Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Smart Pixel ARray Cellular Logic (SPARCL) Processor for Eliminating SIMD I/O Bottlenecks: System Demonstration and Performance Scaling

Not Accessible

Your library or personal account may give you access

Abstract

Running an image or data processing routine on a computing machine requires three distinct steps: 1) moving the data from an input device (such as a memory or video camera) to the processor(s); 2) performing the operations required by the routine; and 3) moving the data from the processor(s) to an output device (a memory or display device). The processing speed, Spr, is a measure of computational performance and is defined as the number of data elements (or pixels) processed divided by the time required to process them, described by where Tl Top, Tu, is the time required to load, operate on, and unload the N × N data field or image, respectively.

© 1997 Optical Society of America

PDF Article
More Like This
Smart Pixel Array Network Interface (SAPIENT) for 2D Parallel Data Packet Networks

C.-H. Chen, B. Hoanca, C.B. Kuznia, J.-M. Wu, and A.A. Sawchuk
OThD.11 Optics in Computing (IP) 1997

GaAs Smart Pixel Arrays for High Performance Optoelectronic Computing Modules

D. S. McCallum, J. W. Kim, P. S. Guilfoyle, W. H. Chang, J. Mu, and M. Feng
OFB.3 Optics in Computing (IP) 1997

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.