{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T14:02:48Z","timestamp":1765807368547,"version":"3.37.3"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2016,8,4]],"date-time":"2016-08-04T00:00:00Z","timestamp":1470268800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003329","name":"Ministerio de Econom\u00eda y Competitividad","doi-asserted-by":"publisher","award":["CICYT TIN2011-23283","CICYT TIN2014-53495-R"],"award-info":[{"award-number":["CICYT TIN2011-23283","CICYT TIN2014-53495-R"]}],"id":[{"id":"10.13039\/501100003329","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003329","name":"Ministerio de Econom\u00eda y Competitividad","doi-asserted-by":"publisher","award":["CICYT TIN2012-32180"],"award-info":[{"award-number":["CICYT TIN2012-32180"]}],"id":[{"id":"10.13039\/501100003329","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EU FET project","award":["318793"],"award-info":[{"award-number":["318793"]}]},{"DOI":"10.13039\/501100003176","name":"Ministerio de Educaci\u00f3n, Cultura y Deporte","doi-asserted-by":"publisher","award":["FPU13\/06434"],"award-info":[{"award-number":["FPU13\/06434"]}],"id":[{"id":"10.13039\/501100003176","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2016,9]]},"DOI":"10.1007\/s10586-016-0611-8","type":"journal-article","created":{"date-parts":[[2016,8,4]],"date-time":"2016-08-04T06:55:02Z","timestamp":1470293702000},"page":"1037-1051","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Architecture-aware configuration and scheduling of matrix multiplication on asymmetric multicore processors"],"prefix":"10.1007","volume":"19","author":[{"given":"Sandra","family":"Catal\u00e1n","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francisco D.","family":"Igual","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael","family":"Mayo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael","family":"Rodr\u00edguez-S\u00e1nchez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,8,4]]},"reference":[{"issue":"5","key":"611_CR1","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.: Design of ion-implanted MOSFET\u2019s with very small physical dimensions. IEEE J. Solid State Circuit 9(5), 256\u2013268 (1974)","journal-title":"IEEE J. Solid State Circuit"},{"issue":"8","key":"611_CR2","first-page":"114","volume":"38","author":"G Moore","year":"1965","unstructured":"Moore, G.: Cramming more components onto integrated circuits. Electronics 38(8), 114\u2013117 (1965)","journal-title":"Electronics"},{"key":"611_CR3","unstructured":"Duranton, M., et al.: The HiPEAC vision for advanced computing in horizon 2020. http:\/\/www.hipeac.net\/roadmap (2013)"},{"key":"611_CR4","unstructured":"Lavignon J.F., et al.: ETP4HPC strategic research agenda achieving HPC leadership in Europe. (2013)"},{"key":"611_CR5","unstructured":"Lucas R., et al.: Top ten Exascale research challenges. http:\/\/science.energy.gov\/~\/media\/ascr\/ascac\/pdf\/meetings\/20140210\/Top10reportFEB14 (2014)"},{"key":"611_CR6","doi-asserted-by":"crossref","unstructured":"Esmaeilzadeh, H., Blem, E., St.\u00a0Amant, R., Sankaralingam, K., Burger, D.: Dark silicon and the end of multicore scaling. In: Proceedings 38th Annual International Symposium on Computer Architecture, ISCA\u201911, pp. 365\u2013376 (2011)","DOI":"10.1145\/2000064.2000108"},{"key":"611_CR7","doi-asserted-by":"publisher","unstructured":"G\u00f6ddeke, D., Komatitsch, D., Geveler, M., Ribbrock, D., Rajovic, N., Puzovic, N., Ramirez, A.: Energy efficiency vs. performance of the numerical solution of PDEs: An application study on a low-power ARM-based cluster. J. Comput. Phys. 237(0), 132\u2013150 (2013). doi: 10.1016\/j.jcp.2012.11.031 http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0021999112007115","DOI":"10.1016\/j.jcp.2012.11.031"},{"key":"611_CR8","doi-asserted-by":"publisher","unstructured":"Rajovic, N., Carpenter, P.M., Gelado, I., Puzovic, N., Ramirez, A., Valero, M.: Supercomputing with commodity CPUs: Are mobile SoCs ready for HPC? In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC \u201913, pp. 40:1\u201340:12. ACM, New York, NY, USA (2013). doi: 10.1145\/2503210.2503281","DOI":"10.1145\/2503210.2503281"},{"key":"611_CR9","unstructured":"The TOP500 list. http:\/\/www.top500.org (2015)"},{"key":"611_CR10","unstructured":"The GREEN500 list. http:\/\/www.green500.org (2015)"},{"issue":"7","key":"611_CR11","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/MC.2008.209","volume":"41","author":"M Hill","year":"2008","unstructured":"Hill, M., Marty, M.: Amdahl\u2019s law in the multicore era. Computer 41(7), 33\u201338 (2008)","journal-title":"Computer"},{"key":"611_CR12","doi-asserted-by":"crossref","unstructured":"Kumar, R., Tullsen, D.M., Ranganathan, P., Jouppi, N.P., Farkas, K.I.: Single-ISA heterogeneous multi-core architectures for multithreaded workload performance. In: Proceedings 31st Annual International Symposium on Computer Architecture, ISCA\u201904, p. 64 (2004)","DOI":"10.1109\/ISCA.2004.1310764"},{"key":"611_CR13","doi-asserted-by":"crossref","unstructured":"Morad, T., Weiser, U., Kolodny, A., Valero, M., Ayguade, E.: Performance, power efficiency and scalability of asymmetric cluster chip multiprocessors. Comput. Arch. Lett. 5(1), 14\u201317 (2006)","DOI":"10.1109\/L-CA.2006.6"},{"key":"611_CR14","doi-asserted-by":"crossref","unstructured":"Winter, J.A., Albonesi, D.H., Shoemaker, C.A.: Scalable thread scheduling and global power management for heterogeneous many-core architectures. In: Proceeding 19th International Conference Parallel Architectures and Compilation Techniques, PACT\u201910, pp. 29\u201340 (2010)","DOI":"10.1145\/1854273.1854283"},{"issue":"1","key":"611_CR15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/77626.79170","volume":"16","author":"JJ Dongarra","year":"1990","unstructured":"Dongarra, J.J., Du Croz, J., Hammarling, S., Duff, I.: A set of level 3 basic linear algebra subprograms. ACM Trans. Math. Softw. 16(1), 1\u201317 (1990)","journal-title":"ACM Trans. Math. Softw."},{"issue":"3","key":"611_CR16","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1145\/292395.292412","volume":"24","author":"B K\u00e5gstr\u00f6m","year":"1998","unstructured":"K\u00e5gstr\u00f6m, B., Ling, P., van Loan, C.: GEMM-based level 3 BLAS: high-performance model implementations and performance evaluation benchmark. ACM Trans. Math. Softw. 24(3), 268\u2013302 (1998)","journal-title":"ACM Trans. Math. Softw."},{"key":"611_CR17","unstructured":"Asanovic, K., Bodik, R., Catanzaro, B.C., Gebis, J.J., Husbands, P., Keutzer, K., Patterson, D.A., Plishker, W.L., Shalf, J., Williams, S.W., Yelick, K.A.: The landscape of parallel computing research: a view from Berkeley. Technical report UCB\/EECS-2006-183, University of California at Berkeley, Electrical Engineering and Computer Sciences (2006)"},{"key":"611_CR18","unstructured":"Intel\u00a0Corp.: Intel math kernel library (MKL) 11.0. http:\/\/software.intel.com\/en-us\/intel-mkl (2015)"},{"key":"611_CR19","unstructured":"AMD: AMD core math library. http:\/\/developer.amd.com\/tools\/cpu\/acml\/pages\/default.aspx (2015)"},{"key":"611_CR20","unstructured":"IBM: Engineering and scientific subroutine library. http:\/\/www.ibm.com\/systems\/software\/essl\/ (2015)"},{"key":"611_CR21","unstructured":"NVIDIA: CUDA basic linear algebra subprograms. https:\/\/developer.nvidia.com\/cuBLAS (2015)"},{"key":"611_CR22","doi-asserted-by":"crossref","unstructured":"Goto, K., van\u00a0de Geijn, R.: Anatomy of a high-performance matrix multiplication. ACM Trans. Math. Softw. 34(3), 12:1\u201312:25 (2008)","DOI":"10.1145\/1356052.1356053"},{"key":"611_CR23","doi-asserted-by":"publisher","unstructured":"Goto, K., van\u00a0de Geijn, R.: High performance implementation of the level-3 BLAS. ACM Trans. Math. Softw. 35(1), 4:1\u20134:14 (2008). doi: 10.1145\/1377603.1377607","DOI":"10.1145\/1377603.1377607"},{"key":"611_CR24","unstructured":"OpenBLAS. http:\/\/xianyi.github.com\/OpenBLAS\/ (2015)"},{"key":"611_CR25","doi-asserted-by":"crossref","unstructured":"Van Zee, F.G., van\u00a0de Geijn, R.A.: BLIS: A framework for generating BLAS-like libraries. ACM Trans. Math. Softw. (2016), (To appear)","DOI":"10.1145\/2755561"},{"key":"611_CR26","doi-asserted-by":"crossref","unstructured":"Whaley, R.C., Dongarra, J.J.: Automatically tuned linear algebra software. In: Proceedings of SC\u201998 (1998)","DOI":"10.1109\/SC.1998.10004"},{"key":"611_CR27","doi-asserted-by":"publisher","unstructured":"Chitlur, N., Srinivasa, G., Hahn, S., Gupta, P., Reddy, D., Koufaty, D., Brett, P., Prabhakaran, A., Zhao, L., Ijih, N., Subhaschandra, S., Grover, S., Jiang, X., Iyer, R.: Quickia: Exploring heterogeneous architectures on real prototypes. In: High Performance Computer Architecture (HPCA), 2012 IEEE 18th International Symposium on, pp. 1\u20138 (2012). doi: 10.1109\/HPCA.2012.6169046","DOI":"10.1109\/HPCA.2012.6169046"},{"key":"611_CR28","doi-asserted-by":"crossref","unstructured":"Chitlur, N., Srinivasa, G., Hahn, S., Gupta, P.K., Reddy, D., Koufaty, D., Brett, P., Prabhakaran, A., Zhao, L., Ijih, N., Subhaschandra, S., Grover, S., Jiang, X., Iyer, R.: Quickia: Exploring heterogeneous architectures on real prototypes. In: Proceedings IEEE 18th International Symposium on High-Performance Computer Architecture, HPCA\u201912, pp. 1\u20138 (2012)","DOI":"10.1109\/HPCA.2012.6169046"},{"key":"611_CR29","unstructured":"Hourd, J., Fan, C., Zeng, J., Zhang, Q.S., Best, M.J., Fedorova, A., Mustard, C.: Exploring practical benefits of asymmetric multicore processors. In: 2nd Workshop on Parallel Execution of Sequential Programs on Multi-core Architectures, PESPMA (2009)"},{"key":"611_CR30","doi-asserted-by":"crossref","unstructured":"Lakshminarayana, N.B., Lee, J., Kim, H.: Age based scheduling for asymmetric multiprocessors. In: Proceedings Conference on High Performance Computing Networking, Storage and Analysis, SC\u201909, pp. 25:1\u201325:12 (2009)","DOI":"10.1145\/1654059.1654085"},{"key":"611_CR31","doi-asserted-by":"crossref","unstructured":"Rodrigues, R., Annamalai, A., Koren, I., Kundu, S.: Improving performance per watt of asymmetric multi-core processors via online program phase classification and adaptive core morphing. ACM Trans. Des. Autom. Electron. Syst. 18(1), 5:1\u20135:23 (2013)","DOI":"10.1145\/2390191.2390196"},{"key":"611_CR32","doi-asserted-by":"crossref","unstructured":"Clarke, D., Lastovetsky, A., Rychkov, V.: Column-based matrix partitioning for parallel matrix multiplication on heterogeneous processors based on functional performance models. In: Euro-Par 2011: Parallel Processing Workshops, LNCS, vol. 7155, pp. 450\u2013459 (2012)","DOI":"10.1007\/978-3-642-29737-3_50"},{"key":"611_CR33","doi-asserted-by":"crossref","unstructured":"Beaumont, O., Marchal, L.: Analysis of dynamic scheduling strategies for matrix multiplication on heterogeneous platforms. In: Proceedings 23rd International Symposium High-performance Parallel and Distributed Computing, HPDC\u201914, pp. 141\u2013152 (2014)","DOI":"10.1145\/2600212.2600223"},{"key":"611_CR34","unstructured":"Low, T.M., Igual, F.D., Smith, T.M., Quintana-Ort\u00ed, E.S.: Analytical modeling is enough for high performance BLIS. Technical report FLAWN #74, Department of Computer Sciences, The University of Texas at Austin ACM Trans. Math. Softw. (2014). http:\/\/www.cs.utexas.edu\/users\/flame\/"},{"key":"611_CR35","unstructured":"Van\u00a0Zee, F.G., Smith, T.M., Marker, B., Low, T.M., van\u00a0de Geijn, R.A., Igual, F.D., Smelyanskiy, M., Zhang, X., Kistler, M., Austel, V., Gunnels, J., Killough, L.: The BLIS framework: Experiments in portability. ACM Trans. Math. Softw. (2014). In review. http:\/\/www.cs.utexas.edu\/users\/flame"},{"key":"611_CR36","doi-asserted-by":"crossref","unstructured":"Smith, T.M., van\u00a0de Geijn, R., Smelyanskiy, M., Hammond, J.R., Van\u00a0Zee, F.G.: Anatomy of high-performance many-threaded matrix multiplication. In: Proceedings IEEE 28th International Parallel and Distributed Processing Symposium, IPDPS\u201914, pp. 1049\u20131059 (2014)","DOI":"10.1109\/IPDPS.2014.110"},{"key":"611_CR37","doi-asserted-by":"crossref","unstructured":"Alonso, P., Badia, R.M., Labarta, J., Barreda, M., Dolz, M.F., Mayo, R., Quintana-Ort\u00ed, E.S., Reyes, R.: Tools for power-energy modelling and analysis of parallel scientific applications. In: 41st International Conference on Parallel Processing\u2014ICPP, pp. 420\u2013429 (2012)","DOI":"10.1109\/ICPP.2012.57"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-016-0611-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-016-0611-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-016-0611-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,4]],"date-time":"2022-07-04T22:44:56Z","timestamp":1656974696000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-016-0611-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8,4]]},"references-count":37,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,9]]}},"alternative-id":["611"],"URL":"https:\/\/doi.org\/10.1007\/s10586-016-0611-8","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"type":"print","value":"1386-7857"},{"type":"electronic","value":"1573-7543"}],"subject":[],"published":{"date-parts":[[2016,8,4]]}}}