Abstract
Evolutionary algorithms are useful optimization tools but are very time consuming to run. We present a self-contained FPGA-based implementation of a spatially-structured evolutionary algorithm that provides significant speedup over conventional serial processing in three ways: (a) efficient hardware-pipelined fitness evaluation of individuals, (b) evaluation of an entire population of individuals in parallel, and (c) elimination of slow off-chip communication. We demonstrate using the system to solve a non-trivial signal reconstruction problem using a non-linear digital filter on a Xilinx Virtex FPGA, and find a speedup factor of over 1000 compared to a C implementation of the same system. The general principles behind the system are very scalable, and as FPGAs become even larger in the future, similar systems will provide extremely large speedups over serial processing.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Chen, K. (1989). Bit-serial realizations of a class of nonlinear filters based on positive boolean functions. IEEE Transactions on Circuits and Systems, 36(6).
Chu, C. (1990). The application of an adaptive plan to the configuration of nonlinear image processing algorithms. In SPIE Proceedings-Nonlinear Image Processing, volume 1247, pages 248–257.
Higuchi, T., Iwata, M., and Liu, W., editors (1996). Evolvable Systems: From Biology to Hardware: Proc. ICES’ 96, volume 1259 of Lecture Notes in Computer Science. Springer.
Manderick, B. and Spiessens, P. (1989). Fine-grained parallel genetic algorithms. In Schaffer, J., editor, Proc. 3rd Int. Conf on Genetic Algorithms. Morgan Kaufmann.
Sipper, M. (1997). Evolution of Parallel Cellular Machines, volume 1194 of Lecture Notes in Computer Science. Springer-Verlag.
Sipper, M., Mange, D., and Pérez-Uribe, A., editors (1998). Evolvable Systems: From Biology to Hardware: Proc. ICES’ 98, volume 1478 of Lecture Notes in Computer Science. Springer.
Woolfries, N., Lysaght, P., Marshall, P., McGregor, S., and Robinson, G. (1998). Fast adaptive image processing in fpgas using stack filters. In Hartenstein, R. W. and Keevallik, A., editors, Field Programmable Logic and Applications: From FPGAs to Computing Paradigm: 8th Int. Workshop.
Xilinx, I. (1999). Virtex 2.5v field programmable gate arrays. Advance Product Specification. Version 1.3.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Perkins, S., Porter, R., Harvey, N. (2000). Everything on the Chip: A Hardware-Based Self-Contained Spatially-Structured Genetic Algorithm for Signal Processing. In: Miller, J., Thompson, A., Thomson, P., Fogarty, T.C. (eds) Evolvable Systems: From Biology to Hardware. ICES 2000. Lecture Notes in Computer Science, vol 1801. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46406-9_17
Download citation
DOI: https://doi.org/10.1007/3-540-46406-9_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-67338-5
Online ISBN: 978-3-540-46406-8
eBook Packages: Springer Book Archive