{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T06:30:11Z","timestamp":1743057011311,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319751771"},{"type":"electronic","value":"9783319751788"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-75178-8_48","type":"book-chapter","created":{"date-parts":[[2018,2,7]],"date-time":"2018-02-07T07:12:27Z","timestamp":1517987547000},"page":"597-609","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Data Partitioning Strategies for Stencil Computations on NUMA Systems"],"prefix":"10.1007","author":[{"given":"Frank","family":"Feinbube","sequence":"first","affiliation":[]},{"given":"Max","family":"Plauth","sequence":"additional","affiliation":[]},{"given":"Marius","family":"Knaust","sequence":"additional","affiliation":[]},{"given":"Andreas","family":"Polze","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,2,8]]},"reference":[{"issue":"3","key":"48_CR1","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/71.86107","volume":"2","author":"SG Abraham","year":"1991","unstructured":"Abraham, S.G., Hudak, D.E.: Compile-time partitioning of iterative parallel loops to reduce cache coherency traffic. IEEE Trans. Parallel Distrib. Syst. 2(3), 318\u2013328 (1991)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"48_CR2","unstructured":"Datta, K.: Auto-tuning Stencil Codes for Cache-Based Multicore Platforms. Ph.D. thesis, University of California, Berkeley (2009)"},{"key":"48_CR3","unstructured":"DeFlumere, A.: Optimal partitioning for parallel matrix computation on a small number of abstract heterogeneous processors. Ph.D. thesis, University College Dublin (2014)"},{"key":"48_CR4","unstructured":"Dursun, H., Nomura, K.I., Wang, W., Kunaseth, M., Peng, L., Seymour, R., Kalia, R.K., Nakano, A., Vashishta, P.: In-core optimization of high-order stencil computations. In: PDPTA, pp. 533\u2013538 (2009)"},{"key":"48_CR5","doi-asserted-by":"crossref","unstructured":"Hagen, W., Plauth, M., Eberhardt, F., Polze, A.: PGASUS: a framework for C++ application development on NUMA architectures. In: 2016 Fourth International Symposium on Computing and Networking (CANDAR), pp. 368\u2013374. IEEE, Hiroshima, November 2016","DOI":"10.1109\/CANDAR.2016.0071"},{"key":"48_CR6","doi-asserted-by":"crossref","unstructured":"Henretty, T., Veras, R., Franchetti, F., Pouchet, L.N., Ramanujam, J., Sadayappan, P.: A stencil compiler for short-vector SIMD architectures. In: Proceedings of the 27th International ACM Conference on International Conference on Supercomputing, pp. 13\u201324. ACM (2013)","DOI":"10.1145\/2464996.2467268"},{"key":"48_CR7","unstructured":"Hewlett-Packard Development Company: Red Hat Linux NUMA Support for HP ProLiant Servers. Technical report. (2013). Accessed 1 Feb 2017"},{"key":"48_CR8","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1515\/crll.1846.30.51","volume":"30","author":"CGJ Jacobi","year":"1846","unstructured":"Jacobi, C.G.J.: \u00dcber ein leichtes Verfahren die in der Theorie der S\u00e4cularst\u00f6rungen vorkommenden Gleichungen numerisch aufzul\u00f6sen. Journal f\u00fcr die reine und angewandte Mathematik 30, 51\u201394 (1846)","journal-title":"Journal f\u00fcr die reine und angewandte Mathematik"},{"issue":"4598","key":"48_CR9","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1126\/science.220.4598.671","volume":"220","author":"S Kirkpatrick","year":"1983","unstructured":"Kirkpatrick, S., Vecchi, M.P., et al.: Optimization by simulated annealing. Science 220(4598), 671\u2013680 (1983)","journal-title":"Science"},{"key":"48_CR10","unstructured":"Knaust, M.: Partitioning 2D Data for Stencil Computations on NUMA Systems. Master\u2019s thesis, Hasso Plattner Institute, University of Potsdam (2016)"},{"key":"48_CR11","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: Proceedings of the 2010 ACM\/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201313. IEEE Computer Society (2010)","DOI":"10.1109\/SC.2010.2"},{"key":"48_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/978-3-642-19595-2_6","volume-title":"Languages and Compilers for Parallel Computing","author":"D Orozco","year":"2011","unstructured":"Orozco, D., Garcia, E., Gao, G.: Locality optimization of stencil applications using data dependency graphs. In: Cooper, K., Mellor-Crummey, J., Sarkar, V. (eds.) LCPC 2010. LNCS, vol. 6548, pp. 77\u201391. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-19595-2_6"},{"key":"48_CR13","doi-asserted-by":"crossref","unstructured":"Plauth, M., Hagen, W., Feinbube, F., Eberhardt, F., Feinbube, L., Polze, A.: Parallel implementation strategies for hierarchical non-uniform memory access systems by example of the scale-invariant feature transform algorithm. In: IEEE International Parallel and Distributed Processing Symposium Workshops, pp. 1351\u20131359. IEEE, Chicago, May 2016","DOI":"10.1109\/IPDPSW.2016.47"},{"issue":"7","key":"48_CR14","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1109\/TC.1987.1676980","volume":"100","author":"DA Reed","year":"1987","unstructured":"Reed, D.A., Adams, L.M., Patrick, M.L.: Stencils and problem partitionings: their influence on the performance of multiple processor systems. IEEE Trans. Comput. 100(7), 845\u2013858 (1987)","journal-title":"IEEE Trans. Comput."},{"key":"48_CR15","doi-asserted-by":"crossref","unstructured":"Roth, G., Mellor-crummey, J., Kennedy, K., Brickner, R.G.: Compiling stencils in high performance Fortran. In: Supercomputing 1997: Proceedings of the 1997 ACM\/IEEE conference on Supercomputing, pp. 1\u201320. ACM Press (1997)","DOI":"10.1145\/509593.509605"},{"key":"48_CR16","doi-asserted-by":"crossref","unstructured":"Shaheen, M., Strzodka, R.: NUMA aware iterative stencil computations on many-core systems. In: 2012 IEEE 26th International Parallel and Distributed Processing Symposium (IPDPS), pp. 461\u2013473. IEEE (2012)","DOI":"10.1109\/IPDPS.2012.50"},{"key":"48_CR17","unstructured":"Silicon Graphics International Corp: SGI UV 300H for SAP HANA (2015)"},{"key":"48_CR18","doi-asserted-by":"crossref","unstructured":"Strzodka, R., Shaheen, M., Pajak, D., Seidel, H.P.: Cache oblivious parallelograms in iterative stencil computations. In: Proceedings of the 24th ACM International Conference on Supercomputing, pp. 49\u201359. ACM (2010)","DOI":"10.1145\/1810085.1810096"},{"key":"48_CR19","doi-asserted-by":"crossref","unstructured":"Wellein, G., Hager, G., Zeiser, T., Wittmann, M., Fehske, H.: Efficient temporal blocking for stencil computations by multicore-aware wavefront parallelization. In: 33rd Annual IEEE International Computer Software and Applications Conference, COMPSAC 2009, vol. 1, pp. 579-586. IEEE (2009)","DOI":"10.1109\/COMPSAC.2009.82"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2017: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-75178-8_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T01:07:42Z","timestamp":1644282462000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-75178-8_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319751771","9783319751788"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-75178-8_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"8 February 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Santiago de Compostela","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/europar2017.usc.es","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}