Abstract
In this paper, we enhance the SuperMatrix runtime scheduler from the libflame library for dense linear algebra in two different directions that address high performance and energy. First, we extend the runtime scheduler by accommodating hybrid CPU-GPU executions and managing task priorities for dense linear algebra operations, with remarkable performance improvements. Second, we introduce techniques to reduce energy consumption during idle times inherent to parallel executions, attaining fair energy savings. While our techniques are applicable to the complete libflame library, in this paper we use the LU factorization with partial pivoting to illustrate the actual impact on performance and energy consumption of the adopted techniques.
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
References
Alonso, P., Badia, R. M., Labarta, J., Barreda, M., Dolz, M. F., Mayo, R., Quintana-Ortí, E. S., Reyes, R.: Tools for power-energy modelling and analysis of parallel scientific applications. In: 41st International Conference on Parallel Processing - ICPP, pp. 420–429 (2012)
Alonso, P., Dolz, M. F., Igual, F. D., Mayo, R., Quintana-Ortí, E. S.: Saving energy in the LU factorization with partial pivoting on multi-core processors. In: Proceedings of the 20th Euromicro International Conference on Parallel, Distributed and Network-Based Processing - PDP (2012)
Alonso, P., Dolz, M. F., Igual, F. D., Mayo, R., Quintana-Ortí, E. S.: Reducing energy consumption of dense linear algebra operations on hybrid CPU-GPU platforms. In: Proceedings of the 10th IEEE International Symposium on Parallel and Distributed Processing with Applications- ISPA 2012, pp. 56–62 (2012)
Badia, R.M., Herrero, J.R., Labarta, J., Pérez, J.M., Quintana-Ortí, E.S., Quintana-Ortí, G.: Parallelizing dense and banded linear algebra libraries using SMPSs. Concurr. Comput. Pract. Exp. 21(18), 2438–2456 (2009)
Barrachina, S., Castillo, M., Igual, F.D., Mayo, R., Quintana-Ortí, E.S., Quintana-Ortí, G.: Exploiting the capabilities of modern GPUs for dense matrix computations. Concurr. Comput. Pract. Exp. 21(18), 2457–2477 (2009)
Bientinesi, P., Gunnels, J. A., Myers, M. E., Quintana-Ortí, E. S., van de Geijn, R. A.: The science of deriving dense linear algebra algorithms. ACM Trans. Math. Softw. 31(1), 1–26 (2005)
Borkar, S., Chien, A.A.: The future of microprocessors. Commun. ACM 54(5), 67–77 (2011)
Cilk project. http://supertech.csail.mit.edu/cilk/
Elnozahy, E.N., Kistler, M., Rajamony, R.: Energy-efficient server clusters. In: Falsati, B., Vijaykumar, T.N. (eds.) PACS 2002. LNCS, vol. 2325, pp. 179--197. Springer, Heidelberg (2003)
Esmaeilzadeh, H., Blem, E., St. Amant, R., Sankaralingam, K., Burger, D.: Dark silicon and the end of multicore scaling. In: Proceedings of the 38th Annual International Symposium Computer architecture, ISCA ’11, pp. 365–376 (2011)
Igual, F. D., Quintana-Ortí, G., van de Geijn, R.: Scheduling algorithms-by-blocks on small clusters. Concurr. Comput. Pract. Experience (2012)
OmpSs project home page. http://pm.bsc.es/ompss
Paraver project. http://www.cepba.upc.es/paraver
PLASMA project home page. http://icl.cs.utk.edu/plasma
Quintana-Ortí, G., Quintana-Ortí, E. S., van de Geijn, R. A., Van Zee, F. G., Chan, E.: Programming matrix algorithms-by-blocks for thread-level parallelism. ACM Trans. Math. Softw. 36(3), 14:1–14:26 (2009)
Quintana-Ortí, G., Igual, F. D., Quintana-Ortí, E. S., van de Geijn, R.: Solving dense linear algebra problems on platforms with multiple hardware accelerators. In: 14th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - PPoPP, pp. 121–129 (2009)
StarPU project. http://runtime.bordeaux.inria.fr/StarPU/
Van Zee, F.G.: libflame. the complete reference, 2008. In preparation. http://www.cs.utexas.edu/users/flame
Acknowledgments
This research was supported by project CICYT TIN2011-23283, MICINN-TIN 2008/508, TIN 2012/32180 and FEDER.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Alonso, P., Dolz, .F., Igual, F.D., Quintana-Ortí, E.S., Mayo, R. (2013). Runtime Scheduling of the LU Factorization: Performance and Energy. In: Pierson, JM., Da Costa, G., Dittmann, L. (eds) Energy Efficiency in Large Scale Distributed Systems. EE-LSDS 2013. Lecture Notes in Computer Science(), vol 8046. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40517-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-40517-4_14
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40516-7
Online ISBN: 978-3-642-40517-4
eBook Packages: Computer ScienceComputer Science (R0)