Abstract
Partial dynamic reconfiguration (often referred to as partial RTR) enables true on-demand computing. In an on-demand computing environment, a dynamically invoked application is assigned resources such as data bandwidth, configurable logic. The limited logic resources are customized during application execution by exploiting partial RTR. In this article, we propose an approach that maximizes application performance when available bandwidth and logic resources are limited. Our proposed approach is based on theoretical principles of minimizing application schedule length under bandwidth and logic resource constraints. It includes detailed microarchitectural considerations on a commercially popular reconfigurable device, and it exploits partial RTR very effectively by utilizing data-parallelism property of common image-processing applications. We present extensive application case studies on a cycle-accurate simulation platform that includes detailed resource considerations of the Xilinx Virtex XC2V3000. Our experimental results demonstrate that applying our proposed approach to common image-filtering applications leads to 15--20% performance gain in scenarios with limited bandwidth, when compared to prior work that also exploits data-parallelism with RTR but includes simpler bandwidth considerations. Last but not the least, we also demonstrate how our proposed theoretical principles can be directly applied to solve related problems such as minimizing schedule length under logic resource and power constraints.
- }}AMBA. See http://www.arm.com/products/solutions/AMBAHomePage.html.Google Scholar
- }}Banerjee, S., Bozorgzadeh, E., and Dutt, N. 2006a. PARLGRAN: Parallelism granularity selection for scheduling task chains on dynamically reconfigurable architectures. In Proceedings of the Asia South Pacific Design Automation Conference (ASPDAC). 491--496. Google Scholar
Digital Library
- }}Banerjee, S., Bozorgzadeh, E., Noguera, J., and Dutt, N. 2006b. Minimizing peak power for application chains on architectures with partial dynamic reconfiguration. In Proceedings of the International Conference on Field Programmable Technology (FPT). 273--276.Google Scholar
- }}Banerjee, S., Bozorgzadeh, E., Noguera, J., and Dutt, N. 2007. Selective bandwidth and resource management in scheduling for dynamically reconfigurable architectures. In Proceedings of the Design Automation Conference (DAC). 771--776. Google Scholar
Digital Library
- }}Banerjee, S., Bozorgzadeh, E., Noguera, J., and Dutt, N. 2008. Bandwidth-aware scheduling and task frequency assignment on architectures with partial dynamic reconfiguration. CECS Tech. Rep., University of California, Irvine.Google Scholar
- }}Bobda, C., Majer, M., Ahmadiniya, A., Haller, T., Linarth, A., and Teich, J. 2005. The Erlangen Slot machine: Increasing flexibility in FPGA-based reconfigurable platforms. In Proceedings of the International Conference on Field-Programmable Technology (FPT). 37--42.Google Scholar
- }}Fekete, S. P., Kohler, E., and Teich, J. 2001. Optimal FPGA module placement with temporal precedence constraints. In Proceedings of the Design Automation and Test in Europe (DATE). 658--667. Google Scholar
Digital Library
- }}Ghiasi, S. and Sarrafzadeh, M. 2003. Optimal reconfiguration sequence management. In Proceedings of the Asia South Pacific Design Automation Conference (ASPDAC). 359--365. Google Scholar
Digital Library
- }}Huebner, M., Becker, T., and Becker, J. 2004. Real-Time LUT-based network topologies for dynamic and partial self-reconfiguration. In Proceedings of the Symposium on Integrated Circuits and Systems Design (SBCCI). 28--32. Google Scholar
Digital Library
- }}Krasteva, Y. E., Jimeno, A. B., Torre, E., and Riesgo, T. 2005. Flexible core reallocation for Virtex-II structures. In Proceedings of the International Conference on Engineering of Reconfigurable Systems and Algorithms (ERSA). 189--195.Google Scholar
- }}Li, F., Lin, Y., and He, L. 2004. FPGA power reduction using configurable dual-Vdd. In Proceedings of the Design Automation Conference (DAC). 735--740. Google Scholar
Digital Library
- }}Li, Z. 2002. Configuration management techniques for reconfigurable computing. Ph.D. thesis, Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL.Google Scholar
- }}Lysaught, P., Blodget, B., Mason, J., Young, J., and Bridgeford, B.. 2006. Enhanced architectures, design methodologies, and CAD tools for dynamic reconfiguration of Xilinx FPGAs. In Proceedings of the International Conference on Field-Programmable Logic, and Applications Applications (FPL). 1--6.Google Scholar
- }}Noguera, J. and Badia, R. M. 2002. Dynamic runtime HW/SW scheduling techniques for reconfigurable architectures. In Proceedings of the International Conference on Hardware-Software Codesign (CODES). 205--210. Google Scholar
Digital Library
- }}Noguera, J. and Badia, R. M. 2005. Performance and energy analysis of task-level graph transformation techniques on dynamically reconfigurable architectures. In Proceedings of the International Conference on Field Programmable Logic and Applications (FPL). 563--567.Google Scholar
- }}Palma, J. C., Melo, A. V., Moraes, F. G., and Calazans, N. 2002. Core communication interface for FPGAs. In Proceedings of the Symposium on Integrated Circuits and Systems Design (SBCCI). 183--190. Google Scholar
Digital Library
- }}Panainte, E. M., Bertels, K., and Vassiliadis, S. 2006. Interprocedural compiler optimization for partial runtime reconfiguration. J. VLSI Signal Process. 43, 2, 161--172. Google Scholar
Digital Library
- }}Quinn, H., King, L. A. S., Leeser, M., and Meleis, W. 2003. Runtime assignment of reconfigurable hardware components for image processing pipelines. In Proceedings of the IEEE Symposium on Field Programmable Custom Computing Machines (FCCM). 173--182. Google Scholar
Digital Library
- }}Resano, J., Mozos, D., and Catthoor, F. 2005. A hybrid prefetch scheduling heuristic to minimize at runtime the reconfiguration overhead of dynamically reconfigurable architectures. In Proceedings of the Design Automation and Test in Europe (DATE). 106--111. Google Scholar
Digital Library
- }}Sedcole, N., Cheung, P. Y. K., Constantinides, G. A., and Luk, W. 2003. A reconfigurable platform for real-time embedded video image processing. In Proceedings of the Field Programmable Logic and Applications (FPL). 606--615.Google Scholar
- }}Sedcole, P., Blodget, B., Becker, T., Anderson, J., and Lysaught, P. 2006. Modular dynamic reconfiguration in Virtex FPGAs. IEE Proceedings of the Computers Digital Techniques 153, 3, 157--164.Google Scholar
Cross Ref
- }}Shin, Y., Choi, K., and Sakurai, T. 2000. Power optimization of real-time embedded systems on variable speed processors. In Proceedings of the International Conference on Computer-Aided Design (ICCAD). 365--368. Google Scholar
Digital Library
- }}Singh, D., Rabaey, J. M., Pedram, M., Catthoor, F., Rajgopal, S., Sehgal, N., and Mozdzen, T. J. 1995. Power conscious CAD tools and Methodologies: A perspective. Proc. IEEE 83, 4, 570--594.Google Scholar
Cross Ref
- }}Singh, H., Lu, G., Filho, E. M. C., Maestre, R., Lee, M.-H., Kurdahi, F. J., and Bagherzadeh, N. 2000. MorphoSys: Case study of a reconfigurable computing system targeting multimedia applications. In Proceedings of the Design Automation Conference (DAC). 573--578. Google Scholar
Digital Library
- }}Stefanov, T., Kienhuis, B., and Deprettere, E. 2002. Algorithmic transformation techniques for efficient exploration of alternative application instances. In Proceedings of the International Symposium on Hardware/Software Codesign (CODES). 7--12. Google Scholar
Digital Library
- }}Steiger, C., Walder, H., and Platzner, M. 2004. Operating systems for reconfigurable embedded platforms: Online scheduling of real-time tasks. IEEE Trans. Comput. 53, 11, 1393--1407. Google Scholar
Digital Library
- }}Vikram, K. N. and Vasudevan, V. 2006. Mapping data-parallel tasks onto partially reconfigurable hybrid processor architectures. IEEE Trans. VLSI 14, 9, 1010--1023. Google Scholar
Digital Library
- }}Xilinx. http://direct.xilinx.com/bvdocs/userguides/ug002.pdf.Google Scholar
Index Terms
Bandwidth Management in Application Mapping for Dynamically Reconfigurable Architectures
Recommendations
Selective bandwidth and resource management in scheduling for dynamically reconfigurable architectures
DAC '07: Proceedings of the 44th annual Design Automation ConferencePartial dynamic reconfiguration (often referred to as partial RTR) enables true on-demand computing. A dynamically invoked application is assigned resources such as data bandwidth, configurable logic, and the limited logic resources are customized ...
Pipeline Reconfigurable DSP for Dynamically Reconfigurable Architectures
Dynamically reconfigurable architectures, such as NATURE, achieve high logic density and low reconfiguration latency compared to traditional field-programmable gate arrays. Unlike fine-grained NATURE, reconfigurable DSP block incorporated NATURE ...
Hardware supported task scheduling on dynamically reconfigurable SoC architectures
Dynamically reconfigurable system-on-a-chip (RSoC) technology features embedded microprocessors that are dispersed on the same die with significant amounts of programmable logic fabric. In this paper, we present a strategy to solve the recently emerging ...






Comments