Latency and bandwidth considerations in parallel robotics image processing

• Published in: Proceedings of the 1993 ACM/IEEE conference on Supercomputing pp. 230 - 239
• Main Author: Webb, J. A.
• Format: Conference Proceeding
• Language: English
• Published: New York, NY, USA ACM 01.12.1993; IEEE
• Series: ACM Conferences
• Subjects: Application software; Bandwidth; Computer systems organization > Architectures > Distributed architectures > Grid computing; Computer systems organization > Architectures > Parallel architectures; Computer systems organization > Architectures > Parallel architectures > Multicore architectures; Computer systems organization > Architectures > Serial architectures > Superscalar architectures; Computer systems organization > Embedded and cyber-physical systems > Robotics; Computing methodologies > Artificial intelligence > Control methods > Robotic planning; Computing methodologies > Artificial intelligence > Planning and scheduling > Robotic planning; Computing methodologies > Modeling and simulation > Simulation types and techniques > Massively parallel and high-performance simulations; Control systems; Delay; Image processing; Message passing; Parallel robots; Pipeline processing; Robot control; Robot sensing systems; Software and its engineering > Software organization and properties > Software system structures > Distributed systems organizing principles > Grid computing
• ISBN: 0818643404; 9780818643408
• ISSN: 1063-9535
• DOI: 10.1145/169627.169714

Parallel image processing for robotics applications differs in a fundamental way from parallel scientific computing applications: the problem size is fixed, and latency requirements are tight. This brings Amdhal's law in effect with full force, so that message-passing latency and bandwidth severely restrict performance. The authors examine an application from this domain, stereo image processing, which has been implemented in Adapt, a niche language for parallel image processing implemented on the Carnegie Mellon-Intel Corporation iWarp. High performance has been achieved for this application. It is shown how a I/O building block approach on iWarp achieved this, and the implications of this performance for more traditional machines that do not have iWarp's rich I/O primitive set are examined.