Abstract
Performance anomalies when running Gaussian frequency calculations in parallel on SGI Altix computers with CC-NUMA memory architecture are analyzed using performance tools that access hardware counters. The bottleneck is the frequent and nearly simultaneous data-loads of all threads involved in the calculation of data allocated in the node where the master thread runs. Code changes that ensure these data-loads are localized improve performance by a factor close to two. The improvements carry over to other molecular models and other types of calculations. An expansion or an alternative of FirstPrivate OpenMP’s clause can facilitate the code transformations.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Frisch, M.J., Trucks, G.W., Schlegel, H.B., Scuseria, G.E., Robb, M.A., Cheeseman, J.R., Montgomery Jr., J.A., Vreven, T., Scalmani, G., Mennucci, B., Barone, V., Petersson, G.A., Caricato, M., Nakatsuji, H., Hada, M., Ehara, M., Toyota, K., Fukuda, R., Hasegawa, J., Ishida, M., Nakajima, T., Honda, Y., Kitao, O., Nakai, H., Li, X., Hratchian, H.P., Peralta, J.E., Izmaylov, A.F., Kudin, K.N., Heyd, J.J., Brothers, E., Staroverov, V.N., Zheng, G., Kobayashi, R., Normand, J., Sonnenberg, J.L., Ogliaro, F., Bearpark, M., Parandekar, P.V., Ferguson, G.A., Mayhall, N.J., Iyengar, S.S., Tomasi, J., Cossi, M., Rega, N., Burant, J.C., Millam, J.M., Klene, M., Knox, J.E., Cross, J.B., Bakken, V., Adamo, C., Jaramillo, J., Gomperts, R., Stratmann, R.E., Yazyev, O., Austin, A.J., Cammi, R., Pomelli, C., Ochterski, J.W., Ayala, P.Y., Morokuma, K., Voth, G.A., Salvador, P., Dannenberg, J.J., Zakrzewski, V.G., Dapprich, S., Daniels, A.D., Strain, M.C., Farkas, O., Malick, D.K., Rabuck, A.D., Raghavachari, K., Foresman, J.B., Ortiz, J.V., Cui, Q., Baboul, A.G., Clifford, S., Cioslowski, J., Stefanov, B.B., Liu, G., Liashenko, A., Piskorz, P., Komaromi, I., Martin, R.L., Fox, D.J., Keith, T., Al-Laham, M.A., Peng, C.Y., Nanayakkara, A., Challacombe, M., Chen, W., Wong, M.W., Pople, J.A.: Gaussian Development Version, Revision G.03+. Gaussian, Inc., Wallingford
OpenMP Application Program Interface, Version 3.0 (May 2008), http://www.openmp.org/mp-documents/spec30.pdf
Pople, J.A., Raghavachari, K., Schlegel, H.B., et al.: Int. J. Quantum Chem. Quant. Chem. Symp. S13, 225 (1979)
Frisch, M.J., Head-Gordon, M., Pople, J.A.: Chem. Phys. 141(2-3), 189 (1990)
Osamura, Y., Yamaguchi, Y., Saxe, P., et al.: J. Mol. Struct (Theochem.) 12, 183 (1983)
Pulay, P.: J. Chem. Phys. 78(8), 5043 (1983)
Boys, S.F.: Proc. Roy. Soc. Ser. A 542 (1950)
Roothaan, C.C.J.: Rev. Mod. Phys. 23(2), 69 (1951)
Roothaan, C.C.J.: Rev. Mod. Phys. 32(179) (1960)
Stephens, P.J., Devlin, F.J., Ashvar, C.S., et al.: Faraday Discuss 99, 103 (1994)
Greengard, L., Rokhlin, V.: J. Comp. Phys. 73(2), 325 (1987)
Strain, M.C., Scuseria, G.E., Frisch, M.J.: Science 271(5245), 51 (1996)
Burant, J.C., Strain, M.C., Scuseria, G.E., et al.: Chem. Phys. Lett. 258, 45 (1996)
Stratmann, R.E., Burant, J.C., Scuseria, G.E., et al.: J. Chem. Phys. 106(24), 10175 (1997)
Izmaylov, A.F., Scuseria, G., Frisch, M.J.: J. Chem. Phys. 125(104103), 1 (2006)
Pulay, P.: Ab Initio Methods in Quantum chemistry - II, p. 241 (1987)
Devlin, F.J., Stephens, P.J., Cheeseman, J.R., et al.: J. Phys. Chem. A 101(35), 6322 (1997)
Devlin, F.J., Stephens, P.J., Cheeseman, J.R., et al.: J. Phys. Chem. A 101(51), 9912 (1997)
Lenoski, D.E., Weber, W.-D.: Scalable Shared-Memory Mulitprocessing. Morgan Kaufmann Publishers, San Francisco (1995)
SGI Altix 450 servers, http://www.sgi.com/products/servers/altix/450/
SGI Histx performance analysis tools, http://www.sgi.com/products/software/linux/histx.html
Intel® Itanium® 2 Processor Reference Manual for Software Development and Optimization, http://download.intel.com/design/Itanium2/manuals/25111003.pdf
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gomperts, R., Frisch, M., Panziera, JP. (2009). Scalability of Gaussian 03 on SGI Altix: The Importance of Data Locality on CC-NUMA Architecture. In: MĂĽller, M.S., de Supinski, B.R., Chapman, B.M. (eds) Evolving OpenMP in an Age of Extreme Parallelism. IWOMP 2009. Lecture Notes in Computer Science, vol 5568. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02303-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-02303-3_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02284-5
Online ISBN: 978-3-642-02303-3
eBook Packages: Computer ScienceComputer Science (R0)