Hardware Accelerator of Cartesian Genetic Programming with Multiple Fitness Units

Authors

  • Zdeněk Vašíček
  • Lukáš Sekanina

Keywords:

Cartesian genetic programming, hardware accelerator, evolutionary circuit design, FPGA

Abstract

A new accelerator of Cartesian genetic programming is presented in this paper. The accelerator is completely implemented in a single FPGA. The proposed architecture contains multiple instances of virtual reconfigurable circuit to evaluate several candidate solutions in parallel. An advanced memory organization was developed to achieve the maximum throughput of processing. The search algorithm is implemented using the on-chip PowerPC processor. In the benchmark problem (image filter evolution) the proposed platform provides a significant speedup (170) in comparison with a highly optimized software implementation. Moreover, the accelerator is 8 times faster than previous FPGA accelerators of image filter evolution.

Downloads

Download data is not yet available.

Author Biographies

Zdeněk Vašíček

Faculty of Information Technology
Brno University of Technology
Božetechova 2
612 66 Brno, Czech Republic

Lukáš Sekanina

Faculty of Information Technology
Brno University of Technology
Božetechova 2
612 66 Brno, Czech Republic

Downloads

Published

2012-01-26

How to Cite

Vašíček, Z., & Sekanina, L. (2012). Hardware Accelerator of Cartesian Genetic Programming with Multiple Fitness Units. COMPUTING AND INFORMATICS, 29(6+), 1359–1371. Retrieved from https://www.cai.sk/ojs/index.php/cai/article/view/149