{"id":"https://openalex.org/W2792649368","doi":"https://doi.org/10.1145/3178433.3178434","title":"Small SIMD Matrices for CERN High Throughput Computing","display_name":"Small SIMD Matrices for CERN High Throughput Computing","publication_year":2018,"publication_date":"2018-02-16","ids":{"openalex":"https://openalex.org/W2792649368","doi":"https://doi.org/10.1145/3178433.3178434","mag":"2792649368"},"language":"en","primary_location":{"id":"doi:10.1145/3178433.3178434","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178433.3178434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 4th Workshop on Programming Models for SIMD/Vector Processing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01760260","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089652964","display_name":"F. Lema\u0131\u0302tre","orcid":"https://orcid.org/0000-0002-0908-3629"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I67311998","display_name":"European Organization for Nuclear Research","ror":"https://ror.org/01ggx4157","country_code":"CH","type":"facility","lineage":["https://openalex.org/I67311998"]}],"countries":["CH","FR"],"is_corresponding":false,"raw_author_name":"Florian Lemaitre","raw_affiliation_strings":["CERN, Geneva, Switzerland, Sorbonne Universit\u00e9, CNRS, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CERN, Geneva, Switzerland, Sorbonne Universit\u00e9, CNRS, Paris, France","institution_ids":["https://openalex.org/I67311998","https://openalex.org/I39804081","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011210827","display_name":"B. Couturier","orcid":"https://orcid.org/0000-0001-6749-1033"},"institutions":[{"id":"https://openalex.org/I67311998","display_name":"European Organization for Nuclear Research","ror":"https://ror.org/01ggx4157","country_code":"CH","type":"facility","lineage":["https://openalex.org/I67311998"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Benjamin Couturier","raw_affiliation_strings":["CERN, Geneva, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CERN, Geneva, Switzerland","institution_ids":["https://openalex.org/I67311998"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086965094","display_name":"Lionel Lacassagne","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lionel Lacassagne","raw_affiliation_strings":["Sorbonne Universit\u00e9, CNRS, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, CNRS, Paris, France","institution_ids":["https://openalex.org/I39804081","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3953,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.64402481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11044","display_name":"Particle Detector Development and Performance","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/3106","display_name":"Nuclear and High Energy Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7583383321762085},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7341749668121338},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.7251461744308472},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5798949003219604},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.569456160068512},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.5433909893035889},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5012922286987305},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.44959795475006104},{"id":"https://openalex.org/keywords/large-hadron-collider","display_name":"Large Hadron Collider","score":0.44717666506767273},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.44072970747947693},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4370661675930023},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32924026250839233},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.1526455283164978},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15150701999664307},{"id":"https://openalex.org/keywords/particle-physics","display_name":"Particle physics","score":0.11458256840705872},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.10786321759223938},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09643211960792542}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583383321762085},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7341749668121338},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.7251461744308472},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5798949003219604},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.569456160068512},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.5433909893035889},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5012922286987305},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.44959795475006104},{"id":"https://openalex.org/C87668248","wikidata":"https://www.wikidata.org/wiki/Q40605","display_name":"Large Hadron Collider","level":2,"score":0.44717666506767273},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.44072970747947693},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4370661675930023},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32924026250839233},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.1526455283164978},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15150701999664307},{"id":"https://openalex.org/C109214941","wikidata":"https://www.wikidata.org/wiki/Q18334","display_name":"Particle physics","level":1,"score":0.11458256840705872},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.10786321759223938},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09643211960792542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3178433.3178434","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178433.3178434","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 4th Workshop on Programming Models for SIMD/Vector Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01760260v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01760260","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WPMVP 2018 Workshop on Programming Models for SIMD/Vector Processing, Feb 2018, Vienna, Austria. ⟨10.1145/3178433.3178434⟩","raw_type":"Conference papers"},{"id":"pmh:oai:inspirehep.net:1670546","is_oa":false,"landing_page_url":"http://cds.cern.ch/record/2632924","pdf_url":null,"source":{"id":"https://openalex.org/S4306402195","display_name":"CERN Document Server (European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01760260v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01760260","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WPMVP 2018 Workshop on Programming Models for SIMD/Vector Processing, Feb 2018, Vienna, Austria. ⟨10.1145/3178433.3178434⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"score":0.8700000047683716,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1677691940","https://openalex.org/W1985895827","https://openalex.org/W2006682733","https://openalex.org/W2020804487","https://openalex.org/W2067635581","https://openalex.org/W2088427879","https://openalex.org/W2103892714","https://openalex.org/W2111529652","https://openalex.org/W2114090069","https://openalex.org/W2114929171","https://openalex.org/W2163000655","https://openalex.org/W2183754142","https://openalex.org/W2201290654","https://openalex.org/W2582708067","https://openalex.org/W2596968257","https://openalex.org/W2603212626","https://openalex.org/W2625458075","https://openalex.org/W3022909171","https://openalex.org/W4236293132","https://openalex.org/W4239569515","https://openalex.org/W6995434384"],"related_works":["https://openalex.org/W2213533160","https://openalex.org/W2120385681","https://openalex.org/W2085105049","https://openalex.org/W2056079253","https://openalex.org/W3203561460","https://openalex.org/W3009624197","https://openalex.org/W4251138667","https://openalex.org/W2682544458","https://openalex.org/W1969709731","https://openalex.org/W2929736795"],"abstract_inverted_index":{"System":[0],"tracking":[1],"is":[2,59,101],"an":[3],"old":[4],"problem":[5],"and":[6,29,51,63,66,82,107],"has":[7],"been":[8],"heavily":[9,67],"optimized":[10,68],"throughout":[11],"the":[12],"past.":[13],"However,":[14],"in":[15,24],"High":[16],"Energy":[17],"Physics,":[18],"many":[19],"small":[20,55],"systems":[21],"are":[22],"tracked":[23],"real-time":[25],"using":[26],"Kalman":[27,52,99],"filtering":[28],"no":[30],"implementation":[31],"satisfying":[32],"those":[33],"constraints":[34],"currently":[35],"exists.":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"present":[41],"a":[42,114],"code":[43],"generator":[44,58],"used":[45],"to":[46,61,93],"speed":[47],"up":[48],"Cholesky":[49,85],"Factorization":[50],"Filter":[53,100],"for":[54],"matrices.":[56],"The":[57,98],"easy":[60],"use":[62],"produces":[64],"portable":[65],"code.":[69],"We":[70],"focus":[71],"on":[72,113],"current":[73],"SIMD":[74],"architectures":[75],"(SSE,":[76],"AVX,":[77],"AVX512,":[78],"Neon,":[79],"SVE,":[80],"Altivec":[81],"VSX).":[83],"Our":[84],"factorization":[86],"outperforms":[87],"any":[88],"existing":[89,105],"libraries:":[90],"from":[91],"x3":[92],"x10":[94],"faster":[95,103],"than":[96,104],"MKL.":[97],"also":[102],"implementations,":[106],"achieves":[108],"4":[109],"\u00b7":[110],"109":[111],"iter/s":[112],"2x24C":[115],"Intel":[116],"Xeon.":[117]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}