Improving the Performance and Efficiency of an Adaptive Amplification Operation Using Configurable Hardware

Authors:
Michael J. Wirthlin;Steve Morrison;Paul Graham;Brian Bray
Affiliations:
-;-;-;-
Venue:
FCCM '00 Proceedings of the 2000 IEEE Symposium on Field-Programmable Custom Computing Machines
Year:
2000

Citing 8
Cited 2

The PowerPC architecture: a specification for a new family of RISC processors

The PowerPC architecture: a specification for a new family of RISC processors
FPGA-based sonar processing

FPGA '98 Proceedings of the 1998 ACM/SIGDA sixth international symposium on Field programmable gate arrays
Automated target recognition on SPLASH 2

FCCM '97 Proceedings of the 5th IEEE Symposium on FPGA-Based Custom Computing Machines
Field Programmable Gate Array Based Radar Front-End Digital Signal Processing

FCCM '99 Proceedings of the Seventh Annual IEEE Symposium on Field-Programmable Custom Computing Machines
A CAD Suite for High-Performance FPGA Design

FCCM '99 Proceedings of the Seventh Annual IEEE Symposium on Field-Programmable Custom Computing Machines
Reconfigurable Processing: The Solution to Low-Power Programmable DSP

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 1 - Volume 1
Flexible image acquisition using reconfigurable hardware

FCCM '95 Proceedings of the IEEE Symposium on FPGA's for Custom Computing Machines
Reconfigurable architectures for general-purpose computing

Reconfigurable architectures for general-purpose computing

Using Design-Level Scan to Improve FPGA Design Observability and Controllability for Functional Verification

FPL '01 Proceedings of the 11th International Conference on Field-Programmable Logic and Applications
Applications of adaptive computing systems for signal processing challenges

ASP-DAC '03 Proceedings of the 2003 Asia and South Pacific Design Automation Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

An adaptive amplification operation has been designed and tested in configurable hardware for a computationally intensive object recognition system. This configurable system provides over forty-one times the throughput of an industry-standard embedded processor by exploiting the bandwidth of internal block memories and parallelism within the algorithm. Operating at less than one half the power of the programmable processor, the configurable approach performs the computation with 90 times less energy. The improvements in both performance and power are obtained by customizing the datapath, memory interfaces, and control to the amplification algorithm.