Profiling high performance dense linear algebra algorithms on multicore architectures for power and energy efficiency

Computer Science - Research and Development - Tập 27 - Trang 277-287 - 2011
Hatem Ltaief1, Piotr Luszczek2, Jack Dongarra2
1KAUST Supercomputing Laboratory, Thuwal, Saudi Arabia
2Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, USA

Tóm tắt

This paper presents the power profile of two high performance dense linear algebra libraries i.e., LAPACK and PLASMA. The former is based on block algorithms that use the fork-join paradigm to achieve parallel performance. The latter uses fine-grained task parallelism that recasts the computation to operate on submatrices called tiles. In this way tile algorithms are formed. We show results from the power profiling of the most common routines, which permits us to clearly identify the different phases of the computations. This allows us to isolate the bottlenecks in terms of energy efficiency. Our results show that PLASMA surpasses LAPACK not only in terms of performance but also in terms of energy efficiency.

Tài liệu tham khảo

Agullo E, Hadri B, Ltaief H, Dongarrra J (2009) Comparative study of one-sided factorizations with multiple software packages on multi-core hardware. In: SC ’09: proceedings of the conference on high performance computing networking, storage and analysis. ACM, New York, pp 1–12. http://doi.acm.org/10.1145/1654059.1654080 Anderson E, Bai Z, Bischof C, Blackford SL, Demmel JW, Dongarra JJ, Croz JD, Greenbaum A, Hammarling S, McKenney A, Sorensen DC (1999) LAPACK user’s guide, 3rd edn. Society for Industrial and Applied Mathematics, Philadelphia Anzt H, Rocker B, Heuveline V (2010) Energy efficiency of mixed precision iterative refinement methods using hybrid hardware platforms—an evaluation of different solver and hardware configurations. Comput Sci 25(3–4):141–148. doi:10.1007/s00450-010-0124-2 Bekas C, Curioni A (2010) A new energy aware performance metric. Comput Sci 25(3–4):187–195. doi:10.1007/s00450-010-0119-z Bischof CH, Lang B, Sun X (2000) Algorithm 807: the SBR toolbox—software for successive band reduction. ACM Trans Math Softw 26(4):602–616. http://doi.acm.org/10.1145/365723.365736 Buttari A, Dongarra J, Langou J, Langou J, Luszczek P, Kurzak J (2007) Mixed precision iterative refinement techniques for the solution of dense linear systems. Int J Hight Perform Comput Appl 21(4):457–466. doi:10.1177/1094342007084026 Buttari A, Langou J, Kurzak J, Dongarra J (2009) A class of parallel tiled linear algebra algorithms for multicore architectures. Parallel Comput 35(1):38–53 Chen G, Malkowski K, Kandemir MT, Raghavan P (2005) Reducing power with performance constraints for parallel sparse applications. In: IPDPS. IEEE Comput Soc, Los Alamitos. http://doi.ieeecomputersociety.org/10.1109/IPDPS.2005.378 Ding Y, Malkowski K, Raghavan P, Kandemir MT (2008) Towards energy efficient scaling of scientific codes. In: IPDPS. IEEE Press, New York, pp 1–8. doi:10.1109/IPDPS.2008.4536217 Freeh VW, Lowenthal DK (2005) Using multiple energy gears in MPI programs on a power-scalable cluster. In: Pingali K, Yelick KA, Grimshaw AS (eds) Proceedings of the ACM SIGPLAN symposium on principles and practice of parallel programming (10th PPOPP’2005), Chicago, IL, USA. ACM SIGPLAN Notices, vol 40, pp 164–173 Ge R, Feng X, Song S, Chang HC, Li D, Cameron KW (2010) Powerpack: Energy profiling and analysis of high-performance systems and applications. IEEE Trans Parallel Distrib Syst PDS-21(5):658–671 Golub GH, Van Loan CF (1996) Matrix computation, 3rd edn. John Hopkins studies in the mathematical sciences. Johns Hopkins University Press, Baltimore Kågström B, Kressner D, Quintana-Ortí E, Quintana-Ortí G (2008) Blocked algorithms for the reduction to Hessenberg-triangular form revisited. BIT Numer Math 48:563–584 Kappiah N, Freeh VW, Lowenthal DK (2005) Just in time dynamic voltage scaling: exploiting inter-node slack to save energy in MPI programs. In: SC. IEEE Comput Soc, Los Alamitos, p 33. http://doi.acm.org/10.1145/1105760.1105797 Kogge P, Bergman K, Borkar S, Campbell D, Carlson W, Dally W, Denneau M, Franzon P, Harrod W, Hill K, Hiller J, Karp S, Keckler S, Klein D, Lucas R, Richards M, Scarpelli A, Scott S, Snavely A, Sterling T, Williams RS, Yelick K (2008) Exascale computing study: technology challenges in achieving exascale systems. Tech Rep TR-2008-13, Department of Computer Science and Engineering. University of Notre Dame Ltaief H, Luszczek P, Dongarra J (2011, submitted) High performance bidiagonal reduction using tile algorithms on homogeneous multicore architectures. ACM Trans Math Softw Luszczek P, Ltaief H, Dongarra J (2011) Two-stage tridiagonal reduction for dense symmetric matrices using tile algorithms on multicore architectures. In: Proceedings of IPDPS 2011. ACM, Anchorage Multicore application modeling infrastructure (MuMI) project. http://www.mumi-tool.org Sutter H (2005) The free lunch is over: a fundamental turn toward concurrency in software. Dr Dobb’s Journal 30(3). http://www.ddj.com/184405990 Trefethen LN, Bau D (1997) Numerical linear algebra. SIAM, Philadelphia. http://www.siam.org/books/OT50/Index.htm University of Tennessee Knoxville (2010) PLASMA users’ guide, parallel linear algebra software for multicore architectures, version 2.3. Available electronically at http://icl.cs.utk.edu/projectsfiles/plasma/pdf/users_guide.pdf