{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:34:28Z","timestamp":1742970868795,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030162047"},{"type":"electronic","value":"9783030162054"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-16205-4_9","type":"book-chapter","created":{"date-parts":[[2019,3,30]],"date-time":"2019-03-30T05:01:59Z","timestamp":1553922119000},"page":"112-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Improving Performance and Energy Efficiency of Geophysics Applications on GPU Architectures"],"prefix":"10.1007","author":[{"given":"Pablo J.","family":"Pavan","sequence":"first","affiliation":[]},{"given":"Matheus S.","family":"Serpa","sequence":"additional","affiliation":[]},{"given":"Emmanuell Diaz","family":"Carre\u00f1o","sequence":"additional","affiliation":[]},{"given":"V\u00edctor","family":"Mart\u00ednez","sequence":"additional","affiliation":[]},{"given":"Edson Luiz","family":"Padoin","sequence":"additional","affiliation":[]},{"given":"Philippe O. A.","family":"Navaux","sequence":"additional","affiliation":[]},{"given":"Jairo","family":"Panetta","sequence":"additional","affiliation":[]},{"given":"Jean-Fran\u00e7ois","family":"Mehaut","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,3,31]]},"reference":[{"key":"9_CR1","doi-asserted-by":"publisher","unstructured":"Bauer, M., Cook, H., Khailany, B.: Cudadma: optimizing GPU memory bandwidth via warp specialization. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2011, pp. 12:1\u201312:11. ACM, New York (2011). https:\/\/doi.org\/10.1145\/2063384.2063400 . http:\/\/doi.acm.org\/10.1145\/2063384.2063400","DOI":"10.1145\/2063384.2063400"},{"key":"9_CR2","doi-asserted-by":"publisher","first-page":"2146","DOI":"10.1016\/j.procs.2011.04.235","volume":"4","author":"R Cruz de la","year":"2011","unstructured":"de la Cruz, R., Araya-Polo, M.: Towards a multi-level cache performance model for 3D stencil computation. Procedia Comput. Sci. 4, 2146\u20132155 (2011)","journal-title":"Procedia Comput. Sci."},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Datta, K., et al.: Stencil computation optimization and auto-tuning on state-of-the-art multicore architectures. In: Proceedings of the 2008 ACM\/IEEE Conference on Supercomputing, p. 4. IEEE Press (2008)","DOI":"10.1109\/SC.2008.5222004"},{"key":"9_CR4","doi-asserted-by":"publisher","unstructured":"Dong, Y., Chen, J., Tang, T.: Power measurements and analyses of massive object storage system. In: Proceedings of the International Conference on Computer and Information Technology (CIT), pp. 1317\u20131322. IEEE Computer Society (2010). https:\/\/doi.org\/10.1109\/CIT.2010.237","DOI":"10.1109\/CIT.2010.237"},{"key":"9_CR5","doi-asserted-by":"publisher","unstructured":"Falch, T.L., Elster, A.C.: Register caching for stencil computations on GPUs. In: 2014 16th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, pp. 479\u2013486. IEEE, September 2014. https:\/\/doi.org\/10.1109\/SYNASC.2014.70","DOI":"10.1109\/SYNASC.2014.70"},{"key":"9_CR6","doi-asserted-by":"publisher","unstructured":"Feng, X., Ge, R., Cameron, K.W.: Power and energy profiling of scientific applications on distributed systems. In: International Parallel and Distributed Processing Symposium (IPDPS), International Conference on Performance Engineering, p. 34. IEEE (2005). https:\/\/doi.org\/10.1109\/IPDPS.2005.346","DOI":"10.1109\/IPDPS.2005.346"},{"key":"9_CR7","unstructured":"Hamilton, B., Webb, C.J., Gray, A., Bilbao, S.: Large stencil operations for GPU-based 3-d acoustics simulations. In: Proceedings of the Digital Audio Effects (DAFx), Trondheim, Norway (2015)"},{"key":"9_CR8","doi-asserted-by":"publisher","unstructured":"Laros, J., et al.: Topics on measuring real power usage on high performance computing platforms. In: Proceedings of the International Conference on Cluster Computing and Workshops (ICCC), pp. 1\u20138 (2009). https:\/\/doi.org\/10.1109\/CLUSTR.2009.5289179","DOI":"10.1109\/CLUSTR.2009.5289179"},{"key":"9_CR9","unstructured":"Maruyama, N., Aoki, T.: Optimizing stencil computations for NVIDIA Kepler GPUs. In: Proceedings of the 1st International Workshop on High-Performance Stencil Computations, Vienna, pp. 89\u201395 (2014)"},{"key":"9_CR10","doi-asserted-by":"publisher","unstructured":"Micikevicius, P.: 3D finite difference computation on GPUs using CUDA. In: Proceedings of 2nd Workshop on General Purpose Processing on Graphics Processing Units, GPGPU-2, pp. 79\u201384. ACM, New York (2009). https:\/\/doi.org\/10.1145\/1513895.1513905 . http:\/\/doi.acm.org\/10.1145\/1513895.1513905","DOI":"10.1145\/1513895.1513905"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Nasciutti, T.C., Panetta, J.: Impacto da arquitetura de mem\u00f3ria de GPGPUs na velocidade de computa\u00e7\u00e3poundso de est\u00eanceis. In: XVII Simp\u00f3sio de Sistemas Computacionais (WSCAD-SSC), Aracaju, SE, pp. 1\u20138 (2016)","DOI":"10.5753\/wscad.2016.14251"},{"issue":"6","key":"9_CR12","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1016\/j.jocs.2012.08.011","volume":"3","author":"VV Nikitin","year":"2012","unstructured":"Nikitin, V.V., Duchkov, A.A., Andersson, F.: Parallel algorithm of 3D wave-packet decomposition of seismic data: implementation and optimization for GPU. J. Comput. Sci. 3(6), 469\u2013473 (2012)","journal-title":"J. Comput. Sci."},{"key":"9_CR13","unstructured":"Padoin, E.L., de Oliveira, D.A.G., Velho, P., Navaux, P.O.A., Mehaut, J.F.: ARM-based cluster: performance, scalability and energy efficiency. In: 4th Workshop on Applications for Multi-Core Architectures (WAMCA SBAC-PAD), Porto de Galinhas, PB, Brasil, pp. 1\u20136 (2013)"},{"issue":"3","key":"9_CR14","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s10586-012-0219-6","volume":"16","author":"EL Padoin","year":"2013","unstructured":"Padoin, E.L., Pilla, L.L., Boito, F.Z., Kassick, R.V., Velho, P., Navaux, P.O.: Evaluating application performance and energy consumption on hybrid CPU+GPU architecture. Cluster Comput. 16(3), 511\u2013525 (2013)","journal-title":"Cluster Comput."},{"key":"9_CR15","doi-asserted-by":"publisher","unstructured":"Schafer, A., Fey, D.: High performance stencil code algorithms for GPGPUs. Procedia Comput. Sci. 4, 2027\u20132036 (2011). https:\/\/doi.org\/10.1016\/j.procs.2011.04.221 . http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050911002791 . proceedings of the International Conference on Computational Science, ICCS 2011","DOI":"10.1016\/j.procs.2011.04.221"},{"key":"9_CR16","doi-asserted-by":"publisher","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009). https:\/\/doi.org\/10.1145\/1498765.1498785 . http:\/\/doi.acm.org\/10.1145\/1498765.1498785","DOI":"10.1145\/1498765.1498785"},{"key":"9_CR17","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.cageo.2015.05.008","volume":"82","author":"Q Xue","year":"2015","unstructured":"Xue, Q., Wang, Y., Zhan, Y., Chang, X.: An efficient GPU implementation for locating micro-seismic sources using 3D elastic wave time-reversal imaging. Comput. Geosci. 82, 89\u201397 (2015)","journal-title":"Comput. Geosci."},{"key":"9_CR18","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.ijepes.2016.03.048","volume":"83","author":"G Zhou","year":"2016","unstructured":"Zhou, G., et al.: A novel GPU-accelerated strategy for contingency screening of static security analysis. Int. J. Electr. Power Energy Syst. 83, 33\u201339 (2016)","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"9_CR19","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1016\/j.procs.2012.04.104","volume":"9","author":"J Zhou","year":"2012","unstructured":"Zhou, J., Unat, D., Choi, D.J., Guest, C.C., Cui, Y.: Hands-on performance tuning of 3D finite difference earthquake simulation on GPU fermi chipset. Procedia Comput. Sci. 9, 976\u2013985 (2012)","journal-title":"Procedia Comput. Sci."}],"container-title":["Communications in Computer and Information Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-16205-4_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T21:38:45Z","timestamp":1663191525000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-16205-4_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030162047","9783030162054"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-16205-4_9","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"31 March 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CARLA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Latin American High Performance Computing Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bucaramanga","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Colombia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"carla2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/carla2018.ccarla.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}