{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T09:14:48Z","timestamp":1743066888438,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":28,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642387494"},{"type":"electronic","value":"9783642387500"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-38750-0_19","type":"book-chapter","created":{"date-parts":[[2013,6,10]],"date-time":"2013-06-10T01:26:27Z","timestamp":1370827587000},"page":"255-266","source":"Crossref","is-referenced-by-count":15,"title":["Fork-Join and Data-Driven Execution Models on Multi-core Architectures: Case Study of the FMM"],"prefix":"10.1007","author":[{"given":"Abdelhalim","family":"Amer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoya","family":"Maruyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miquel","family":"Peric\u00e0s","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenjiro","family":"Taura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rio","family":"Yokota","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Matsuoka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"1","key":"19_CR1","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1006\/jcph.2002.7026","volume":"179","author":"W. Dehnen","year":"2002","unstructured":"Dehnen, W.: A hierarchical o(n) force calculation algorithm. Journal of Computational Physics\u00a0179(1), 27\u201342 (2002)","journal-title":"Journal of Computational Physics"},{"key":"19_CR2","doi-asserted-by":"publisher","first-page":"4233","DOI":"10.1016\/j.cma.2008.04.024","volume":"197","author":"S. Chaillat","year":"2008","unstructured":"Chaillat, S., Bonnet, M., Semblat, J.F.: A multi-level fast multipole bem for 3-d elastodynamics in the frequency domain. Computer Methods in Applied Mechanics and Engineering\u00a0197, 4233\u20134249 (2008)","journal-title":"Computer Methods in Applied Mechanics and Engineering"},{"key":"19_CR3","unstructured":"Yokota, R., Narumi, T., Barba, L.A., Yasuoka, K.: Petascale turbulence simulation using a highly parallel fast multipole method (2011)"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Chandramowlishwaran, A., Williams, S., Oliker, L., Lashuk, I., Biros, G., Vuduc, R.: Optimizing and tuning the fast multipole method for state-of-the-art multicore architectures. In: 2010 IEEE International Symposium on Parallel Distributed Processing (IPDPS), pp. 1\u201312 (April 2010)","DOI":"10.1109\/IPDPS.2010.5470415"},{"key":"19_CR5","first-page":"1","volume-title":"Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010","author":"A. Chandramowlishwaran","year":"2010","unstructured":"Chandramowlishwaran, A., Madduri, K., Vuduc, R.: Diagnosis, tuning, and redesign for multicore performance: A case study of the fast multipole method. In: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010, pp. 1\u201312. IEEE Computer Society, Washington, DC (2010)"},{"key":"19_CR6","unstructured":"Augonnet, C., Thibault, S., Namyst, R.: StarPU: a Runtime System for Scheduling Tasks over Accelerator-Based Multicore Machines. Rapport de Recherche RR-7240, INRIA (March 2010)"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Duran, A., Ayguade, E., Badia, R.M., Labarta, J., Martinell, L., Martorell, X., Planas, J.: Ompss: a proposal for programming heterogeneous multi-core architectures. Parallel Processing Letters, 173\u2013193 (2011)","DOI":"10.1142\/S0129626411000151"},{"key":"19_CR8","unstructured":"YarKhan, A., Kurzak, J., Dongarra, J.: Quark users\u2019 guide: Queueing and runtime for kernels. Technical report, University of Tennessee Innovative Computing Laboratory (April 2011)"},{"key":"19_CR9","unstructured":"http:\/\/code.google.com\/p\/massivethreads\/"},{"issue":"6096","key":"19_CR10","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1038\/324446a0","volume":"324","author":"J. Barnes","year":"1986","unstructured":"Barnes, J., Hut, P.: A hierarchical O(N log N) force-calculation algorithm. Nature\u00a0324(6096), 446\u2013449 (1986)","journal-title":"Nature"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Greengard, L.F.: The rapid evaluation of potential fields in particle systems. PhD thesis, New Haven, CT, USA, AAI8727216 (1987)","DOI":"10.7551\/mitpress\/5750.001.0001"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Ying, G.L., Biros, Zorin, D., Langston, H.: A new parallel kernel-independent fast multipole method. In: Supercomputing, 2003 ACM\/IEEE Conference, p. 14 (November 2003)","DOI":"10.1145\/1048935.1050165"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Ying, L., Biros, G., Zorin, D.: A kernel-independent adaptive fast multipole algorithm in two and three dimensions (2003)","DOI":"10.1016\/j.jcp.2003.11.021"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Greengard, L.: The Rapid Evaluation of Potential Fields in Particle Systems, vol.\u00a052. MIT Press (1988)","DOI":"10.7551\/mitpress\/5750.001.0001"},{"key":"19_CR15","unstructured":"McCalpin, J.D.: Memory bandwidth and machine balance in current high performance computers. IEEE Computer Society Technical Committee on Computer Architecture TCCA Newsletter, 19\u201325 (1995)"},{"key":"19_CR16","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-540-68564-7_9","volume-title":"Tools for High Performance Computing","author":"A. Kn\u00fcpfer","year":"2008","unstructured":"Kn\u00fcpfer, A., Brunst, H., Doleschal, J., Jurenz, M., Lieber, M., Mickler, H., M\u00fcller, M.S., Nagel, W.E.: The Vampir Performance Analysis Tool-Set. In: Resch, M., Keller, R., Himmler, V., Krammer, B., Schulz, A. (eds.) Tools for High Performance Computing, pp. 139\u2013155. Springer, Heidelberg (2008)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Brunst, H., Kn\u00fcpfer, A.: Vampir. In: Encyclopedia of Parallel Computing. Springer (2011)","DOI":"10.1007\/978-0-387-09766-4_60"},{"key":"19_CR18","unstructured":"http:\/\/icl.cs.utk.edu\/PAPI\/"},{"key":"19_CR19","unstructured":"http:\/\/software.intel.com\/en-us\/intel-vtune-amplifier-xe"},{"key":"19_CR20","unstructured":"Drongowski, P.J.: Basic performance measurements for amd athlontm 64, amd opterontm and amd phenomtm processors (September 25, 2008)"},{"key":"19_CR21","unstructured":"Intel xeon processor e5-2600 product family uncore performance monitoring guide (March 2012)"},{"key":"19_CR22","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S. Williams","year":"2009","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM\u00a052, 65\u201376 (2009)","journal-title":"Commun. ACM"},{"key":"19_CR23","unstructured":"Bergstrom, L.: Measuring numa effects with the stream benchmark (2011)"},{"key":"19_CR24","unstructured":"Agullo, E., Bramas, B., Coulaud, O., Darve, E., Messner, M., Takahashi, T.: Pipelining the fast multipole method over a runtime system (2012)"},{"key":"19_CR25","unstructured":"Pericas, M., Amer, A., Fukuda, K., Maruyama, N., Yokota, R., Matsuoka, S.: Towards a dataflow fmm using the ompss programming model. In: 136th IPSJ Conference on High Performance Computing"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Taura, K., Yokota, R., Maruyama, N.: A task parallelism meets fast multipole methods. In: Proceedings of SCALA 2012 (November 2012)","DOI":"10.1109\/SC.Companion.2012.86"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Datta, K., Kamil, S., Williams, S., Oliker, L., Shalf, J., Yelick, K.: Optimization and performance modeling of stencil computations on modern microprocessors (2009)","DOI":"10.1137\/070693199"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Williams, S., Oliker, L., Vuduc, R., Shalf, J., Yelick, K., Demmel, J.: Optimization of sparse matrix-vector multiplication on emerging multicore platforms. In: Proceedings of the 2007 ACM\/IEEE Conference on Supercomputing, SC 2007, 38:1\u201338:12. ACM, New York (2007)","DOI":"10.1145\/1362622.1362674"}],"container-title":["Lecture Notes in Computer Science","Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-38750-0_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T09:14:10Z","timestamp":1639732450000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-642-38750-0_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642387494","9783642387500"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-38750-0_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}