Tech Report Announcement CMU-CS-89-208

[Michael.Witbrock@CS.CMU.EDU]

Requests for copies should go to the address at the bottom of this post,
not to the poster.

             PLEASE DO NOT FORWARD TO OTHER BULLETIN BOARDS.
=========================================================================
====

                           An Implementation of
                    Back-Propagation Learning on GF11,
                      a Large SIMD Parallel Computer

                     Michael Witbrock and Marco Zagha
                        Carnegie Mellon University

                               CMU-CS-89-208
                               December 1989


     Current connectionist simulations require huge computational
     resources.  We describe a neural network simulator for the IBM GF11,
     an experimental SIMD machine with 566 processors and a peak
arithmetic
     performance of 11 Gigaflops.  We present our parallel
implementation of
     the backpropagation learning algorithm, techniques for increasing
     efficiency, performance measurements on the  NetTalk
     text-to-speech benchmark, and a performance model for the simulator.
     Our simulator currently runs the back-propagation learning algorithm
     at 900 million connections per second, where each ``connection per
     second'' includes both a forward and backward pass.  This figure was
     obtained on the machine when only 356 processors were working; with
     all 566 processors operational, our simulation will run at over one
     billion connections per second.  We conclude that the GF11 is
     well-suited to neural network simulation, and we analyze our use of
     the machine to determine which features are the most important for
     high performance.  

=========================================================================
====
            PLEASE DO NOT FORWARD TO OTHER BULLETIN BOARDS.


Requests for copies should go to:
                                    C Copetas
                                    School of Computer Science
                                    Carnegie Mellon University
                                    Pittsburgh PA 15213-3890    USA
or to   copetas at cs.cmu.edu

The technical report deals with implementation issues for fast parallel
connectionist
simulators. It may not be of any great interest to anyone not working in
this area.

-------------------------------------------------------------------------
-----
P.S. This TR is in postscript. Could the person who runs the ftp archive
tell
     me how to go about submitting it? Thanks.