Abstract
Using historical information to predict future runs of parallel jobs has shown to be valuable in job scheduling. Trends toward more flexible job-scheduling techniques such as adaptive resource allocation, and toward the expansion of scheduling to grids, make runtime predictions even more important. We present a technique of employing both a user’s knowledge of his/her parallel application and historical application-run data, synthesizing them to derive accurate and scalable predictions for future runs. These scalable predictions apply to runtime characteristics for different numbers of nodes (processor scalability) and different problem sizes (problem-size scalability). We employ multiple linear regression and show that for decently accurate complexity models, good prediction accuracy can be obtained.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Sodan, A.C., Liu, L.: Dynamic Multi-Resource Monitoring for Predictive Job Scheduling with ScoPro. Technical Report 04-002, U of W, CS Department (February 2005)
Sodan, A.C., Huang, X.: Adaptive Time/Space Scheduling with SCOJO. In: Int. Symp. on High-Performance Computing Systems (HPCS), Winnipeg/Manitoba, May 2004, pp. 165–178 (2004)
Sodan, A.C., Han, L.: ATOP–Space and Time Adaptation for Parallel and Grid Applications via Flexible Data Partitioning. In: 3rd ACM/IFIP/USENIX Workshop on Reflective and Adaptive Middleware, Toronto (October 2004)
Sodan, A.C., Lan, L.: LOMARC–Lookahead Matchmaking in Multi-Resource Coscheduling. In: Feitelson, D.G., Rudolph, L., Schwiegelshohn, U. (eds.) JSSPP 2004. LNCS, vol. 3277, pp. 288–315. Springer, Heidelberg (2005)
Cirne, W., Berman, F.: A Model for Moldable Supercomputer Jobs. In: Proc. Internat. Parallel and Distributed Processing Symposium (IPDPS) (April 2001)
Sodan, A.C.: Loosely Coordinated Coscheduling in the Context of Other Dynamic Approaches for Job Scheduling–A Survey. In: Concurrency & Computation: Practice & Experience, 57 pages (accepted for publication)
Naik, V.K., Setia, S.K., Squillante, M.S.: Processor Allocation in Multiprogrammed Distributed-Memory Parallel Computer Systems. J. of Parallel and Distributed Computing 46(1), 28–47 (1997)
Frachtenberg, E., Feitelson, D., Petrini, F., Fernandez, J.: Flexible CoScheduling: Mitigating Load Imbalance and Improving Utilization of Heterogeneous Resources. In: Proc. Int. Parallel and Distributed Processing Symposium (IPDPS 2003), Nice, France (April 2003)
Gibbons, R.A.: Historical Application Profiler for Use by Parallel Schedulers. In: Feitelson, D.G., Rudolph, L. (eds.) IPPS-WS 1997 and JSSPP 1997. LNCS, vol. 1291. Springer, Heidelberg (1997)
Mu’alem, A., Feitelson, D.G.: Utilization, Predictability, Workloads and User Runtime Estimates in Scheduling the IBM SP2 with Backfilling. IEEE Transactions Parallel & Distributed Systems 12(6) (June 2001)
Perkovic, D., Keleher, P.J.: Randomization, Speculation, and Adaptation in Batch Schedulers. In: Proc. ACM/IEEE Supercomputing (SC), Dallas/TX (November 2000)
Chiang, S.-H., Vernon, M.K.: Characteristics of a Large Shared Memory Production Workload. In: Feitelson, D.G., Rudolph, L. (eds.) JSSPP 2001. LNCS, vol. 2221, pp. 159–187. Springer, Heidelberg (2001)
Smith, W., Taylor, V., Foster, I.: Using Run-Time Predictions to Estimate Queue Wait Times and Improve Scheduler Performance. In: Feitelson, D.G., Rudolph, L. (eds.) JSSPP 1999, IPPS-WS 1999, and SPDP-WS 1999. LNCS, vol. 1659, p. 202. Springer, Heidelberg (1999)
Arpaci-Dusseau, A.C., Culler, D.E., Mainwaring, A.M.: Scheduling with Implicit Information in Distributed Systems. In: Proc. SIGMETRICS 1998/PERFORMANCE 1998 Joint Conference on the Measurement and Modeling of Computer Systems, Madison/WI, USA (June 1998)
Crovella, M.E., LeBlanc, T.J.: Parallel Performance Prediction Using Lost Cycles Analysis. In: Proc. Supercomputing, SC (1994)
Keahey, K., Beckman, P., Ahrens, J.: Ligature: Component Architecture for High Performance Applications. The International Journal of High Performance Applications 14(4), 347–356 (winter 2000)
Vraalsen, F., Aydt, R.A., Mendes, C.L., Reed, D.A.: Performance Contracts: Predicting and Monitoring Grid Application Behavior. In: Proc. 2nd Internat. Workshop on Grid Computing (November 2001)
Marin, G., Mellor-Crummey, J.: Cross-Architecture Predictions for Scientific Applications Using Parameterized Models. In: Proc. Joint. Internat. Conf. on Measurement and Modeling of Computer Systems (SIGMETRICS), New York, NY, USA (June 2004)
Snavely, A., Carrington, L., Wolter, N.: Modeling Application Performance by Convolving Machine Signatures with Application Profiles. In: Proc. IEEE 3rd Annual Workshop on Workload Characterization (2001)
NIST/SEMATECH e-Handbook of Statistical Methods, http://www.itl.nist.gov/div898/handbook (retrieved October 2004)
Cohen, J., Cohen, P., West, S.G., Alken, L.S.: Applied Multiple Regression/Correlation Analysis for the Behavioural Sciences, 3rd edn. Lawrence Erlbaum Associates, Mahwah (2003)
Mendenhall, W., Beaver, R.J., Beaver, B.M.: Introduction to Probability and Statistics, 10th edn. Brooks/Cole Publishing Company, Pacific Grove (1999)
Bailey, D.H., Harris, T., Saphir, W.C., Van der Wijngaart, R.F., Woo, A.C., Yarrow, M.: The NAS Parallel Benchmarks 2.0. NAS Technical Report NAS-95-020, NASA Ames Research Center, Moffett Field, CA (1995)
Grama, A., Gupta, A., Karypis, G., Kumar, V.: Introduction to Parallel Computing, 2nd edn. Addison-Wesley, Reading (2003)
Yarrow, M., Van der Wijngaart, R.F.: Communication Improvement for the LU NAS Parallel Benchmark: A Model for Efficient Parallel Relaxation Schemes. NAS Technical Report NAS-97-032, NASA Ames Research Center, Moffett Field, CA (1997)
Barszcz, E., Fatoohi, R., Venkatakrishnan, V., Weeratunga, S.: Solution of Regular, Sparse Triangular Linear Systems on Vector and Distributed-Memory Multiprocessors. NAS Applied Research Branch Report RNR-94-007, NASA Ames Research Center, Moffet Field, CA (1993)
Maple 9.5–Advanced Mathematics Software for Engineers, Academics, Researchers, and Students, http://www.maplesoft.com/products/maple/index.aspx (retrieved December 2004)
OpenMaple–An API into Maple, http://www.adaptscience.com/products//maple/html/OpenMaple.html (retrieved December 2004)
HPL–A Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers, http://www.netlib.org/benchmark/hpl/ (retrieved June 2005)
Foster, I.: Designing and Building Parallel Programs. Addison-Wesley, Reading (1995)
Vadhiyar, S.S., Fagg, G.E., Dongarra, J.: Automatically Tuned Collective Communications. In: IEEE/ACM Supercomputing (November 2000)
Pješivac-Grbović, J., Angskun, T., Bosilca, G., Fagg, G.E., Gabriel, E., Dongarra, J.J.: Performance Analysis of MPI Collective Operations. In: PMEO-PDS (April 2005)
Todorowski, L., Ljubič, P., Džeroski, S.: Inducing Polynomial Equations for Regression. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) ECML 2004. LNCS (LNAI), vol. 3201, pp. 441–452. Springer, Heidelberg (2004)
Schmidt, E., Schulz, A., Kruse, L., von Cölln, G., Nebel, W.: Automatic Generation of Complexity Functions for High-Level Power Analysis. In: PATMOS (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lafreniere, B.J., Sodan, A.C. (2005). ScoPred–Scalable User-Directed Performance Prediction Using Complexity Modeling and Historical Data. In: Feitelson, D., Frachtenberg, E., Rudolph, L., Schwiegelshohn, U. (eds) Job Scheduling Strategies for Parallel Processing. JSSPP 2005. Lecture Notes in Computer Science, vol 3834. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11605300_3
Download citation
DOI: https://doi.org/10.1007/11605300_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-31024-2
Online ISBN: 978-3-540-31617-6
eBook Packages: Computer ScienceComputer Science (R0)