{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T07:10:32Z","timestamp":1725865832546},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319455495"},{"type":"electronic","value":"9783319455501"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-45550-1_12","type":"book-chapter","created":{"date-parts":[[2016,9,20]],"date-time":"2016-09-20T06:49:52Z","timestamp":1474354192000},"page":"156-170","source":"Crossref","is-referenced-by-count":1,"title":["Scaling FMM with Data-Driven OpenMP Tasks on Multicore Architectures"],"prefix":"10.1007","author":[{"given":"Abdelhalim","family":"Amer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Satoshi","family":"Matsuoka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miquel","family":"Peric\u00e0s","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoya","family":"Maruyama","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":"Pavan","family":"Balaji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,21]]},"reference":[{"unstructured":"Amer, A.: Parallelism, data movement, and synchronization in threading models on massively parallel systems. Technical report, Tokyo Institute of Technology, Department of Mathematical and Computing Sciences (2015)","key":"12_CR1"},{"key":"12_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1007\/978-3-642-38750-0_19","volume-title":"Supercomputing","author":"A Amer","year":"2013","unstructured":"Amer, A., Maruyama, N., Peric\u00e0s, M., Taura, K., Yokota, R., Matsuoka, S.: Fork-join and data-driven execution models on multi-core architectures: case study of the FMM. In: Kunkel, J.M., Ludwig, T., Meuer, H.W. (eds.) ISC 2013. LNCS, vol. 7905, pp. 255\u2013266. Springer, Heidelberg (2013)"},{"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 (2010)","key":"12_CR3","DOI":"10.1109\/IPDPS.2010.5470415"},{"key":"12_CR4","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/5750.001.0001","volume-title":"The Rapid Evaluation of Potential Fields in Particle Systems","author":"L Greengard","year":"1988","unstructured":"Greengard, L.: The Rapid Evaluation of Potential Fields in Particle Systems, vol. 52. MIT Press, Cambridge (1988)"},{"doi-asserted-by":"crossref","unstructured":"Ltaief, H., Yokota, R.: Data-driven execution of fast multipole methods (2012)","key":"12_CR5","DOI":"10.1002\/cpe.3132"},{"key":"12_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1007\/978-3-662-44471-9_10","volume-title":"Concurrent Objects and Beyond","author":"J Nakashima","year":"2014","unstructured":"Nakashima, J., Taura, K.: Massivethreads: a thread library for high productivity languages. In: Agha, G., Igarashi, A., Kobayashi, N., Masuhara, H., Matsuoka, S., Shibayama, E., Taura, K. (eds.) Concurrent Objects and Beyond. LNCS, vol. 8665, pp. 222\u2013238. Springer, Heidelberg (2014)"},{"doi-asserted-by":"crossref","unstructured":"Olivier, S.L., De Supinski, B.R., Schulz, M., Prins, J.F.: Characterizing and mitigating work time inflation in task parallel programs. In: Proceedings of the 2012 ACM\/IEEE Conference on Supercomputing, pp. 1\u201312. IEEE (2012)","key":"12_CR7","DOI":"10.1109\/SC.2012.27"},{"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 (2012)","key":"12_CR8"},{"key":"12_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1007\/978-3-319-10214-6_4","volume-title":"High Performance Computing Systems. Performance Modeling, Benchmarking and Simulation","author":"M Peric\u00e0s","year":"2014","unstructured":"Peric\u00e0s, M., Amer, A., Taura, K., Matsuoka, S.: Analysis of data reuse in task-parallel runtimes. In: Jarvis, S.A., Wright, S.A., Hammond, S.D. (eds.) PMBS 2013. LNCS, vol. 8551, pp. 73\u201387. Springer, Heidelberg (2014)"},{"doi-asserted-by":"crossref","unstructured":"Tasirlar, S., Sarkar, V.: Data-driven tasks and their implementation. In: 2011 International Conference on Parallel Processing (ICPP), pp. 652\u2013661 (2011)","key":"12_CR10","DOI":"10.1109\/ICPP.2011.87"},{"issue":"3","key":"12_CR11","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1016\/S0022-0000(75)80008-0","volume":"10","author":"JD Ullman","year":"1975","unstructured":"Ullman, J.D.: NP-complete scheduling problems. J. Comput. Syst. Sci. 10(3), 384\u2013393 (1975)","journal-title":"J. Comput. Syst. Sci."},{"key":"12_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1007\/978-3-642-13374-9_12","volume-title":"Languages and Compilers for Parallel Computing","author":"Y Yan","year":"2010","unstructured":"Yan, Y., Zhao, J., Guo, Y., Sarkar, V.: Hierarchical place trees: a portable abstraction for task parallelism and data movement. In: Gao, G.R., Pollock, L.L., Cavazos, J., Li, X. (eds.) LCPC 2009. LNCS, vol. 5898, pp. 172\u2013187. Springer, Heidelberg (2010)"},{"doi-asserted-by":"crossref","unstructured":"Ying, L., Biros, G., Zorin, D., Langston, H.: A new parallel kernel-independent fast multipole method. In: ACM\/IEEE Conference on Supercomputing, p. 14 (2003)","key":"12_CR13","DOI":"10.1145\/1048935.1050165"}],"container-title":["Lecture Notes in Computer Science","OpenMP: Memory, Devices, and Tasks"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-45550-1_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,9,26]],"date-time":"2020-09-26T00:31:24Z","timestamp":1601080284000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-45550-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319455495","9783319455501"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-45550-1_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}