[kepler-users] Combined Sequential Parallel Workflow

[Edward A. Lee]

Ken,

I am aware of a few efforts towards such distributed execution,
although I think there is quite a bit of work to be done.

You might want to start by looking in $PTII/ptolemy/distributed
at the distributed SDF mechanism created by Daniel Lazaro Cuadrado (kapokasa at kom.aau.dk).  I haven't personally worked with it, so
I can't really vouch for it, but Daniel gave a very nice talk about
it at the last Ptolemy Miniconference.

There is also a distributed PN that was implemented a few years ago
that has not been maintained but could probably be resurrected (perhaps
with some effort).  The basic README file is at
$PTII/ptolemy/apps/dpn/tcfr/README_DPN.htm

Also, Yang Zhao built a few demo systems using JINI and RMI (remote
method invocation) that supported distributed models.  Unfortunately,
she never really packaged this, and I don't even know if her code
is in the tree.  There seems to be some related stuff in
$PTII/ptolemy/distributed.

I don't think any of these is built on MPI2, but it's possible that
Daniel's distributed SDF is.  Building on MPI2 seems like the right way
to go.

Edward

At 06:04 AM 11/9/2007, Kenneth Evans, Jr. wrote:
>I can do a loop of simple processes so far.  I am having some problems with
>flow control (i.e. determining when it is all done and doing the final
>process) but have done that to some degree.   I have mostly used SDF and
>probably don't understand PN well.  I don’t know much of anything about how
>to handle the parallelization.  I see a DistributedCompositeActor and a
>number of Jobs actors, but have no idea how to use them.  Some guidance,
>advice, places to get more information, and most especially examples, would
>be great.

------------ 
Edward A. Lee
Chair of EECS and Robert S. Pepper Distinguished Professor
231 Cory Hall, UC Berkeley, Berkeley, CA 94720-1770
phone: 510-642-0253, fax: 510-642-2845
eal at eecs.Berkeley.EDU, http://www.eecs.berkeley.edu/Faculty/Homepages/lee.html