Abstract
The communication overhead in many multiprocessor computing platform is a critical factor over performance. In this paper we present communication performance of a large processing array built with TI 320C40 DSPs. Inter-processor communication is provided by message passing which is a common method used in multiprocessors systems. The system is developed for image processing therefore transmission of large data blocks and various forms of communication are required frequently. The processor used in this system has six built in communication links. They are 8-bit, bi-directional links with a speed of 20 Mbytes/sec. A processing array built with these processors employs MIMD paradigm and static interconnection. In this paper, the communication performance of such DSP network is investigated and performance results are presented. The communication functions include broadcasting, scattering, gathering and point to point transmission of messages.
Original language | English |
---|---|
Pages (from-to) | 314-321 |
Number of pages | 8 |
Journal | Proceedings of SPIE - The International Society for Optical Engineering |
Volume | 3166 |
DOIs | |
Publication status | Published - Sept 1997 |
Event | Parallel and Distributed Methods for Image Processing - San Diego, CA, United States Duration: 28 Jul 1997 → 28 Jul 1997 |
Keywords
- Distributed memory systems
- Inter processor communication
- Parallel processing
ASJC Scopus subject areas
- Electronic, Optical and Magnetic Materials
- Condensed Matter Physics
- Computer Science Applications
- Applied Mathematics
- Electrical and Electronic Engineering