摘要: A genetic algorithm (GA) is a robust problem-solving method based on natural selection. Hardware's speed advantage and its ability to parallelize offer great rewards algorithms. Speedups of 1-3 orders magnitude have been observed when frequently used software routines were implemented in hardware by way reprogrammable field-programmable gate arrays (FPGAs). Reprogrammability essential general-purpose GA engine because certain modules require changeability (e.g. the function be optimized GA). Thus hardware-based both feasible desirable. fully functional (the HGA) presented here as proof-of-concept system. It was designed using VHDL allow for easy scalability. act coprocessor with CPU PC. The user programs FPGAs which implement optimized. Other parameters may also specified user. Simulation results performance analyses HGA are presented. prototype described compared similar software. In simple tests, took about 6% many clock cycles run software-based GA. Further suggested improvements could realistically make 2–3 faster than
acm.org
elsevier.com
sci-hub.se 参考文章(9)
Pak K. Chan, A FIELD-PROGRAMMABLE PROTOTYPING BOARD: XC4000 BORG USER''S GUIDE University of California at Santa Cruz. ,(1994)
William M. Spears, Kenneth A. De Jong, Using Genetic Algorithms to Solve NP-Complete Problems international conference on genetic algorithms. pp. 124- 132 ,(1989)
M. Gokhale, W. Holmes, A. Kopser, S. Lucas, R. Minnich, D. Sweely, D. Lopresti, Building and using a highly parallel programmable logic array IEEE Computer. ,vol. 24, pp. 81- 89 ,(1991) , 10.1109/2.67197
P.M. Athanas, H.F. Silverman, Processor reconfiguration through instruction-set metamorphosis IEEE Computer. ,vol. 26, pp. 11- 18 ,(1993) , 10.1109/2.204677
J.G. Eldredge, B.L. Hutchings, Density enhancement of a neural network using FPGAs and run-time reconfiguration field programmable gate arrays. pp. 180- 188 ,(1994) , 10.1109/FPGA.1994.315611
S. Casselman, Virtual computing and the Virtual Computer [1993] Proceedings IEEE Workshop on FPGAs for Custom Computing Machines. pp. 43- 48 ,(1993) , 10.1109/FPGA.1993.279480
P. Bertin, D. Roncin, J. Vuillemin, Programmable active memories: a performance assessment Proceedings of the First Heinz Nixdorf Symposium on Parallel Architectures and Their Efficient Use. pp. 119- 130 ,(1992) , 10.1007/3-540-56731-3_12
P. Kenyon, S. Seth, A. Clematis, P. Agrawal, G. Dodero, V. Gianuzzi, Programming pipelined CAD applications on message-passing architectures Concurrency and Computation: Practice and Experience. ,vol. 7, pp. 315- 337 ,(1995) , 10.1002/CPE.4330070405
David E. Goldberg, Genetic algorithms in search, optimization and machine learning Reading: Addison-Wesley. ,(1989)