FPGA Framework for Agent Systems Using Dynamic Partial Reconfiguration
Dynamic Partial Reconfiguration of FPGAs enables tasks typically executed in software, such as threads and agents, to be executed directly in hardware. Typically, these systems use a CPU to manage the hardware and software tasks, but they do not take full advantage of the concurrency capable from an FPGA. This paper presents a hardware framework that leverages the concept of agents for FPGA-based designs. This enables not only the hardware modules to be viewed as agents, but also provides a means to selectively design and componentize the communications network for the hardware agents. The proposed framework enables hardware agents to be implemented to run concurrently and allows them to communicate with each other without requiring a CPU.
KeywordsDynamic Partial Reconfiguration FPGA Hardware Abstraction Agent Systems
Unable to display preview. Download preview PDF.
- 6.Gabrick, M., Nicholson, R.: Winters. F., Young, B., Patton, J.: FPGA Considerations for Automotive Applications. In: Proceedings of SAE World Congress and Exhibition (2006)Google Scholar
- 8.Lysaght, P., Blodget, B., Mason, J., Young, J., Bridgeford, B.: Enhanced Architecture, Design Methodologies and CAD tools for Dynamic Reconfiguration for Xilinx FPGAs. In: Proceedings of International Conference on Field Programmable Logic and Applications, Madrid, Spain, pp. 1–6 (2006)Google Scholar
- 9.Kao, C.: Benefits of Partial Reconfiguration. Xcell Journal, Fourth Quarter, Xilinx, Inc., 65–68 (2005)Google Scholar
- 11.Field Programmable Gate Arrays, http://en.wikipedia.org/wiki/fpga
- 12.Altera Corporation: FPGA Run-Time Reconfiguration: Two Approaches. White Paper 01055, version 1.0 (2008)Google Scholar
- 13.Wooldridge, M., Jenning, N.: Intelligent Agents – Theories, Architectures, and Languages. Lectures Notes in Artificial Intelligence (1995)Google Scholar
- 18.Ismail, A., Shannon. L.: FUSE: Front-end User Framework for OS Abstraction of Hardware Accelerators. In: IEEE Symposium on Field Programmable Custom Computing Machines, Salt Lake City, Utah, pp. 170–177 (2011)Google Scholar