{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:33:06Z","timestamp":1750221186496,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,2,24]],"date-time":"2018-02-24T00:00:00Z","timestamp":1519430400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,2,24]]},"DOI":"10.1145\/3178433.3178434","type":"proceedings-article","created":{"date-parts":[[2018,2,16]],"date-time":"2018-02-16T16:01:58Z","timestamp":1518796918000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Small SIMD Matrices for CERN High Throughput Computing"],"prefix":"10.1145","author":[{"given":"Florian","family":"Lemaitre","sequence":"first","affiliation":[{"name":"CERN, Geneva, Switzerland, Sorbonne Universit\u00e9, CNRS, Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Benjamin","family":"Couturier","sequence":"additional","affiliation":[{"name":"CERN, Geneva, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lionel","family":"Lacassagne","sequence":"additional","affiliation":[{"name":"Sorbonne Universit\u00e9, CNRS, Paris, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,2,24]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Morgan Kaufmann","author":"Allen R.","year":"2002","unstructured":"Allen , R. , and Kennedy , K. , Eds . Optimizing compilers for modern architectures: a dependence-based approach . Morgan Kaufmann , 2002 , ch. 8, 9, 11. Allen, R., and Kennedy, K., Eds. Optimizing compilers for modern architectures: a dependence-based approach. Morgan Kaufmann, 2002, ch. 8, 9, 11."},{"key":"e_1_3_2_1_2_1","first-page":"3","article-title":"LHCb Kalman Filter cross architecture studies","volume":"898","author":"C\u00e9mpora P\u00e9rez D. H","year":"2017","unstructured":"C\u00e9mpora P\u00e9rez , D. H . LHCb Kalman Filter cross architecture studies . Journal of Physics: Conference Series 898 , 3 ( 2017 ), 032052. C\u00e9mpora P\u00e9rez, D. H. LHCb Kalman Filter cross architecture studies. Journal of Physics: Conference Series 898, 3 (2017), 032052.","journal-title":"Journal of Physics: Conference Series"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-29778-1_19"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/898\/4\/042051"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC.2014.30"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2568058.2568063"},{"key":"e_1_3_2_1_7_1","volume-title":"AMD and VIA CPUs, 2016","author":"Fog A.","year":"2016","unstructured":"Fog , A. Instruction tables : Lists of instruction latencies, throughputs and micro-operation breakdowns for Intel , AMD and VIA CPUs, 2016 . accessed version: 2016 -01-09. Fog, A. Instruction tables: Lists of instruction latencies, throughputs and micro-operation breakdowns for Intel, AMD and VIA CPUs, 2016. accessed version: 2016-01-09."},{"key":"e_1_3_2_1_8_1","volume-title":"http:\/\/agner.org\/optimize\/vectorclass.zip","author":"Fog A.","year":"2017","unstructured":"Fog , A. C++ vector class library. http:\/\/agner.org\/optimize\/vectorclass.zip , 2017 . accessed version: 2017-07-27. Fog, A. C++ vector class library. http:\/\/agner.org\/optimize\/vectorclass.zip, 2017. accessed version: 2017-07-27."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/0168-9002(87)90887-4"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2007.10.001"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898718027","volume-title":"Accuracy and stability of numerical algorithms","author":"Higham N. J.","year":"2002","unstructured":"Higham , N. J. Accuracy and stability of numerical algorithms . SIAM , 2002 . Higham, N. J. Accuracy and stability of numerical algorithms. SIAM, 2002."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/wics.18"},{"key":"e_1_3_2_1_13_1","unstructured":"JINJA2. Python template engine. http:\/\/jinja.pocoo.org\/.  JINJA2. Python template engine. http:\/\/jinja.pocoo.org\/."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3026937.3026939"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1002\/spe.1149"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2568058.2568067"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2017.06.005"},{"key":"e_1_3_2_1_18_1","volume-title":"Header-only zero-overhead c++ wrapper for simd intrinsics of multiple instruction sets. https:\/\/github.com\/p12tic\/libsimdpp","author":"Libsimdpp","year":"2017","unstructured":"Libsimdpp . Header-only zero-overhead c++ wrapper for simd intrinsics of multiple instruction sets. https:\/\/github.com\/p12tic\/libsimdpp , 2017 . commit: 7c2b867. Libsimdpp. Header-only zero-overhead c++ wrapper for simd intrinsics of multiple instruction sets. https:\/\/github.com\/p12tic\/libsimdpp, 2017. commit: 7c2b867."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2847598.2847626"},{"key":"e_1_3_2_1_20_1","unstructured":"MKL. Intel(R) math kernel library. https:\/\/software.intel.com\/en-us\/intel-mkl.  MKL. Intel(R) math kernel library. https:\/\/software.intel.com\/en-us\/intel-mkl."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/FMPC.1990.89438"},{"key":"e_1_3_2_1_22_1","first-page":"1","volume-title":"Innovative Parallel Computing (InPar)","author":"Pharr M.","year":"2012","unstructured":"Pharr , M. , and Mark , W. R . ispc: A SPMD compiler for high-performance CPU programming . In Innovative Parallel Computing (InPar) , 2012 (2012), IEEE , pp. 1 -- 13 . Pharr, M., and Mark, W. R. ispc: A SPMD compiler for high-performance CPU programming. In Innovative Parallel Computing (InPar), 2012 (2012), IEEE, pp. 1--13."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/243439.243481"}],"event":{"name":"PPoPP '18: 23nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"],"location":"Vienna Austria","acronym":"PPoPP '18"},"container-title":["Proceedings of the 2018 4th Workshop on Programming Models for SIMD\/Vector Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3178433.3178434","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3178433.3178434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:39:07Z","timestamp":1750210747000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3178433.3178434"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,24]]},"references-count":23,"alternative-id":["10.1145\/3178433.3178434","10.1145\/3178433"],"URL":"https:\/\/doi.org\/10.1145\/3178433.3178434","relation":{},"subject":[],"published":{"date-parts":[[2018,2,24]]},"assertion":[{"value":"2018-02-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}