{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:39:01Z","timestamp":1740123541701,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2017,3,28]],"date-time":"2017-03-28T00:00:00Z","timestamp":1490659200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004281","name":"Narodowe Centrum Nauki","doi-asserted-by":"publisher","award":["UMO-2015\/17\/D\/ST6\/04059"],"award-info":[{"award-number":["UMO-2015\/17\/D\/ST6\/04059"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MINECO and FEDER","award":["TIN2014-53495-R"],"award-info":[{"award-number":["TIN2014-53495-R"]}]},{"name":"EU COST: Network for Sustainable Ultrascale Computing (NESUS)","award":["IC1305"],"award-info":[{"award-number":["IC1305"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2017,10]]},"DOI":"10.1007\/s11227-017-2020-z","type":"journal-article","created":{"date-parts":[[2017,3,28]],"date-time":"2017-03-28T18:01:29Z","timestamp":1490724089000},"page":"4373-4389","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Modeling power consumption of 3D MPDATA and the CG method on ARM and Intel multicore architectures"],"prefix":"10.1007","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2635-7345","authenticated-orcid":false,"given":"Krzysztof","family":"Rojek","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roman","family":"Wyrzykowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,3,28]]},"reference":[{"issue":"4","key":"2020_CR1","doi-asserted-by":"crossref","first-page":"1335","DOI":"10.1007\/s10586-014-0402-z","volume":"17","author":"JI Aliaga","year":"2014","unstructured":"Aliaga JI, Barreda M, Dolz MF, Mart\u00edn AF, Mayo R, Quintana-Ort\u00ed ES (2014) Assessing the impact of the CPU power-saving modes on the task-parallel solution of sparse linear systems. Clust Comput 17(4):1335\u20131348","journal-title":"Clust Comput"},{"key":"2020_CR2","doi-asserted-by":"crossref","unstructured":"Alonso P, Badia RM, Labarta J, Barreda M, Dolz MF, Mayo R, Quintana-Ort\u00ed ES, Reyes R (2012) Tools for power-energy modelling and analysis of parallel scientific applications. In: 41st International Conference on Parallel Processing\u2014ICPP, pp 420\u2013429","DOI":"10.1109\/ICPP.2012.57"},{"key":"2020_CR3","unstructured":"AnandTech Forums (2011) Power-consumption scaling with clockspeed and Vcc for the i7-2600K. http:\/\/forums.anandtech.com\/showthread.php?t=2195927"},{"issue":"7","key":"2020_CR4","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1109\/TC.2012.97","volume":"62","author":"R Bertran","year":"2013","unstructured":"Bertran R, Gonzalez M, Martorell X, Navarro N, Ayguade E (2013) A systematic methodology to generate decomposable and responsive power models for CMPs. IEEE Trans Comput 62(7):1289\u20131302","journal-title":"IEEE Trans Comput"},{"key":"2020_CR5","doi-asserted-by":"crossref","unstructured":"Catal\u00e1n S, Malossi ACI, Bekas C, Quintana-Ort\u00ed ES(2016) The impact of voltage\u2013frequency scaling for the matrix-vector product on the \u201cibm power8\u201d. In: Proceedings of 22nd International Euro-Par Conference, Lecture Notes in Computer Science. Springer. To appear","DOI":"10.1007\/978-3-319-43659-3_8"},{"key":"2020_CR6","doi-asserted-by":"crossref","unstructured":"Choi J, Dukhan M, Liu X, Vuduc R (2014) Algorithmic time, energy, and power on candidate \u201chpc\u201d compute building blocks. In: 2014 IEEE 28th international parallel and distributed processing symposium, pp 447\u2013457","DOI":"10.1109\/IPDPS.2014.54"},{"issue":"10","key":"2020_CR7","doi-asserted-by":"crossref","first-page":"1396","DOI":"10.1109\/TPDS.2007.70804","volume":"19","author":"M Curtis-Maury","year":"2008","unstructured":"Curtis-Maury M, Blagojevic F, Antonopoulos C, Nikolopoulos D (2008) Prediction-based power-performance adaptation of multithreaded scientific codes. IEEE Trans Parallel and Distrib Syst 19(10):1396\u20131410","journal-title":"IEEE Trans Parallel and Distrib Syst"},{"issue":"5","key":"2020_CR8","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1109\/JSSC.1974.1050511","volume":"9","author":"R Dennard","year":"1974","unstructured":"Dennard R, Gaensslen F, Rideout V, Bassous E, LeBlanc A (1974) Design of ion-implanted MOSFET\u2019s with very small physical dimensions. IEEE J Solid State Circuits 9(5):256\u2013268","journal-title":"IEEE J Solid State Circuits"},{"key":"2020_CR9","unstructured":"Duranton M, De\u00a0Bosschere K, Cohen A, Maebe J, Munk H (2015) HiPEAC vision 2015. https:\/\/www.hipeac.org\/publications\/vision\/"},{"key":"2020_CR10","doi-asserted-by":"crossref","unstructured":"Elnozahy E, Kistler M, Rajamony R (2003) Energy-efficient server clusters. In: Power-aware computer systems second international workshop, PACS 2002, Lecture Notes in Computer Science, vol. 2325, pp 179\u2013197","DOI":"10.1007\/3-540-36612-1_12"},{"key":"2020_CR11","doi-asserted-by":"crossref","first-page":"658","DOI":"10.1109\/TPDS.2009.76","volume":"21","author":"R Ge","year":"2010","unstructured":"Ge R, Feng X, Song S, Chang HC, Li D, Cameron KW (2010) PowerPack: energy profiling and analysis of high-performance systems and applications. IEEE Trans Parallel Distrib Syst 21:658\u2013671","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"2","key":"2020_CR12","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1002\/cpe.3180","volume":"28","author":"G Hager","year":"2012","unstructured":"Hager G, Treibig J, Habich J, Wellein G (2012) Exploring performance and power properties of modern multicore chips via simple machine models. Concurr Comput Pract Exp 28(2):189\u2013210","journal-title":"Concurr Comput Pract Exp"},{"key":"2020_CR13","volume-title":"Introduction to high performance computing for scientists and engineers","author":"G Hager","year":"2011","unstructured":"Hager G, Wellein G (2011) Introduction to high performance computing for scientists and engineers. CRC Press, Boca Raton"},{"key":"2020_CR14","unstructured":"Home - OpenMP (02\/2017). http:\/\/www.openmp.org\/"},{"key":"2020_CR15","unstructured":"Karakasis V, Goumas G, Koziris N (2011) Exploring the performance-energy tradeoffs in sparse matrix-vector multiplication. In: Workshop on emerging supercomputing technologies (WEST)\u2014ICS\u201911"},{"key":"2020_CR16","doi-asserted-by":"crossref","unstructured":"Keramidas G, Spiliopoulos V, Kaxiras S (2010) Interval-based models for run-time DVFS orchestration in superscalar processors. In: Proceedings of the 7th ACM International Conference on Computing Frontiers (CF), pp 287\u2013296","DOI":"10.1145\/1787275.1787338"},{"key":"2020_CR17","doi-asserted-by":"crossref","unstructured":"Kestor G, Gioiosa R, Kerbyson DJ, Hoisie A (2013) Quantifying the energy cost of data movement in scientific applications. In: IEEE international symposium on workload characterization (IISWC), pp 56\u201365","DOI":"10.1109\/IISWC.2013.6704670"},{"key":"2020_CR18","unstructured":"Lucas R (2014) Top ten Exascale research challenges. http:\/\/science.energy.gov\/~\/media\/ascr\/ascac\/pdf\/meetings\/20140210\/Top10reportFEB14.pdf"},{"key":"2020_CR19","unstructured":"Malkowski K (2008) Co-adapting scientific applications and architectures toward energy-efficient high performance computing. Ph.D. thesis, University Park, PA, USA"},{"key":"2020_CR20","doi-asserted-by":"crossref","unstructured":"Malossi ACI, Ineichen Y, Bekas C, Curioni A, Quintana-Ort\u00ed ES (2014) Performance and energy-aware characterization of the sparse matrix-vector multiplication on multithreaded architectures. In: Proceedings of 43rd International Conference on Parallel Processing (ICCP), Minneapolis (MN), USA, pp 139\u2013148","DOI":"10.1109\/ICPPW.2014.30"},{"key":"2020_CR21","first-page":"24","volume":"7","author":"ACI Malossi","year":"2016","unstructured":"Malossi ACI, Ineichen Y, Bekas C, Curioni A, Quintana-Ort\u00ed ES (2016) Systematic derivation of time and power models for linear algebra kernels on multicore architectures. Sustain Comput Inform Syst 7:24\u201340","journal-title":"Sustain Comput Inform Syst"},{"key":"2020_CR22","doi-asserted-by":"crossref","unstructured":"Manousakis I, Nikolopoulos DS (2012) BTL: a framework for measuring and modeling energy in memory hierarchies. In: Proceedings of the 24th IEEE international symposium on computer architecture and high performance computing (SBAC-PAD), pp 139\u2013146","DOI":"10.1109\/SBAC-PAD.2012.38"},{"key":"2020_CR23","doi-asserted-by":"crossref","unstructured":"Molka D, Hackenberg D, Schone R, Muller MS (2010) Characterizing the energy consumption of data transfers and arithmetic operations on x86-64 processors. In: Proceedings of the 1st International Green Computing Conference (IGCC), pp 123\u2013133","DOI":"10.1109\/GREENCOMP.2010.5598316"},{"issue":"9","key":"2020_CR24","doi-asserted-by":"crossref","first-page":"1193","DOI":"10.1016\/j.compfluid.2007.12.001","volume":"37","author":"JM Prusa","year":"2008","unstructured":"Prusa JM, Smolarkiewicz PK, Wyszogrodzki AA (2008) EULAG, a computational model for multiscale flows. Comput Fluids 37(9):1193\u20131207","journal-title":"Comput Fluids"},{"key":"2020_CR25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-37801-0","volume-title":"Parallel programming for multicore and cluster systems","author":"T Rauber","year":"2013","unstructured":"Rauber T, Runger G (2013) Parallel programming for multicore and cluster systems, 2nd edn. Springer, Berlin","edition":"2"},{"issue":"4","key":"2020_CR26","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1002\/cpe.3417","volume":"27","author":"K Rojek","year":"2015","unstructured":"Rojek K, Ciznicki M, Rosa B, Kopta P, Kulczewski M, Kurowski K, Piotrowski Z, Szustak L, Wojcik D, Wyrzykowski R (2015) Adaptation of fluid model EULAG to graphics processing unit architecture. Concurr Comput Pract Exp 27(4):937\u2013957","journal-title":"Concurr Comput Pract Exp"},{"key":"2020_CR27","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1007\/978-3-319-21909-7_43","volume":"9251","author":"K Rojek","year":"2015","unstructured":"Rojek K, Wyrzykowski R (2015) Parallelization of 3D MPDATA algorithm using many graphics processors. Lect Notes Comput Sci 9251:445\u2013457","journal-title":"Lect Notes Comput Sci"},{"issue":"2","key":"2020_CR28","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1007\/s11227-016-1774-z","volume":"73","author":"K Rojek","year":"2017","unstructured":"Rojek K, Wyrzykowski R (2017) Performance modeling of 3D MPDATA simulations on GPU cluster. J Supercomput 73(2):664\u2013675","journal-title":"J Supercomput"},{"key":"2020_CR29","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3970","author":"K Rojek","year":"2016","unstructured":"Rojek K, Wyrzykowski R, Kuczynski L (2016) Systematic adaptation of stencil-based 3D MPDATA to GPU architectures. Concurr Comput Pract Exp. doi: 10.1002\/cpe.3970","journal-title":"Concurr Comput Pract Exp"},{"key":"2020_CR30","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898718003","volume-title":"Iterative methods for sparse linear systems","author":"Y Saad","year":"2003","unstructured":"Saad Y (2003) Iterative methods for sparse linear systems. SIAM, New Delhi"},{"key":"2020_CR31","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1002\/fld.1071","volume":"50","author":"P Smolarkiewicz","year":"2006","unstructured":"Smolarkiewicz P (2006) Multidimensional positive definite advection transport algorithm: an overview. Int J Numer Methods Fluids 50:1123\u20131144","journal-title":"Int J Numer Methods Fluids"},{"key":"2020_CR32","first-page":"207","volume-title":"Turbulent flow computation","author":"P Smolarkiewicz","year":"2002","unstructured":"Smolarkiewicz P, Prusa J (2002) Forward-in-time differencing for fluids: simulation of geophysical turbulence. In: Drikakis D, Guertz B (eds) Turbulent flow computation. Springer, Dordrecht, pp 207\u2013240"},{"key":"2020_CR33","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1007\/978-3-319-32149-3_39","volume":"9573","author":"L Szustak","year":"2016","unstructured":"Szustak L, Halbiniak K, Kulawik A, Wrobel J, Gepner P (2016) Toward parallel modeling of solidification based on the generalized finite difference method using Intel Xeon Phi. Lect Notes Comput Sci 9573:411\u2013412","journal-title":"Lect Notes Comput Sci"},{"key":"2020_CR34","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1155\/2015\/642705","volume":"2015","author":"L Szustak","year":"2015","unstructured":"Szustak L, Rojek K, Olas T, Kuczynski L, Halbiniak K, Gepner P (2015) Adaptation of MPDATA heterogeneous stencil computation to Intel Xeon Phi coprocessor. Sci Program 2015:14. doi: 10.1155\/2015\/642705","journal-title":"Sci Program"},{"issue":"8","key":"2020_CR35","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/j.parco.2014.04.009","volume":"40","author":"R Wyrzykowski","year":"2014","unstructured":"Wyrzykowski R, Szustak L, Rojek K (2014) Parallelization of 2D MPDATA EULAG algorithm on hybrid architectures with GPU accelerators. Parallel Comput 40(8):425\u2013447","journal-title":"Parallel Comput"},{"key":"2020_CR36","first-page":"434","volume":"8353","author":"R Wyrzykowski","year":"2014","unstructured":"Wyrzykowski R, Szustak L, Rojek K, Tomas A (2014) Towards efficient decomposition and parallelization of MPDATA on hybrid CPU-GPU cluster. Lect Notes Comput Sci 8353:434\u2013444","journal-title":"Lect Notes Comput Sci"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-017-2020-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-017-2020-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-017-2020-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T22:04:47Z","timestamp":1692741887000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-017-2020-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,28]]},"references-count":36,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2017,10]]}},"alternative-id":["2020"],"URL":"https:\/\/doi.org\/10.1007\/s11227-017-2020-z","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2017,3,28]]}}}