ABSTRACT
Cyclo-Static DataFlow (CSDF) is a powerful model for the specification of DSP applications. However, as in any asynchronous model, the synchronization of the different communicating tasks (processes) is made through buffers that have to be sized such that timing constraints are met. In this paper, we want to determine buffer sizes such that the throughput constraint is satisfied. This problem has been proved to be of exponential complexity. Exact techniques to solve this problem are too time and/or space consuming because of the self-timed schedule needed to evaluate the maximum throughput. Therefore, a periodic schedule is used. Each CSDF actor is associated with a period that satisfies the throughput constraint and sufficient buffer sizes are derived in polynomial time. However, within a period, an actor phases can be scheduled in different manners which impacts the evaluation of sufficient buffer sizes. This paper presents a Min-Max Linear Program that derives an optimized periodic phases scheduling per CSDF actor in order to minimize buffer sizes. It is shown through different applications that this Min-Max Linear Program allows to obtain close to optimal values while running in polynomial time.
- M. Benazouz et al. A new method for minimizing buffer sizes for cyclo-static dataflow graphs. In 8th IEEE Workshop ESTIMedia, pages 11--20, 2010.Google ScholarCross Ref
- G. Bilsen et al. Cyclo-static data flow. International Conference on Acoustics, Speech, and Signal Processing, 5:3255--3258, 1995.Google ScholarCross Ref
- T. H. Cormen, C. E. Leiseerson, R. Rivest, and C. Stein. Introduction to Algorithms. MIT Press, 1990. Google ScholarDigital Library
- R. Cruz. A calculus for network delay. i. network elements in isolation. IEEE Transactions on Information Theory, 37(1):114--131, Jan. 1991. Google ScholarDigital Library
- A. Dasdan et al. Efficient algorithms for optimum cycle mean and optimum cost to time ratio problems. In DAC, pages 37--42, 1999. Google ScholarDigital Library
- K. Denolf et al. Exploiting the expressiveness of cyclo-static dataflow to model multimedia implementations. EURASIP Journal on Advances in Signal Processing, page 14 pages, 2007.Google Scholar
- D. Ding-Zhu and P. Panos M. Minimax and Applications. Kluwer Academic Publishers, 1995.Google Scholar
- D. D. Gajski, S. Abdi, A. Gerstlauer, and G. Schirner. Embedded System Design: Modeling, Synthesis and Verification. Springer Publishing Company, Incorporated, 1st edition, 2009. Google ScholarDigital Library
- E. A. Lee. Consistency in dataflow graphs. IEEE Trans. Parallel Distrib. Syst., 2:223--235, April 1991. Google ScholarDigital Library
- E. A. Lee and D. G. Messerschmitt. Synchronous data flow. IEEE Proceedings of the IEEE, 75(9), 1987.Google ScholarCross Ref
- O. Marchetti and A. Munier-Kordon. Complexity results for weighted timed event graphs. Discrete Optimization, 7:166--180, 2010. Google ScholarDigital Library
- A. Moonen et al. Evaluation of the throughput computed with a dataflow model - a case study. TU Eindhoven, Tech. Rep., 2007.Google Scholar
- H. Oh and S. Ha. Fractional rate dataflow model and efficient code synthesis for multimedia applications. ACM SIGPLAN NOTICE, 37:12--17, 2002. Google ScholarDigital Library
- T. M. Parks et al. A comparison of synchronous and cycle-static dataflow. In Proceedings of the 29th Asilomar Conference on Signals, Systems and Computers, page 204, 1995. Google ScholarDigital Library
- S. Stuijk et al. SDF3: SDF For Free. In Proceedings of 6th Application of Concurrency to System Design Conference, pages 276--278, June 2006. Google ScholarDigital Library
- S. Stuijk et al. Throughput-buffering trade-off exploration for cyclo-static and synchronous dataflow graphs. IEEE Trans. Comput., 57:1331--1345, 2008. Google ScholarDigital Library
- E. Teruel et al. On weighted T-systems. In Proocedings of the 13th Internationnal Conference on Application and Theory of Petri Nets, volume 616. Springer, 1992. Google ScholarDigital Library
- M. H. Wiggers et al. Efficient computation of buffer capacities for cyclo-static dataflow graphs. In DAC, pages 658--663. ACM, 2007. Google ScholarDigital Library
- M. H. Wiggers et al. Efficient computation of buffer capacities for cyclo-static real-time systems with back-pressure. In 13th IEEE RTAS Symposium, pages 281--292, 2007. Google ScholarDigital Library
Index Terms
- Cyclo-static DataFlow phases scheduling optimization for buffer sizes minimization
Recommendations
Efficient computation of buffer capacities for cyclo-static dataflow graphs
DAC '07: Proceedings of the 44th annual Design Automation ConferenceA key step in the design of cyclo-static real-time systems is the determination of buffer capacities. In our multi-processor system, we apply back-pressure, which means that tasks wait for space in output buffers. Consequently buffer capacities affect ...
Strictly Periodic Scheduling of Cyclo-Static Dataflow Models
Embedded Computer Systems: Architectures, Modeling, and SimulationAbstractThis paper considers strictly periodic schedules for Cyclo-Static Dataflow Graphs (CSDFGs) where, for every task, only the start time of the first phase of the first iteration is fixed. This alternative CSDFG scheduling paradigm presents further ...
Buffer minimization in earliest-deadline first scheduling of dataflow graphs
LCTES '13: Proceedings of the 14th ACM SIGPLAN/SIGBED conference on Languages, compilers and tools for embedded systemsSymbolic schedulability analysis of dataflow graphs is the process of synthesizing the timing parameters (i.e. periods, phases, and deadlines) of actors so that the task system is schedulable and achieves a high throughput when using a specific ...
Comments