{"id":"https://openalex.org/W2767134114","doi":"https://doi.org/10.1109/hpec.2017.8091057","title":"Sparse matrix assembly on the GPU through multiplication patterns","display_name":"Sparse matrix assembly on the GPU through multiplication patterns","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2767134114","doi":"https://doi.org/10.1109/hpec.2017.8091057","mag":"2767134114"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2017.8091057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2017.8091057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5070162106","display_name":"Rhaleb Zayer","orcid":"https://orcid.org/0000-0002-3452-6276"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Rhaleb Zayer","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014594342","display_name":"Markus Steinberger","orcid":"https://orcid.org/0000-0001-5977-8536"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Markus Steinberger","raw_affiliation_strings":["Graz University of Technology, Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Graz University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058028526","display_name":"Hans\u2010Peter Seidel","orcid":"https://orcid.org/0000-0002-1343-8613"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hans-Peter Seidel","raw_affiliation_strings":["Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"],"affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070162106"],"corresponding_institution_ids":["https://openalex.org/I4210109712"],"apc_list":null,"apc_paid":null,"fwci":0.6948,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.70895264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9966999888420105,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9965000152587891,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7995160222053528},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.7707124948501587},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.7293343544006348},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6820747256278992},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6819427609443665},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6390565633773804},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5764954090118408},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5437406897544861},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4881156384944916},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.47804147005081177},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47507017850875854},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.44831377267837524},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.43802422285079956},{"id":"https://openalex.org/keywords/matrix-representation","display_name":"Matrix representation","score":0.425129234790802},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.42080458998680115},{"id":"https://openalex.org/keywords/polygon-mesh","display_name":"Polygon mesh","score":0.4195401966571808},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.4163215160369873},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4132333993911743},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.41085994243621826},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2747238576412201},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.2237871289253235},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10363337397575378},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.09627151489257812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7995160222053528},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.7707124948501587},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7293343544006348},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6820747256278992},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6819427609443665},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6390565633773804},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5764954090118408},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5437406897544861},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4881156384944916},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.47804147005081177},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47507017850875854},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.44831377267837524},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.43802422285079956},{"id":"https://openalex.org/C103275481","wikidata":"https://www.wikidata.org/wiki/Q6787889","display_name":"Matrix representation","level":3,"score":0.425129234790802},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.42080458998680115},{"id":"https://openalex.org/C31487907","wikidata":"https://www.wikidata.org/wiki/Q1154597","display_name":"Polygon mesh","level":2,"score":0.4195401966571808},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.4163215160369873},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4132333993911743},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.41085994243621826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2747238576412201},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2237871289253235},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10363337397575378},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.09627151489257812},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","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/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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpec.2017.8091057","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2017.8091057","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:escidoc.org:escidoc:2530441","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0000-3B33-5","pdf_url":null,"source":{"id":"https://openalex.org/S7407052962","display_name":"Max Planck Digital Library","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W25664821","https://openalex.org/W114927495","https://openalex.org/W637574335","https://openalex.org/W784772322","https://openalex.org/W1492186218","https://openalex.org/W1520511539","https://openalex.org/W1551542124","https://openalex.org/W1575596969","https://openalex.org/W1967320651","https://openalex.org/W1967913012","https://openalex.org/W1973918431","https://openalex.org/W1978403277","https://openalex.org/W1978979183","https://openalex.org/W1980140364","https://openalex.org/W1980562919","https://openalex.org/W1981885118","https://openalex.org/W1985263109","https://openalex.org/W2004175401","https://openalex.org/W2007259720","https://openalex.org/W2009196736","https://openalex.org/W2019145340","https://openalex.org/W2021261510","https://openalex.org/W2024622349","https://openalex.org/W2038646072","https://openalex.org/W2040092451","https://openalex.org/W2061698080","https://openalex.org/W2077368913","https://openalex.org/W2089437293","https://openalex.org/W2099116730","https://openalex.org/W2105839944","https://openalex.org/W2112975980","https://openalex.org/W2133985755","https://openalex.org/W2136827072","https://openalex.org/W2140798163","https://openalex.org/W2152275551","https://openalex.org/W2168931017","https://openalex.org/W2260408452","https://openalex.org/W2316514014","https://openalex.org/W2320253350","https://openalex.org/W2973296080","https://openalex.org/W2998133163","https://openalex.org/W3099706321","https://openalex.org/W4240774490","https://openalex.org/W4401247571","https://openalex.org/W6604609893","https://openalex.org/W6656654805","https://openalex.org/W6767870318"],"related_works":["https://openalex.org/W4312354936","https://openalex.org/W4200117381","https://openalex.org/W2132428222","https://openalex.org/W2022842990","https://openalex.org/W2914086833","https://openalex.org/W2293771254","https://openalex.org/W4221142455","https://openalex.org/W3121828480","https://openalex.org/W2039875226","https://openalex.org/W2002443693"],"abstract_inverted_index":{"The":[0],"numerical":[1,28],"treatment":[2],"of":[3,62,107,126,136,157,189],"variational":[4],"problems":[5],"gives":[6],"rise":[7],"to":[8,161,167],"large":[9],"sparse":[10,97],"matrices,":[11],"which":[12,89,171],"are":[13,48],"typically":[14],"assembled":[15,109],"by":[16,27,59,75,134],"coalescing":[17],"elementary":[18],"contributions.":[19],"As":[20],"the":[21,30,92,103,108,146,155,168,182,187,194],"explicit":[22],"matrix":[23,110],"form":[24],"is":[25,73,172],"required":[26],"solvers,":[29],"assembly":[31,93,195],"step":[32],"can":[33,56,111,131],"be":[34,57,112,132,162],"a":[35,84,96],"potential":[36],"bottleneck,":[37],"especially":[38],"in":[39,179],"implicit":[40],"and":[41,119,178],"time":[42],"dependent":[43],"settings":[44],"where":[45],"considerable":[46],"updates":[47],"needed.":[49],"On":[50],"standard":[51],"HPC":[52],"platforms,":[53],"this":[54,80],"process":[55],"vectorized":[58],"taking":[60],"advantage":[61],"additional":[63],"mesh":[64,87,190],"querying":[65],"data":[66,158],"structures.":[67],"However,":[68],"on":[69,154,174,181,193],"graphics":[70],"hardware,":[71,177],"vectorization":[72],"inhibited":[74],"limited":[76],"memory":[77,147,191],"resources.":[78],"In":[79],"paper,":[81],"we":[82,185],"propose":[83],"lean":[85],"unstructured":[86],"representation,":[88,138],"allows":[90],"casting":[91],"problem":[94],"as":[95],"matrix-matrix":[98],"multiplication.":[99],"We":[100],"demonstrate":[101],"how":[102,121],"global":[104,165],"graph":[105],"connectivity":[106],"captured":[113],"through":[114],"basic":[115],"linear":[116],"algebra":[117],"operations":[118],"show":[120],"local":[122],"interactions":[123],"between":[124],"nodes/degrees":[125],"freedom":[127],"within":[128],"an":[129],"element":[130],"encoded":[133],"means":[135],"concise":[137],"action":[139],"maps.":[140],"These":[141],"ideas":[142],"not":[143],"only":[144],"reduce":[145],"storage":[148,166],"requirements":[149],"but":[150],"also":[151],"cut":[152],"down":[153],"bulk":[156],"that":[159],"needs":[160],"moved":[163],"from":[164],"compute":[169],"units,":[170],"crucial":[173],"parallel":[175],"computing":[176],"particular":[180],"GPU.":[183],"Furthermore,":[184],"analyze":[186],"effect":[188],"layout":[192],"performance.":[196]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}