SLAPP: A systolic linear algebra parallel processor
- Naval Ocean Systems Center and Cornell Univ.
Systolic array computer architectures provide a means for fast computation of the linear algebra algorithms that form the building blocks of many signal-processing algorithms, facilitating their real-time computation. For applications to signal processing, the systolic array operates on matrices, an inherently parallel view of the data, using numerical linear algebra algorithms that have been suitably parallelized to efficiently utilize the available hardware. This article describes work currently underway at the Naval Ocean Systems Center, San Diego, California, to build a two-dimensional systolic array, SLAPP, demonstrating efficient and modular parallelization of key matric computations for real-time signal- and image-processing problems.
- OSTI ID:
- 5804084
- Journal Information:
- Computer; (United States), Vol. 20:7; ISSN 0018-9162
- Country of Publication:
- United States
- Language:
- ENGLISH
Similar Records
Systolic processor for signal processing
Software development on the High-Speed Systolic Array Processor (HISSAP): Lessons learned. Final report, Mar 88-Mar 91