[The CODE Visual Parallel Programming System]

CODE is a visual parallel programming system, allowing users to compose sequential programs into a parallel one. The parallel program is a directed graph, where data flows on arcs connecting the nodes representing the sequential programs. The sequential programs may be written in any language, and CODE will produce parallel programs for a variety of architectures, as its model is architecture-independent.


The CODE system can produce parallel programs for shared-memory and distributed-memory architectures, including networks of workstations. The newest version (pre-release available below) supports MPI and PVM-based networks, Cray J and T3E series, and Sun and other SMPs with POSIX thread support.

Download CODE

  • Here is a screen shot of CODE.

  • Article on CODE: HPCwire, the on-line journal of high-performance computing, published an article on CODE entitled "Visual Parallel Programming May Come of Age with CODE".

  • Here is a complete list of CODE-related papers available on-line.

  • A CODE FAQ is now available.

  • A CODE Tutorial is now on-line, providing an introduction to using CODE .

  • There is a CODE mailing-list for current (and prospective) CODE users so that they will be notified of releases, new backends, etc.
  • To join the mailing list, fill in the form below. (If you download CODE, you will also be added to the mailing list.)
    First name: Last name: E-mail address:

Documentation & Publications

A CODE Tutorial is now on-line (in construction).

  • The user and reference manual for the previous version of CODE (2.0) is available in uncompressed or gzipped PostScript. Despite the changes in the user interface, this manual is still quite useful. A new manual is in the works.

  • Click here for CODE-related publications.

 

Contact Information

For specific comments regarding CODE, send e-mail to Emery Berger at emery@cs.utexas.edu. To send snail mail to a group member, address it to:
Department of Computer Sciences
The University of Texas at Austin
Austin, TX 78712-1188

 

The Research Group

Name Research Area
Dr. James C. Browne Group leader
Dwip Banerjee Incorporation of dynamic data partitioning into the CODE model.
Emery Berger An efficient implementation of CODE for clusters of SMPs based on MPI and threads.
Ajita John A programming system based on constraints for automatic parallelization.
Alumni

Mastering the lawless science of our law,--
That codeless myriad of precedent,
That wilderness of single instances.

-- Alfred Lord Tennyson


[Overview] [Announcements] [Software]
[Researchers] [Publications] [Contacts]

CODE Home Page / emery@cs.utexas.edu / Created: Tue Oct 1 17:57:59 CDT 1996 hhmts start Last modified: Thu Aug 7 16:00:36 CDT 1997 hhmts end