Abstract
In many application domains, it is desirable to meet some user-defined performance requirement while minimizing resource usage and optimizing additional performance parameters. For example, application workflows with real-time constraints may have strict throughput requirements and desire a low latency or response-time. The structure of these workflows can be represented as directed acyclic graphs of coarse-grained application tasks with data dependences. In this paper, we develop a novel mapping and scheduling algorithm that minimizes the latency of workflows that act on a stream of input data, while satisfying throughput requirements. The algorithm employs pipelined parallelism and intelligent clustering and replication of tasks to meet throughput requirements. Latency is minimized by exploiting task parallelism and reducing communication overheads. Evaluation using synthetic benchmarks and application task graphs shows that our algorithm 1) consistently meets throughput requirements even when other existing schemes fail, 2) produces lower-latency schedules, and 3) results in lesser resource usage.
This research was supported in part by the National Science Foundation under Grants #CCF-0342615 and #CNS-0403342.
Chapter PDF
Similar content being viewed by others
References
Kumar, V.S., Rutt, B., Kurc, T., Catalyurek, U., Saltz, J., Chow, S., Lamont, S., Martone, M.: Large image correction and warping in a cluster environment. In: Supercomputing Conf., p. 79 (2006)
Guirado, F., Ripoll, A., Roig, C., Luque, E.: Optimizing latency under throughput requirements for streaming applications on cluster execution. In: Cluster Computing Conf. (2005)
Spencer, M., Ferreira, R., Beynon, M., Kurc, T., Catalyurek, U., Sussman, A., Saltz, J.: Executing multiple pipelined data analysis operations in the grid. In: Supercomputing Conf., pp. 1–18 (2002)
Shukla, S.B., Agrawal, D.P.: Scheduling pipelined communication in distributed memory multiprocessors for real-time applications. SIGARCH Comput. Archit. News 19(3) (1991)
Garey, M.R., Johnson, D.S.: Computers and Intractability; A Guide to the Theory of NP-Completeness. W. H. Freeman & Co, New York, USA (1990)
Kwok, Y.K., Ahmad, I.: Static scheduling algorithms for allocating directed task graphs to multiprocessors. ACM Comput. Surv. 31(4), 406–471 (1999)
Hary, S.L., Ozguner, F.: Precedence-constrained task allocation onto point-to-point networks for pipelined execution. IEEE Trans. Par. Distrib. Syst. 10(8), 838–851 (1999)
Yang, M.T., Kasturi, R., Sivasubramaniam, A.: A pipeline-based approach for scheduling video processing algorithms on now. IEEE Trans. Par. Distrib. Syst. 14(2), 119–130 (2003)
Benoit, A., Robert, Y.: Mapping pipeline skeletons onto heterogeneous platforms. Technical Report LIP RR-2006-40 (2006)
Subhlok, J., Vondran, G.: Optimal latency-throughput tradeoffs for data parallel pipelines. In: 8th ACM Symp. on Parallel Algorithms and Arch, pp. 62–71. ACM Press, New York (1996)
Benoit, A., Robert, Y.: Complexity results for throughput and latency optimization of replicated and data-parallel workflows. Technical Report LIP RR-2007-12 (2007)
Vydyanathan, N., Catalyurek, U., Kurc, T., Sadayappan, P., Saltz, J.: An approach for optimizing latency under throughput constraints for application workflows on clusters. Technical Report OSU-CISRC-1/07-TR03, The Ohio State University (2007)
Davidovic, T., Crainic, T.G.: Benchmark-problem instances for static scheduling of task graphs with communication delays on homogeneous multiprocessor systems. Computers & OR 33(8), 2155–2177 (2006)
Vallerio, K.: Task graphs for free, http://ziyang.ece.northwestern.edu/tgff/maindoc.pdf
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vydyanathan, N., Catalyurek, U.V., Kurc, T.M., Sadayappan, P., Saltz, J.H. (2007). Toward Optimizing Latency Under Throughput Constraints for Application Workflows on Clusters. In: Kermarrec, AM., Bougé, L., Priol, T. (eds) Euro-Par 2007 Parallel Processing. Euro-Par 2007. Lecture Notes in Computer Science, vol 4641. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74466-5_20
Download citation
DOI: https://doi.org/10.1007/978-3-540-74466-5_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74465-8
Online ISBN: 978-3-540-74466-5
eBook Packages: Computer ScienceComputer Science (R0)