The Impact of Communication Style on Machine Resource
              Usage for the iWarp Parallel Processor


T. Gross, A. Hasegawa, S. Hinrichs, D. O'Hallaron, and T. Stricker
                          November, 1992
                          CMU-CS-92-215


                   School of Computer Science
                   Carnegie Mellon University
                      Pittsburgh, PA 15213


                            Abstract

Programs executing on a private-memory parallel system exchange data
by explicitly sending and receiving messages. Two communication styles
have been identified for such systems: memory communication (each
message exchanged between two processors is buffered in memory, e.g.
as in message passing) and systolic communication (each word of a
message is transmitted directly from the sender processor to receiver
processor, without any buffering in memory). The iWarp system supports
both communication styles and therefore provides a platform that
allows us to evaluate how the choice of communication style impacts
the usage of processor resources.  Parallel program generators map a
machine independent description of a computation onto a private-memory
parallel system. We use two different parallel program generators that
employ the two communication styles to map a set of application
kernels onto iWarp. By using tools to generate the parallel programs,
we are able to obtain realistic data on the execution of programs
using the different communication styles. This paper reports on
measurements of instruction format usage, the utilization of the
communication ports (gates), and instruction frequencies on the iWarp
system. It is a first step towards understanding how features and
capabilities of parallel processors are actually used by parallel
programs that have been mapped automatically.

Keywords: Processor architecture design and evaluation, parallel
systems, inter-processor communication architecture, instruction level
parallelism


Note: To appear in IEEE Computers, Summer 1994.