments to a subtraction base until your 
> "clocks" match within some resolution across the entire network.
> 
> I actually don't think this would be horribly difficult.  
> It's sort of like you and I looking at our watches and saying 
> "10:02:02" (you adjust a tick and say "10:02:04" (and I 
> adjust a tick) and eventually we get to the point where we 
> are PREDICTING what the other person will say so that given 
> an average latency MEASURED to within some precision, we can 
> say that our clocks match within that precision.  I'm sure 
> NTP does something like this now with a coarser-grained 
> clock, and you might be able to steal it and just hack it to 
> use the tsc and get what you want.
> 
>   rgb
> 
> -- 
> Robert G. Brown	                       
> http://www.phy.duke.edu/~rgb/
> Duke University Dept. of 
> Physics, Box 90305
> Durham, N.C. 27708-0305
> Phone: 1-919-660-2567  Fax: 919-660-2525     email:rgb at phy.duke.edu
> 
> 
> 
> _______________________________________________
> Beowulf mailing list, Beowulf at beowulf.org
> To change your subscription (digest mode or unsubscribe) 
> visit http://www.beowulf.org/mailman/listinfo/beowulf
> 
> 
> 
> 
> _______________________________________________
> Discuss-gnuradio mailing list
> Discuss-gnuradio at gnu.org 
> http://mail.gnu.org/mailman/listinfo/discuss-> gnuradio
> 