{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T08:35:22Z","timestamp":1673598922586},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2013,7,25]],"date-time":"2013-07-25T00:00:00Z","timestamp":1374710400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comput Sci Res Dev"],"published-print":{"date-parts":[[2014,8]]},"DOI":"10.1007\/s00450-013-0242-8","type":"journal-article","created":{"date-parts":[[2013,7,24]],"date-time":"2013-07-24T18:03:22Z","timestamp":1374689002000},"page":"221-229","source":"Crossref","is-referenced-by-count":4,"title":["Automatic detection of power bottlenecks in parallel scientific applications"],"prefix":"10.1007","volume":"29","author":[{"given":"Mar\u00eda","family":"Barreda","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sandra","family":"Catal\u00e1n","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manuel F.","family":"Dolz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafael","family":"Mayo","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":[[2013,7,25]]},"reference":[{"key":"242_CR1","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1145\/1735223.1735245","volume":"53","author":"S Albers","year":"2010","unstructured":"Albers S (2010) Energy-efficient algorithms. Commun ACM 53:86\u201396","journal-title":"Commun ACM"},{"issue":"3","key":"242_CR2","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/j.parco.2010.11.002","volume":"37","author":"JI Aliaga","year":"2011","unstructured":"Aliaga JI, Bollh\u00f6fer M, Mart\u00edn AF, Quintana-Ort\u00ed ES (2011) Exploiting thread-level parallelism in the iterative solution of sparse linear systems. Parallel Comput 37(3):183\u2013202","journal-title":"Parallel Comput"},{"key":"242_CR3","series-title":"Lecture notes in computer science","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/978-3-642-32606-6_5","volume-title":"2nd int con on ICT as key technology against global warming\u2014ICT-GLOW","author":"JI Aliaga","year":"2012","unstructured":"Aliaga JI, Dolz MF, Mart\u00edn AF, Mayo R, Quintana-Ort\u00ed ES (2012) Leveraging task-parallelism in energy-efficient ILU preconditioners. In: 2nd int con on ICT as key technology against global warming\u2014ICT-GLOW. Lecture notes in computer science, vol\u00a07453, pp\u00a055\u201363"},{"key":"242_CR4","first-page":"420","volume-title":"41st int conf on parallel processing\u2014ICPP","author":"P Alonso","year":"2012","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 int conf on parallel processing\u2014ICPP, pp 420\u2013429"},{"key":"242_CR5","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/ISPA.2012.16","volume-title":"Proc 10th IEEE int symp on parallel and distributed processing with applications\u2014ISPA 2012","author":"P Alonso","year":"2012","unstructured":"Alonso P, Dolz MF, Igual FD, Mayo R, Quintana-Ort\u00ed ES (2012) Reducing energy consumption of dense linear algebra operations on hybrid CPU-GPU platforms. In: Proc 10th IEEE int symp on parallel and distributed processing with applications\u2014ISPA 2012, pp\u00a056\u201362"},{"key":"242_CR6","volume-title":"Proc energy efficiency in large scale distributed systems conference\u2014EE-LSDS 2013","author":"P Alonso","year":"2013","unstructured":"Alonso P, Dolz MF, Igual FD, Quintana-Ort\u00ed ES, Mayo R (2013) Runtime scheduling of the LU factorization: performance and energy. In: Proc energy efficiency in large scale distributed systems conference\u2014EE-LSDS 2013 (to appear)"},{"key":"242_CR7","volume-title":"Summary report of the advanced scientific computing advisory committee (ASCAC) subcommittee","author":"S Ashby","year":"2010","unstructured":"Ashby S et al. (2010) The opportunities and challenges of Exascale computing. In: Summary report of the advanced scientific computing advisory committee (ASCAC) subcommittee. http:\/\/science.energy.gov\/~\/media\/ascr\/ascac\/pdf\/reports\/Exascale_subcommittee_report.pdf"},{"key":"242_CR8","first-page":"114","volume-title":"Third int conference on smart grids, green communications and IT energy-aware technologies\u2014Energy 2013","author":"M Barreda","year":"2013","unstructured":"Barreda M, Barrachina S, Catal\u00e1n S, Dolz MF, Fabregat G, Mayo R, Quintana ES (2013) A framework for power-performance analysis of parallel scientific applications. In: Third int conference on smart grids, green communications and IT energy-aware technologies\u2014Energy 2013, pp 114\u2013119"},{"key":"242_CR9","volume-title":"DARPA IPTO Exascale computing study","author":"K Bergman","year":"2008","unstructured":"Bergman K et al. (2008) Exascale computing study: technology challenges in achieving exascale systems. In: DARPA IPTO Exascale computing study. http:\/\/computationalsciencesolutions.com\/docs\/DARPA"},{"key":"242_CR10","first-page":"346","volume-title":"Proc 20th euromicro conference on parallel, distributed and network based processing","author":"M Castillo","year":"2012","unstructured":"Castillo M, Fern\u00e1ndez JC, Mayo R, Quintana-Ort\u00ed ES, Roca V (2012) Analysis of strategies to save energy for message-passing dense linear algebra kernels. In: Proc 20th euromicro conference on parallel, distributed and network based processing, pp 346\u2013352"},{"issue":"1","key":"242_CR11","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/1094342010391989","volume":"25","author":"J Dongarra","year":"2011","unstructured":"Dongarra J et al. (2011) The international Exascale software project roadmap. Int J High Perform Comput Appl 25(1):3\u201360","journal-title":"Int J High Perform Comput Appl"},{"key":"242_CR12","volume-title":"The HiPEAC vision for advanced computing in horizon 2020","author":"M Duranton","year":"2013","unstructured":"Duranton M et al. (2013) The HiPEAC vision for advanced computing in horizon 2020. http:\/\/www.hipeac.net\/roadmap"},{"key":"242_CR13","volume-title":"Proc energy efficiency in large scale distributed systems conference\u2014EE-LSDS 2013","author":"M El Mehdi Diouri","year":"2013","unstructured":"El Mehdi Diouri M, Dolz MF, Gl\u00fcck O, Lef\u00e8vre L, Alonso P, Catal\u00e1n S, Mayo R, Quintana-Ort\u00ed ES (2013) Solving some mysteries in power monitoring of servers: take care of your wattmeters! In: Proc energy efficiency in large scale distributed systems conference\u2014EE-LSDS 2013 (to appear)"},{"key":"242_CR14","volume-title":"Advanced configuration and power interface specification, revision\u00a05.0","author":"HP Corp","year":"2011","unstructured":"HP Corp, Intel Corp, Microsoft Corp, Phoenix Tech Ltd, Toshiba Corp (2011) Advanced configuration and power interface specification, revision\u00a05.0"},{"key":"242_CR15","volume-title":"Intel 64 and IA-32 architectures software developer manual","author":"Intel\u00a0Corp","year":"2012","unstructured":"Intel\u00a0Corp (2012) Intel 64 and IA-32 architectures software developer manual"},{"key":"242_CR16","volume-title":"Intel Xeon processor","author":"Intel\u00a0Corp","year":"2012","unstructured":"Intel\u00a0Corp (2012) Intel Xeon processor. http:\/\/www.intel.com\/xeon"},{"key":"242_CR17","unstructured":"Intel: Intel math kernel library (mkl) 11.0. http:\/\/software.intel.com\/en-us\/intel-mkl"},{"key":"242_CR18","doi-asserted-by":"crossref","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 et al. (2008) The vampir performance analysis tool-set. In: Tools for high performance computing, pp 139\u2013155"},{"key":"242_CR19","unstructured":"Kunkel J (2011) HDTrace\u2014a tracing and simulation environment of application and system interaction. Tech Rep 2, Department of Informatics, Scientific Computing. Universit\u00e4t Hamburg"},{"key":"242_CR20","unstructured":"Mienik M CPU burn-in v1.01. http:\/\/www.cpuburnin.com\/"},{"key":"242_CR21","volume-title":"NVIDIA CUDA compute unified device architecture programming guide","author":"NVIDIA Corporation","year":"2009","unstructured":"NVIDIA Corporation (2009) NVIDIA CUDA compute unified device architecture programming guide, 2.3.1 edn.","edition":"2.3.1"},{"key":"242_CR22","unstructured":"Official Website. Python Programming Language. http:\/\/www.python.org\/"},{"key":"242_CR23","volume-title":"18th world OCCAM and transputer user group technical meeting","author":"V Pillet","year":"1995","unstructured":"Pillet V, Labarta J, Cortes T, Girona S (1995) Paraver: a tool to visualize and analyze parallel code. In: 18th world OCCAM and transputer user group technical meeting"},{"issue":"4","key":"242_CR24","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1145\/1594835.1504196","volume":"44","author":"G Quintana-Ort\u00ed","year":"2009","unstructured":"Quintana-Ort\u00ed G, Igual FD, Quintana-Ort\u00ed ES, van de Geijn RA (2009) Solving dense linear systems on platforms with multiple hardware accelerators. SIGPLAN Not 44(4):121\u2013130. doi: 10.1145\/1594835.1504196","journal-title":"SIGPLAN Not"},{"issue":"3","key":"242_CR25","doi-asserted-by":"crossref","first-page":"14:1","DOI":"10.1145\/1527286.1527288","volume":"36","author":"G Quintana-Ort\u00ed","year":"2009","unstructured":"Quintana-Ort\u00ed G, Quintana-Ort\u00ed E, van de Geijn R, Zee FV, Chan E (2009) Programming matrix algorithms-by-blocks for thread-level parallelism. ACM Trans Math Softw 36(3):14:1\u201314:26","journal-title":"ACM Trans Math Softw"},{"key":"242_CR26","volume-title":"ACM queue","author":"E Saxe","year":"2010","unstructured":"Saxe E (2010) Power-efficient software. In: ACM queue"},{"key":"242_CR27","unstructured":"Servat H, Llort G Extrae user guide manual for version 2.1.1"},{"issue":"2","key":"242_CR28","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1177\/1094342006064482","volume":"20","author":"SS Shende","year":"2006","unstructured":"Shende SS, Malony AD (2006) The tau parallel performance system. Int J High Perform Comput Appl 20(2):287\u2013311","journal-title":"Int J High Perform Comput Appl"},{"key":"242_CR29","unstructured":"The Green500 list (2012). http:\/\/www.green500.org"}],"container-title":["Computer Science - Research and Development"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00450-013-0242-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00450-013-0242-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00450-013-0242-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T13:32:49Z","timestamp":1559136769000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00450-013-0242-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,7,25]]},"references-count":29,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2014,8]]}},"alternative-id":["242"],"URL":"https:\/\/doi.org\/10.1007\/s00450-013-0242-8","relation":{},"ISSN":["1865-2034","1865-2042"],"issn-type":[{"value":"1865-2034","type":"print"},{"value":"1865-2042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,7,25]]}}}