{"id":"https://openalex.org/W2887161653","doi":"https://doi.org/10.1145/3225058.3225100","title":"Vectorized Parallel Sparse Matrix-Vector Multiplication in PETSc Using AVX-512","display_name":"Vectorized Parallel Sparse Matrix-Vector Multiplication in PETSc Using AVX-512","publication_year":2018,"publication_date":"2018-08-08","ids":{"openalex":"https://openalex.org/W2887161653","doi":"https://doi.org/10.1145/3225058.3225100","mag":"2887161653"},"language":"en","primary_location":{"id":"doi:10.1145/3225058.3225100","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100430320","display_name":"Hong Zhang","orcid":"https://orcid.org/0000-0002-8129-7728"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hong Zhang","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046201392","display_name":"Richard T. Mills","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard T. Mills","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030188839","display_name":"Karl Rupp","orcid":"https://orcid.org/0000-0002-0198-3999"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Karl Rupp","raw_affiliation_strings":["Institute for Microelectronics, TU Wien, Wien, Austria"],"affiliations":[{"raw_affiliation_string":"Institute for Microelectronics, TU Wien, Wien, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020400213","display_name":"Barry Smith","orcid":"https://orcid.org/0000-0001-5955-8111"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Barry F. Smith","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL, USA"],"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Lemont, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100430320"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":3.5346,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.9354681,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994999766349792,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8333227634429932},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.8279512524604797},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8093125820159912},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.6982966661453247},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.6343772411346436},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5939692854881287},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5667752623558044},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5422213673591614},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.46660277247428894},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.4621577560901642},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4612288773059845},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.43920090794563293},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.10902947187423706},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09529584646224976}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8333227634429932},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.8279512524604797},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8093125820159912},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.6982966661453247},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.6343772411346436},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5939692854881287},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5667752623558044},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5422213673591614},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.46660277247428894},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.4621577560901642},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4612288773059845},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.43920090794563293},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.10902947187423706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09529584646224976},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3225058.3225100","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3225058.3225100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 47th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W90568776","https://openalex.org/W842872497","https://openalex.org/W1207115811","https://openalex.org/W1588915715","https://openalex.org/W1776498962","https://openalex.org/W1902819800","https://openalex.org/W1975116854","https://openalex.org/W1987840949","https://openalex.org/W1995649289","https://openalex.org/W1996274599","https://openalex.org/W2006640177","https://openalex.org/W2052993554","https://openalex.org/W2057980100","https://openalex.org/W2101511474","https://openalex.org/W2103877122","https://openalex.org/W2114977680","https://openalex.org/W2128539477","https://openalex.org/W2128853364","https://openalex.org/W2130289795","https://openalex.org/W2142356482","https://openalex.org/W2148930331","https://openalex.org/W2162630236","https://openalex.org/W2164904521","https://openalex.org/W2518567779","https://openalex.org/W2529487057","https://openalex.org/W2561720083","https://openalex.org/W3099744258","https://openalex.org/W4243261006"],"related_works":["https://openalex.org/W1981557297","https://openalex.org/W2952807630","https://openalex.org/W4300876969","https://openalex.org/W2149629847","https://openalex.org/W3202552726","https://openalex.org/W2182219686","https://openalex.org/W1776498962","https://openalex.org/W2887161653","https://openalex.org/W2791204867","https://openalex.org/W2145018926"],"abstract_inverted_index":{"Emerging":[0],"many-core":[1],"CPU":[2,63,80],"architectures":[3,30,64],"with":[4],"high":[5],"degrees":[6],"of":[7,44,139],"single-instruction,":[8],"multiple":[9],"data":[10],"(SIMD)":[11],"parallelism":[12],"promise":[13],"to":[14,34,102,143],"enable":[15],"increasingly":[16],"ambitious":[17],"simulations":[18,151],"based":[19,119],"on":[20,120],"partial":[21],"differential":[22],"equations":[23],"(PDEs)":[24],"via":[25],"extreme-scale":[26],"computing.":[27],"However,":[28],"such":[29],"present":[31,113],"several":[32],"challenges":[33],"their":[35],"efficient":[36,42,115],"use.":[37],"Here,":[38],"we":[39,126,135],"explore":[40],"the":[41,52,70,130,137],"implementation":[43],"sparse":[45,94],"matrix-vector":[46],"(SpMV)":[47],"multiplications---a":[48],"critical":[49],"kernel":[50],"for":[51],"workhorse":[53],"iterative":[54,146],"linear":[55],"solvers":[56,147],"used":[57],"in":[58,129,148,152],"most":[59],"PDE-based":[60,150],"simulations---on":[61],"recent":[62],"from":[65],"Intel":[66,74],"as":[67,69],"well":[68],"second-generation":[71],"Knights":[72],"Landing":[73],"Xeon":[75],"Phi,":[76],"which":[77,98,125],"features":[78],"many":[79],"cores,":[81],"wide":[82,104],"SIMD":[83,105],"lanes,":[84],"and":[85,112],"on-package":[86],"high-bandwidth":[87],"memory.":[88],"Traditional":[89],"SpMV":[90,117],"algorithms":[91],"use":[92],"compressed":[93],"row":[95],"storage":[96],"format,":[97],"is":[99],"a":[100,121],"hindrance":[101],"exploiting":[103],"lanes.":[106],"We":[107],"study":[108],"alternative":[109],"matrix":[110],"formats":[111],"an":[114],"optimized":[116],"kernel,":[118],"sliced":[122],"ELLPACK":[123],"representation,":[124],"have":[127],"implemented":[128],"PETSc":[131],"library.":[132],"In":[133],"addition,":[134],"demonstrate":[136],"benefit":[138],"using":[140],"this":[141],"representation":[142],"accelerate":[144],"preconditioned":[145],"realistic":[149],"parallel.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}