On Jun 3, 2006, at 3:37 AM, chris clepper wrote:

On 6/2/06, Arie van Schutterhoef <arsche@xs4all.nl> wrote:
>about having the dsp running on seperate cpu's simultanously
>http://music.york.ac.uk/rimm/tech.htm

It would be possible for Pd to use the same Unix shm (and the Win32 equivalent) but some sort of sync system would probably be needed to keep the buffers moving along and not outputting duplicate or partial DSP frames.  I put a very non-sync shm object in GEM which works fine for video as that is more forgiving of minor problems compared to audio. 

Jack is another possiblity to spread DSP over multiple processes.  It might be possible for Pd to open several processes and manage them using one patcher although I have no idea about that feasibility.

Its quite easy to spread the calculation of multiple voices across CPUs.  My brother and I did this for this sound installation:

http://at.or.at/novnain/

We used 6 computers each running the same patch all controlled by a master patch.  If you used something like OSC timetagging, which AFAIK doesn't exist in any OSC implementations, then you could actually have pretty tight sync, and perhaps decent latency, depending on your network setup.

.hc


____________________________________________________________________________


"Terrorism is not an enemy.  It cannot be defeated.  It's a tactic.  It's about as sensible to say we declare war on night attacks and expect we're going to win that war.  We're not going to win the war on terrorism."

                                    - retired U.S. Army general, William Odom