An Integrated Online Scheduling and Placement Methodology
Dynamic task scheduling and online placement are two of the main responsibilities of an operating system for reconfigurable platforms. Since these operations are performed during run-time of the applications, these are overheads on the execution time. There is a need to find fast and efficient algorithms for task placement and scheduling. We propose an integrated online scheduling and placement methodology. We maintain empty area as a list of maximal empty rectangles which allows us to explore solution space efficiently. We defer scheduling decisions until it is absolutely necessary to accommodate dynamically changing task priorities. We propose task queue management data-structures for in-order and out-of-order task scheduling strategies. One of our queuing strategies guarantees the shortest execution time for in-order task execution and the other strategy results in better FPGA area utilization for out-of-order task execution. We provide experimental evidence of improvement our methodology yields over the previous approaches.
KeywordsTask Schedule Online Schedule Input Queue Task Placement Empty Area
Unable to display preview. Download preview PDF.
- 1.Underwood, K.: FPGAs Vs. CPUs: Trends in Peak Floating-Point Performance. In: Proceedings of the Twelfth ACM International Symposium on Field-Programmable Gate Arrays (February 2004)Google Scholar
- 3.Mei, B., Schaumont, P., Vernalde, S.: AHardware-Software Partitioning and Scheduling Algorithm for Dynamically Reconfigurable Embedded Systems. In: 11th ProRISC workshop on Circuits, Systems and Signal Processing Veldhoven, Netherlands (November 2000)Google Scholar
- 4.Dick, R.P., Jha, N.K.: Cords: hardware-software co-synthesis of reconfigurable real-time distributed embedded systems. In: Proceedings of the 1998 IEEE/ACMinternational conference on Computer-aided design, pp. 62–67 (1998)Google Scholar
- 5.Noguera, J., Badia, R.M.: Dynamic run-time hw/sw scheduling techniques for reconfigurable architectures. In: Proceedings of the tenth international symposium on Hardware/software codesign, pp. 205–210 (2002)Google Scholar
- 6.Shang, L., Jha, N.K.: Hardware-Software Co-Synthesis of Low Power Real-Time Distributed Embedded Systems with Dynamically Reconfigurable FPGAs. In: Proceedings of the 15th International Conference on VLSI Design, VLSID 2002 (January 2002)Google Scholar
- 7.Steiger, C., Walder, H., Platzner, M., Thiele, L.: Online Scheduling and Placement of Real-timeTasks to Partially Reconfigurable Devices. In: 24th IEEE International Real-Time Systems Symposium, Cancun, Mexico (December 2003)Google Scholar
- 8.Handa, M., Vemuri, R.: An Efficient Algorithm for Finding Empty Space for Online FPGA Placement. In: Proceeding of the 41st Design Automation Conference (June 2004)Google Scholar
- 9.Bazargan, K., Kastner, R., Sarrafzadeh, M.: Fast Template Placement for Reconfigurable Computing Systems. IEEE Design and Test - Special Issue on Reconfigurable Computing 17(1), 68–83 (2000)Google Scholar
- 10.Walder, H., Steiger, C., Platzner, M.: Fast Online Task Placement on FPGAs: Free Space Partitioning and 2D-Hashing. In: International Parallel and Distributed Processing Symposium (IPDPS 2003), p. 178 (April 2003)Google Scholar