{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T03:59:30Z","timestamp":1742961570522,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"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_16","type":"book-chapter","created":{"date-parts":[[2019,3,30]],"date-time":"2019-03-30T01:01:59Z","timestamp":1553907719000},"page":"213-223","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Performance Evaluation of Stencil Computations Based on Source-to-Source Transformations"],"prefix":"10.1007","author":[{"given":"V\u00edctor","family":"Mart\u00ednez","sequence":"first","affiliation":[]},{"given":"Matheus S.","family":"Serpa","sequence":"additional","affiliation":[]},{"given":"Pablo J.","family":"Pavan","sequence":"additional","affiliation":[]},{"given":"Edson Luiz","family":"Padoin","sequence":"additional","affiliation":[]},{"given":"Philippe O. A.","family":"Navaux","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,3,31]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Breuer, A., Heinecke, A., Bader, M.: Petascale local time stepping for the ADER-DG finite element method. In: 2016 IEEE International Parallel and Distributed Processing Symposium, IPDPS 2016, Chicago, IL, USA, 23\u201327 May 2016, pp. 854\u2013863 (2016)","DOI":"10.1109\/IPDPS.2016.109"},{"issue":"7","key":"16_CR2","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1002\/cpe.1904","volume":"24","author":"R Buchty","year":"2012","unstructured":"Buchty, R., Heuveline, V., Karl, W., Weiss, J.P.: A survey on hardware-aware and heterogeneous computing on multicore processors and accelerators. Concurrency Comput. Pract. Exp. 24(7), 663\u2013675 (2012). \n                    https:\/\/doi.org\/10.1002\/cpe.1904","journal-title":"Concurrency Comput. Pract. Exp."},{"issue":"3\u20134","key":"16_CR3","first-page":"205","volume":"26","author":"M Christen","year":"2011","unstructured":"Christen, M., Schenk, O., Burkhart, H.: Automatic code generation and tuning for stencil kernels on modern shared memory architectures. Comput. Sci. 26(3\u20134), 205\u2013210 (2011)","journal-title":"Comput. Sci."},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Cronsioe, J., Videau, B., Marangozova-Martin, V.: Boast: bringing optimization through automatic source-to-source transformations. In: 2013 IEEE 7th International Symposium on Embedded Multicore SoCs, pp. 129\u2013134, September 2013. \n                    https:\/\/doi.org\/10.1109\/MCSoC.2013.12","DOI":"10.1109\/MCSoC.2013.12"},{"issue":"1","key":"16_CR5","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1137\/070693199","volume":"51","author":"K Datta","year":"2009","unstructured":"Datta, K., Kamil, S., Williams, S., Oliker, L., Shalf, J., Yelick, K.: Optimization and performance modeling of stencil computations on modern microprocessors. SIAM Rev. 51(1), 129\u2013159 (2009). \n                    https:\/\/doi.org\/10.1137\/070693199","journal-title":"SIAM Rev."},{"key":"16_CR6","doi-asserted-by":"crossref","unstructured":"Datta, K., et al.: Auto-Tuning Stencil Computations on Multicore and Accelerators. CRC Press, Taylor & Francis Group (2010)","DOI":"10.1201\/b10376-18"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Dupros, F., Boulahya, F., Aochi, H., Thierry, P.: Communication-avoiding seismic numerical kernels on multicore processors. In: 2015 IEEE 17th International Conference on High Performance Computing and Communications (HPCC), 2015 IEEE 7th International Symposium on Cyberspace Safety and Security (CSS), 2015 IEEE 12th International Conferen on Embedded Software and Systems (ICESS), pp. 330\u2013335, August 2015. \n                    https:\/\/doi.org\/10.1109\/HPCC-CSS-ICESS.2015.230","DOI":"10.1109\/HPCC-CSS-ICESS.2015.230"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Dupros, F., Do, H., Aochi, H.: On scalability issues of the elastodynamics equations on multicore platforms. In: Proceedings of the International Conference on Computational Science, ICCS 2013, Barcelona, Spain, 5\u20137 June 2013, pp. 1226\u20131234 (2013)","DOI":"10.1016\/j.procs.2013.05.289"},{"key":"16_CR9","doi-asserted-by":"publisher","unstructured":"Forth, S.A., Tadjouddine, M., Pryce, J.D., Reid, J.K.: Jacobian code generated by source transformation and vertex elimination can be as efficient ash and-coding. ACM Trans. Math. Softw. 30(3), 266\u2013299 (2004). \n                    https:\/\/doi.org\/10.1145\/1024074.1024076\n                    \n                  . \n                    http:\/\/doi.acm.org\/10.1145\/1024074.1024076","DOI":"10.1145\/1024074.1024076"},{"key":"16_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1007\/978-3-540-45213-3_31","volume-title":"Modular Programming Languages","author":"T Genssler","year":"2003","unstructured":"Genssler, T., Kuttruff, V.: Source-to-source transformation in the large. In: B\u00f6sz\u00f6rm\u00e9nyi, L., Schojer, P. (eds.) JMLC 2003. LNCS, vol. 2789, pp. 254\u2013265. Springer, Heidelberg (2003). \n                    https:\/\/doi.org\/10.1007\/978-3-540-45213-3_31"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Khan, M., Priyanka, N., Ahmed, W., Radhika, N., Pavithra, M., Parimala, K.: Understanding source-to-source transformations for frequent porting of applications on changing cloud architectures. In: 2014 International Conference on Parallel, Distributed and Grid Computing, pp. 350\u2013354, December 2014. \n                    https:\/\/doi.org\/10.1109\/PDGC.2014.7030769","DOI":"10.1109\/PDGC.2014.7030769"},{"key":"16_CR12","doi-asserted-by":"publisher","unstructured":"Lee, S., Min, S.J., Eigenmann, R.: OpenMP to GPGPU: a compiler framework for automatic translation and optimization. SIGPLAN Not. 44(4), 101\u2013110 (2009). \n                    https:\/\/doi.org\/10.1145\/1594835.1504194\n                    \n                  . \n                    http:\/\/doi.acm.org\/10.1145\/1594835.1504194","DOI":"10.1145\/1594835.1504194"},{"key":"16_CR13","doi-asserted-by":"publisher","unstructured":"Loveman, D.B.: Program improvement by source-to-source transformation. J. ACM 24(1), 121\u2013145 (1977). \n                    https:\/\/doi.org\/10.1145\/321992.322000\n                    \n                  . \n                    http:\/\/doi.acm.org\/10.1145\/321992.322000","DOI":"10.1145\/321992.322000"},{"key":"16_CR14","doi-asserted-by":"publisher","unstructured":"Mart\u00ednez, V., Dupros, F., Castro, M., Navaux, P.: Performance improvement of stencil computations for multi-core architectures based on machine learning. Procedia Comput. Sci. 108, 305\u2013314 (2017). \n                    https:\/\/doi.org\/10.1016\/j.procs.2017.05.164\n                    \n                  . \n                    http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050917307408\n                    \n                  . international Conference on Computational Science, ICCS 2017, 12\u201314 June 2017, Zurich, Switzerland","DOI":"10.1016\/j.procs.2017.05.164"},{"key":"16_CR15","doi-asserted-by":"crossref","unstructured":"Mijakovic, R., Firbach, M., Gerndt, M.: An architecture for flexible auto-tuning: the periscope tuning framework 2.0. In: International Conference on Green High Performance Computing (ICGHPC), pp. 1\u20139, February 2016. \n                    https:\/\/doi.org\/10.1109\/ICGHPC.2016.7508066","DOI":"10.1109\/ICGHPC.2016.7508066"},{"issue":"4","key":"16_CR16","doi-asserted-by":"publisher","first-page":"69:1","DOI":"10.1145\/2788396","volume":"47","author":"S Mittal","year":"2015","unstructured":"Mittal, S., Vetter, J.S.: A survey of CPU-GPU heterogeneous computing techniques. ACM Comput. Surv. 47(4), 69:1\u201369:35 (2015). \n                    https:\/\/doi.org\/10.1145\/2788396","journal-title":"ACM Comput. Surv."},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Moczo, P., Robertsson, J., Eisner, L.: The finite-difference time-domain method for modeling of seismic wave propagation. In: Advances in Wave Propagation in Heterogeneous Media, Advances in Geophysics, vol. 48, chap. 8, pp. 421\u2013516. Elsevier - Academic Press (2007)","DOI":"10.1016\/S0065-2687(06)48008-0"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Satish, N., Chhugani, J., Kim, C., Dubey, P.: 3.5-D blocking optimization for stencil computations on modern CPUs and GPUs. In: 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201313, November 2010. \n                    https:\/\/doi.org\/10.1109\/SC.2010.2","DOI":"10.1109\/SC.2010.2"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Noaje, G., Jaillet, C., Krajecki, M.: Source-to-source code translator: OpenMP C to CUDA. In: 2011 IEEE International Conference on High Performance Computing and Communications, pp. 512\u2013519, September 2011. \n                    https:\/\/doi.org\/10.1109\/HPCC.2011.73","DOI":"10.1109\/HPCC.2011.73"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Renault, E., Ancelin, C., Jimenez, W., Botero, O.: Using source-to-source transformation tools to provide distributed parallel applications from openMP source code. In: 2008 International Symposium on Parallel and Distributed Computing, pp. 197\u2013204, July 2008. \n                    https:\/\/doi.org\/10.1109\/ISPDC.2008.65","DOI":"10.1109\/ISPDC.2008.65"},{"issue":"2","key":"16_CR21","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/MM.2016.25","volume":"36","author":"A Sodani","year":"2016","unstructured":"Sodani, A., et al.: Knights landing: second-generation intelxeon phi product. IEEE Micro 36(2), 34\u201346 (2016). \n                    https:\/\/doi.org\/10.1109\/MM.2016.25","journal-title":"IEEE Micro"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Stojanovic, S., Bojic, D., Bojovic, M., Valero, M., Milutinovic, V.: An overview of selected hybrid and reconfigurable architectures. In: 2012 IEEE International Conference on Industrial Technology (ICIT), pp. 444\u2013449, March 2012. \n                    https:\/\/doi.org\/10.1109\/ICIT.2012.6209978","DOI":"10.1109\/ICIT.2012.6209978"},{"key":"16_CR23","doi-asserted-by":"publisher","unstructured":"Tang, Y., Chowdhury, R.A., Kuszmaul, B.C., Luk, C.K., Leiserson, C.E.: The pochoir stencil compiler. In: ACM Symposium on Parallelism in Algorithms and Architectures, SPAA 2011, pp. 117\u2013128. ACM, New York (2011). \n                    https:\/\/doi.org\/10.1145\/1989493.1989508\n                    \n                  . \n                    http:\/\/doi.acm.org\/10.1145\/1989493.1989508","DOI":"10.1145\/1989493.1989508"},{"issue":"1","key":"16_CR24","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1177\/1094342017718068","volume":"32","author":"B Videau","year":"2018","unstructured":"Videau, B., et al.: Boast: a meta programming framework to produce portable and efficient computing kernels for HPC applications. Int. J. High Perform. Comput. Appl. 32(1), 28\u201344 (2018). \n                    https:\/\/doi.org\/10.1177\/1094342017718068","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"16_CR25","doi-asserted-by":"publisher","unstructured":"Wahib, M., Maruyama, N.: Automated GPU kernel transformations in large-scale production stencil applications. In: Proceedings of the 24th International Symposium on High-Performance Parallel and Distributed Computing, HPDC 2015, pp. 259\u2013270. ACM, New York (2015). \n                    https:\/\/doi.org\/10.1145\/2749246.2749255\n                    \n                  . \n                    http:\/\/doi.acm.org\/10.1145\/2749246.2749255","DOI":"10.1145\/2749246.2749255"},{"key":"16_CR26","doi-asserted-by":"publisher","unstructured":"Zhao, B., Li, Z., Jannesari, A., Wolf, F., Wu, W.: Dependence-based code transformation for coarse-grained parallelism. In: Proceedings of the 2015 International Workshop on Code Optimisation for Multi and Many Cores, COSMIC 2015, pp. 1:1\u20131:10. ACM, New York (2015). \n                    https:\/\/doi.org\/10.1145\/2723772.2723777\n                    \n                  . \n                    http:\/\/doi.acm.org\/10.1145\/2723772.2723777","DOI":"10.1145\/2723772.2723777"}],"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_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,21]],"date-time":"2019-05-21T00:20:19Z","timestamp":1558398019000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-16205-4_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030162047","9783030162054"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-16205-4_16","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"}}]}}