Skip to main content Accessibility help
×
Home
Hostname: page-component-559fc8cf4f-sbc4w Total loading time: 0.28 Render date: 2021-02-28T22:04:31.021Z Has data issue: true Feature Flags: { "shouldUseShareProductTool": true, "shouldUseHypothesis": true, "isUnsiloEnabled": true, "metricsAbstractViews": false, "figures": false, "newCiteModal": false, "newCitedByModal": true }

DASHMM: Dynamic Adaptive System for Hierarchical Multipole Methods

Published online by Cambridge University Press:  05 October 2016

J. DeBuhr
Affiliation:
Center for Research in Extreme Scale Technologies, School of Informatics and Computing, Indiana University, Bloomington, IN, 47404, USA
B. Zhang
Affiliation:
Center for Research in Extreme Scale Technologies, School of Informatics and Computing, Indiana University, Bloomington, IN, 47404, USA
A. Tsueda
Affiliation:
College of Arts and Sciences, Loyola University Chicago, Chicago, IL, 60660, USA
V. Tilstra-Smith
Affiliation:
Department of Physics and Mathematics, Central College, Pella, IA, 50219, USA
T. Sterling
Affiliation:
Center for Research in Extreme Scale Technologies, School of Informatics and Computing, Indiana University, Bloomington, IN, 47404, USA
Corresponding
E-mail address:
Get access

Abstract

We present DASHMM, a general library implementing multipole methods (including both Barnes-Hut and the Fast Multipole Method). DASHMM relies on dynamic adaptive runtime techniques provided by the HPX-5 system to parallelize the resulting multipole moment computation. The result is a library that is easy-to-use, extensible, scalable, efficient, and portable. We present both the abstractions defined by DASHMM as well as the specific features of HPX-5 that allow the library to execute scalably and efficiently.

Type
Computational Software
Copyright
Copyright © Global-Science Press 2016 

Access options

Get access to the full version of this content by using one of the access options below.

References

[2] Agullo, E., Bramas, B., Coulaud, O., Darve, E., Messner, M., and Takahashi, T.. Task-based FMM for multicore architectures. SIAM J. Sci. Comput., 36:C66–C93, 2014.CrossRefGoogle Scholar
[3] Aluru, S., Gustafson, J., Prabhu, G. M., and Sevilgen, F. E.. Distribution-independent hierarchical algorithms for the N-body problem. J. SuperComput., 12:303323, 1998.CrossRefGoogle Scholar
[4] Amer, A., Maruyama, N., Pericás, M., Taura, K., Yokota, R., and Matsuoka, S.. Fork-join and data-driven exeuction models on multi-core architectures: Case study of the FMM. Lect. Notes. Comput. Sc., 7905:255266, 2013.CrossRefGoogle Scholar
[5] Barnes, J. and Hut, P.. A hierarchical O(N log N) force-calculation algorithm. Nature, 324:446449, December 1986.CrossRefGoogle Scholar
[6] Bosilca, G., Bouteiller, A., Danalis, A., Herault, T., Lemarinier, P., and Dongarra, J.. DAGuE: A generic distributed DAG engine for high performance computing. Parallel Comput., 38:3751, 2012.CrossRefGoogle Scholar
[7] Chew, W. C., Jin, J. M., Michielssen, E., and Song, J. M.. Fast and Efficient Algorithm in Computational Electromagnetics. Artech House, 2001.Google Scholar
[8] Cruz, F. A., Knepley, M. G., and Barba, L. A.. PetFMM–A dynamically load-balancing parallel fast multipole library. Int. J. Numer. Meth. Eng., 85:403428, 2011.CrossRefGoogle Scholar
[9] Greengard, L. and Gropp, W.. A parallel version of the fast multipole method. Comput. Math. Appl., 20:6371, 1990.CrossRefGoogle Scholar
[10] Greengard, L., Kropinski, MC, and Mayo, A.. Integral Equation Methods for Stokes Flow and Isotropic Elasticity in the Plane. J. Comput. Phys., 125:403414, 1996.CrossRefGoogle Scholar
[11] Greengard, L. and Rokhlin, V.. A fast algorithm for particle simulations. J. Comput. Phys., 73:325348, 1987.CrossRefGoogle Scholar
[12] Gumerov, N. A. and Duraiswami, R.. Fast multipole methods on graphics processors. J. Comput. Phys., 227:82908313, 2008.CrossRefGoogle Scholar
[13] Board, J. A. Jr., Causey, J. W., and Leathrum, J. F. Jr. Accelerated molecular dynamics simulation with the parallel fast multipole algorithm. Chem. Phys. Lett., 198:8994, 1992.CrossRefGoogle Scholar
[14] Leathrum, J. F. Jr. and Board, J. A. Jr. Mapping the adaptive fast multipole algorithm onto MIMD systems. In Unstructured Scientific Computation on Scalable Multiprocessors, pages 161177, Nags Head, NC, USA, 1992.Google Scholar
[15] Kurzak, J. and Pettitt, B.M.. Communications overlapping in fast multipole particle dynamics methods. J. Comput. Phys., 203:731743, 2005.CrossRefGoogle Scholar
[16] Kurzak, J. and Pettitt, B. M.. Massively parallel implementation of a fast multipole method for distributed memory machines. J. Parallel Distr. Com., 65:870881, 2005.CrossRefGoogle Scholar
[17] Lashuk, I., Chandramowlishwaran, A., Langston, H., Nguyen, T.-A., Sampath, R., Shringarpure, A., Vuduc, R., Ying, L., Zorin, D., and Biros, G.. A massively parallel adaptive fast-multipole method on heterogeneous architectures. In Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis, 2009.Google Scholar
[18] Ltaief, H. and Yokota, R.. Data-driven execution of fast multipole methods. CoRR, abs/1203.0889, 2012.Google Scholar
[19] Lu, B., Cheng, X., Huang, J., and McCammon, J.. Order N algorithm for computation of electrostatic Interactions in biomolecular systems. Proceedings of the National Academy of Sciences, 103:1931419319, 2006.CrossRefGoogle ScholarPubMed
[20] Rahimian, A., Lashuk, I., Veerapaneni, S. K., Chandramowlishwaran, A., Malhotra, D., Moon, L., Sampath, R., Shringarpure, A., Vetter, J., Vuduc, R., Zorin, D., and Biros, G.. Petascale direct numerical simulation of blood flow on 200K cores and heterogeneous architectures. In Proceedings of the 2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, 2010.Google Scholar
[21] Singh, J., Holt, C., Hennessy, J., and Gupta, A.. A parallel adaptive fast multipole method. In SC 93’: Proceedings of the 1993 ACM/IEEE Conference on Supercomputing, 1993.Google Scholar
[22] Singh, J., Holt, C., Totsuka, T., Gupta, A., and Hennessy, J.. Load balancing and data locality in adaptive hierarchical n-body methods: Barnes-Hut, fast multipole, and radiosity. J. Parallel Distr. Com., 27:118141, 1995.CrossRefGoogle Scholar
[23] Springel, V., Wang, J., Vogelsberger, M., Ludlow, A., Jenkins, A., Helmi, A., Navarro, J. F., Frenk, C. S., and White, S. D. M.. The Aquarius Project: the subhaloes of galactic haloes. MNRAS, 391:16851711, December 2008.CrossRefGoogle Scholar
[24] Teng, S.. Provably good partitioning and load balancing algorithms for parallel adaptive n-body simulation. SIAM J. Sci. Comput., 19:635656, 1998.CrossRefGoogle Scholar
[25] Wang, H., Lei, T., Li, J., Huang, J., and Yao, Z.. A parallel fast multipole accelerated integral equation scheme for 3D Stokes equations. Int. J. Numer. Meth. Eng., 70:812839, 2007.CrossRefGoogle Scholar
[26] Warren, M. and Salmon, J.. Astrophysical n-body simulation using hierarchical tree data structures. In SC 92’: Proceedings of the 1992 ACM/IEEE Conference on Supercomputing, 1992.Google Scholar
[27] Warren, M. and Salmon, J.. A parallel hashed oct-tree n-body algorithm. In SC 93’: Proceedings of the 1993 ACM/IEEE Conference on Supercomputing, 1993.Google Scholar
[28] Wu, W., Bosilca, G., Bouteiller, A., Faverge, M., and Dongarra, J.. Hierarchical DAG scheduling for hybrid distributed systems. In IPDPS, Hyderabad, India, 2015.Google Scholar
[29] Ying, L., Biros, G., Zorin, D., and Langston, H.. A new parallel kernel-independent fast multipole method. In SC ’03: Proceedings of the 2003 ACM/IEEE Conference on Supercomputing, 2003.Google Scholar
[30] Yokota, R., Bardhan, J. P., Knepley, M. G., Barba, L. A., and Hamada, T.. Biomolecular electrostatics using a fastmultipole BEMon up to 512 GPUs and a billion unknowns. Comput. Phys. Commun., 182:12721283, 2011.CrossRefGoogle Scholar
[31] Yuan, Y. and Banerjee, P.. A parallel implementation of a fast multipole based 3D capacitance extraction program on distributed memory multicomputers. J. Parallel Distr. Com., 61:17511774, 2001.CrossRefGoogle Scholar
[32] Zhang, B.. Asynchronous task scheduling of the fast multipole method using various runtime systems. In Proceedings of the Forth Workshop on Data-Flow Execution Models for Extreme Scale Computing, Edmonton, Canada, 2014.Google Scholar
[33] Zhang, B., Huang, J., Pitsianis, N. P., and Sun, X.. Dynamic prioritization for parallel traversal of irregularly structured spatio-temporal graphs. In Proceedings of 3rd USENIX Workshop on Hot Topics in Parallelism, 2011.Google Scholar
[34] Zhao, F. and Johnsson, S. L.. The parallel multipole method on the connection machine. SIAM J. Sci. Stat. Comp., 12:14201437, 1991.CrossRefGoogle Scholar

Full text views

Full text views reflects PDF downloads, PDFs sent to Google Drive, Dropbox and Kindle and HTML full text views.

Total number of HTML views: 0
Total number of PDF views: 73 *
View data table for this chart

* Views captured on Cambridge Core between 05th October 2016 - 28th February 2021. This data will be updated every 24 hours.

Send article to Kindle

To send this article to your Kindle, first ensure no-reply@cambridge.org is added to your Approved Personal Document E-mail List under your Personal Document Settings on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part of your Kindle email address below. Find out more about sending to your Kindle. Find out more about sending to your Kindle.

Note you can select to send to either the @free.kindle.com or @kindle.com variations. ‘@free.kindle.com’ emails are free but can only be sent to your device when it is connected to wi-fi. ‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.

Find out more about the Kindle Personal Document Service.

DASHMM: Dynamic Adaptive System for Hierarchical Multipole Methods
Available formats
×

Send article to Dropbox

To send this article to your Dropbox account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your <service> account. Find out more about sending content to Dropbox.

DASHMM: Dynamic Adaptive System for Hierarchical Multipole Methods
Available formats
×

Send article to Google Drive

To send this article to your Google Drive account, please select one or more formats and confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your <service> account. Find out more about sending content to Google Drive.

DASHMM: Dynamic Adaptive System for Hierarchical Multipole Methods
Available formats
×
×

Reply to: Submit a response


Your details


Conflicting interests

Do you have any conflicting interests? *