{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T03:45:22Z","timestamp":1778903122771,"version":"3.51.4"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319499550","type":"print"},{"value":"9783319499567","type":"electronic"}],"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\/978-3-319-49956-7_27","type":"book-chapter","created":{"date-parts":[[2016,11,18]],"date-time":"2016-11-18T04:01:20Z","timestamp":1479441680000},"page":"342-353","source":"Crossref","is-referenced-by-count":13,"title":["The Co-design of Astrophysical Code for Massively Parallel Supercomputers"],"prefix":"10.1007","author":[{"given":"Boris","family":"Glinsky","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Igor","family":"Kulikov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Igor","family":"Chernykh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dmitry","family":"Weins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexey","family":"Snytnikov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladislav","family":"Nenashev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrey","family":"Andreev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vitaly","family":"Egunov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Egor","family":"Kharkov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,11,19]]},"reference":[{"issue":"7","key":"27_CR1","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/2699414","volume":"58","author":"DA Reed","year":"2015","unstructured":"Reed, D.A., Dongarra, J.: Exascale computing and big data. Comm. ACM 58(7), 56\u201368 (2015)","journal-title":"Comm. ACM"},{"issue":"1","key":"27_CR2","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/1094342010391989","volume":"25","author":"JJ Dongarra","year":"2011","unstructured":"Dongarra, J.J., et al.: The international exascale software project roadmap. Int. J. High Perf. Comp. App. 25(1), 3\u201360 (2011)","journal-title":"Int. J. High Perf. Comp. App."},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Keyes, D.E.: Exaflop\/s: the why and the how. C.R. Mechanique 339, 70\u201377 (2011)","DOI":"10.1016\/j.crme.2010.11.002"},{"key":"27_CR4","doi-asserted-by":"crossref","unstructured":"Hsu, C-H., Kremer, U.: The design, implementation, and evaluation of a compiler algorithm for CPU energy reduction. In: Programming Languages, Design, and Implementation (2003)","DOI":"10.1145\/780822.781137"},{"key":"27_CR5","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/1562764.1562783","volume":"52","author":"K Asanovic","year":"2009","unstructured":"Asanovic, K., Bodik, R., Demmel, J., Keaveny, T., Keutzer, K., Kubiatowicz, J., Morgan, N., Patterson, D., Sen, K., Wawrzynek, J., Wessel, D., Yelick, K.: A view of the parallel computing landscape. Comm. ACM 52, 56\u201367 (2009)","journal-title":"Comm. ACM"},{"key":"27_CR6","first-page":"104","volume":"24","author":"T Sterling","year":"2013","unstructured":"Sterling, T.: Achieving scalability in the presence of asynchrony for exascale computing. Adv. Parall. Comp. 24, 104\u2013117 (2013)","journal-title":"Adv. Parall. Comp."},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Gao, G., Sterling, T., Stevens R., Hereld, M., Zhuparallex, W.: A study of a new parallel computation model. In: Proceedings of IEEE International Parallel and Distributed Processing Symposium, pp. 1\u20136 (2007)","DOI":"10.1109\/IPDPS.2007.370484"},{"issue":"4","key":"27_CR8","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1145\/1964218.1964232","volume":"38","author":"A Tabbal","year":"2011","unstructured":"Tabbal, A., Anderson, M., Brodowicz, M., Kaiser, H., Sterling, T.: Preliminary design examination of the parallex system from a software and hardware perspective. Sigmetrics Perform. Eval. Rev. 38(4), 81\u201387 (2011)","journal-title":"Sigmetrics Perform. Eval. Rev."},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Shamoto, H., Shirahata, K., Drozd, A., Sato, H., Matsuoka, S.: Large-scale distributed sorting for GPU-based heterogeneous supercomputers. In: Proceedings 2014 IEEE International Conference on Big Data, IEEE Big Data 2014, pp. 510\u2013518 (2014)","DOI":"10.1109\/BigData.2014.7004268"},{"key":"27_CR10","doi-asserted-by":"crossref","unstructured":"Springer, R., Lowenthal, D.K., Rountree, B., Freeh, V.W.: Minimizing execution time in MPI programs on an energy-constrained, power scalable cluster. In: Proceedings of the Eleventh ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 230\u2013238 (2006)","DOI":"10.1145\/1122971.1123006"},{"issue":"6","key":"27_CR11","doi-asserted-by":"crossref","first-page":"835","DOI":"10.1109\/TPDS.2007.1026","volume":"18","author":"VW Freeh","year":"2007","unstructured":"Freeh, V.W., Pan, F., Lowenthal, D.K., Kappiah, N., Springer, R., Rountree, B., Femal, M.E.: Analyzing the energy-time tradeoff in high-performance computing applications. IEEE Trans. Parall. Distr. Sys. 18(6), 835\u2013848 (2007)","journal-title":"IEEE Trans. Parall. Distr. Sys."},{"key":"27_CR12","unstructured":"NVIDIA profiler. http:\/\/docs.nvidia.com\/cuda\/profiler-users-guide\/"},{"key":"27_CR13","unstructured":"Intel micsmc utility. https:\/\/software.intel.com\/en-us\/articles\/measuring-power-on-intel-xeon-phi-product-family-devices"},{"key":"27_CR14","unstructured":"Nikolskiy, V., Stegailov, V.: Floating-point performance of ARM cores and their efficiency in classical molecular dynamics. J. Phys.: Conf. Ser. 681, Conf. 1, 1\u20137 (2015)"},{"key":"27_CR15","doi-asserted-by":"crossref","unstructured":"Keller, V., Gruber, R.: One joule per GFlop for BLAS2 now!. In: AIP Conference Proceedings, vol. 1281, pp. 1321\u20131324 (2010)","DOI":"10.1063\/1.3497961"},{"key":"27_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/978-3-642-15428-7_24","volume-title":"Multiple Access Communications","author":"D Podkorytov","year":"2010","unstructured":"Podkorytov, D., Rodionov, A., Sokolova, O., Yurgenson, A.: Using agent-oriented simulation system agnes for evaluation of sensor networks. In: Vinel, A., Bellalta, B., Sacchi, C., Lyakhov, A., Telek, M., Oliver, M. (eds.) MACOM 2010. LNCS, vol. 6235, pp. 247\u2013250. Springer, Heidelberg (2010). doi: 10.1007\/978-3-642-15428-7_24"},{"key":"27_CR17","doi-asserted-by":"crossref","DOI":"10.1002\/9780470058411","volume-title":"Developing Multi-Agent Systems with JADE","author":"FL Bellifemine","year":"2007","unstructured":"Bellifemine, F.L., Caire, G., Greenwood, D.: Developing Multi-Agent Systems with JADE. Wiley, Chichester (2007)"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Glinsky, B., Rodionov, A., Marchenko, M., Podkorytov, D., Weins, D.: Scaling the distributed stochastic simulation to exaflop supercomputers. In: Proceedings of IEEE High Performance Computing and Communication and 2012 IEEE 9th International Conference on Embedded Software and Systems, pp. 1131\u20131136 (2012)","DOI":"10.1109\/HPCC.2012.166"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Chavarr\u00eda-Miranda, D., Manzano, J., Krishnamoorthy, S., Vishnu, A., Barker, K., Hoisie, A.: SCaLeM: a framework for characterizing and analyzing execution models. In: Proceedings of 20 Years of Beowulf Workshop, ACM International Conference Proceeding Series, pp. 34\u201343 (2015)","DOI":"10.1145\/2737909.2737910"},{"key":"27_CR20","doi-asserted-by":"crossref","unstructured":"Kulkarni, A., Lang, M., Lumsdaine, A.: GoDEL: A multidirectional dataflow execution model for large-scale computing. In: Proceedings of the First Workshop on Data-Flow Execution Models for Extreme Scale Computing, pp. 10\u201318 (2011)","DOI":"10.1109\/DFM.2011.12"},{"issue":"12","key":"27_CR21","first-page":"1","volume":"214","author":"I Kulikov","year":"2014","unstructured":"Kulikov, I.: GPUPEGAS: a new GPU-accelerated hydrodynamic code for numerical simulations of interacting galaxies. Astrophys. J. Suppl. Ser. 214(12), 1\u201312 (2014)","journal-title":"Astrophys. J. Suppl. Ser."},{"key":"27_CR22","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.cpc.2014.09.004","volume":"186","author":"IM Kulikov","year":"2015","unstructured":"Kulikov, I.M., Chernykh, I.G., Snytnikov, A.V., Glinskiy, B.M., Tutukov, A.V.: AstroPhi: a code for complex simulation of dynamics of astrophysical objects using hybrid supercomputers. Comp. Phys. Comm. 186, 71\u201380 (2015)","journal-title":"Comp. Phys. Comm."},{"key":"27_CR23","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1134\/S0965542514060086","volume":"54","author":"SK Godunov","year":"2014","unstructured":"Godunov, S.K., Kulikov, I.M.: Computation of discontinuous solutions of fluid dynamics equations with entropy nondecrease guarantee. Comput. Math. Math. Phys. 54, 1012\u20131024 (2014)","journal-title":"Comput. Math. Math. Phys."},{"key":"27_CR24","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1016\/j.jcp.2016.04.057","volume":"317","author":"I Kulikov","year":"2016","unstructured":"Kulikov, I., Vorobyov, E.: Using the PPML approach for constructing a low-dissipation, operator-splitting scheme for numerical simulations of hydrodynamic flows. J. Comput. Phys. 317, 316\u2013346 (2016)","journal-title":"J. Comput. Phys."},{"key":"27_CR25","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1093\/mnras\/181.3.375","volume":"181","author":"RA Gingold","year":"1977","unstructured":"Gingold, R.A., Monaghan, J.J.: Smoothed particle hydrodynamics: theory and application to non-spherical stars. Mon. Not. R. Astron. Soc. 181, 375\u2013389 (1977)","journal-title":"Mon. Not. R. Astron. Soc."},{"key":"27_CR26","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/0021-9991(89)90035-1","volume":"82","author":"MJ Berger","year":"1989","unstructured":"Berger, M.J., Colella, P.: Local adaptive mesh refinement for shock hydrodynamics. J. Comput. Phys. 82, 64\u201384 (1989)","journal-title":"J. Comput. Phys."},{"key":"27_CR27","doi-asserted-by":"crossref","unstructured":"Pennycook, S.J., Hughes, C. J., Smelyanskiy, M., Jarvis, S.A.: Exploring SIMD for molecular dynamics, using intel xeon processors and intel xeon phi coprocessors. In: 2013 IEEE 27th International Symposium on Parallel and Distributed Processing (IPDPS) 2013, pp. 1085\u20131097. IEEE (2013)","DOI":"10.1109\/IPDPS.2013.44"},{"key":"27_CR28","doi-asserted-by":"crossref","unstructured":"Kim, S., Han, H.: Efficient SIMD code generation for irregular kernels. In: Proceedings of the Symposium on Principles and Practice of Parallel Programming, New Orleans, LA, 25\u201329 February 2012, pp. 55\u201364 (2012)","DOI":"10.1145\/2145816.2145824"},{"key":"27_CR29","unstructured":"Intel\u00ae Architecture Instruction Set Extensions Programming Reference. https:\/\/software.intel.com\/sites\/default\/files\/m\/9\/2\/3\/41604"},{"key":"27_CR30","unstructured":"RSC PetaStream \u2013 1PFLOPS per cabinet massively parallel supercomputer. http:\/\/www.rscgroup.ru\/sites\/default\/files\/rsc_petastream_en_print.pdf"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-49956-7_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,15]],"date-time":"2019-09-15T14:58:02Z","timestamp":1568559482000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-49956-7_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319499550","9783319499567"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-49956-7_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]}}}