22 November 1999 Building a better bathtub: computing at the optical memory interface
Author Affiliations +
Abstract
To fully exploit the high bandwidth and inherent parallelism of optical memory systems, it is necessary to perform correspondingly parallel computations at or near the interface to the memory system. In this paper, we present a system in which a dynamically reconfigurable processor is built at the optical memory interface. Dynamically reconfigurable processors exploit parallelism at the level of individual machine instructions. They are based on the time multiplexing of gate array logic between various processor configurations, each of which is matched to a particular required computation. This paper is an analysis of the performance of an optically reconfigurable processor in comparison to conventional multiple instruction issue processors. We will show that the volume of configuration data required makes these systems difficult to build in electronic implementations but ideal for implementations with optical memory.
© (1999) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Donald M. Chiarulli, Steven Peter Levitan, Robert Hofmann, "Building a better bathtub: computing at the optical memory interface", Proc. SPIE 3802, Advanced Optical Data Storage: Materials, Systems, and Interfaces to Computers, (22 November 1999); doi: 10.1117/12.370227; https://doi.org/10.1117/12.370227
PROCEEDINGS
6 PAGES


SHARE
RELATED CONTENT

SCSI applications on fiber channel
Proceedings of SPIE (February 09 1993)
Optical Storage System Architecture
Proceedings of SPIE (May 19 1989)
Solving graph problems with dynamic computation structures
Proceedings of SPIE (October 21 1996)
Improved memory interfaces based on multiphase clocks
Proceedings of SPIE (November 05 1998)
Programmable hardware for reconfigurable computing systems
Proceedings of SPIE (October 21 1996)

Back to Top