{"id":"https://openalex.org/W2074140323","doi":"https://doi.org/10.1145/1687399.1687501","title":"Taming irregular EDA applications on GPUs","display_name":"Taming irregular EDA applications on GPUs","publication_year":2009,"publication_date":"2009-11-02","ids":{"openalex":"https://openalex.org/W2074140323","doi":"https://doi.org/10.1145/1687399.1687501","mag":"2074140323"},"language":"en","primary_location":{"id":"doi:10.1145/1687399.1687501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1687399.1687501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 International Conference on Computer-Aided Design","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/A5059155953","display_name":"Yangdong Deng","orcid":"https://orcid.org/0000-0002-8257-693X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yangdong (Steve) Deng","raw_affiliation_strings":["Tsinghua University, Beijing, China","Institute of Microelectronics, Tsinghua University, Beijing, 100084, China, 86-10-62771733"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute of Microelectronics, Tsinghua University, Beijing, 100084, China, 86-10-62771733","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059691312","display_name":"Bo David Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo David Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China","Institute of Microelectronics, Tsinghua University, Beijing, 100084, China, 86-10-62784684"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute of Microelectronics, Tsinghua University, Beijing, 100084, China, 86-10-62784684","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050543806","display_name":"Shuai Mu","orcid":"https://orcid.org/0000-0001-8244-2109"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Mu","raw_affiliation_strings":["Tsinghua University, Beijing, China","Institute of Microelectronics, Tsinghua University, Beijing, 100084, China, 86-10-62784684"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Institute of Microelectronics, Tsinghua University, Beijing, 100084, China, 86-10-62784684","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.4604,"has_fulltext":false,"cited_by_count":91,"citation_normalized_percentile":{"value":0.98347639,"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":"539","last_page":"546"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.9987000226974487,"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":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8566869497299194},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8471922874450684},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.7168049812316895},{"id":"https://openalex.org/keywords/graph-traversal","display_name":"Graph traversal","score":0.7009350061416626},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.653290867805481},{"id":"https://openalex.org/keywords/tree-traversal","display_name":"Tree traversal","score":0.6523051857948303},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5409039855003357},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5139052867889404},{"id":"https://openalex.org/keywords/electronic-design-automation","display_name":"Electronic design automation","score":0.4454355239868164},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44006478786468506},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.42666590213775635},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.35820046067237854},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.29177361726760864},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24782970547676086},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.12397730350494385},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09161579608917236},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.08464452624320984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8566869497299194},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8471922874450684},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.7168049812316895},{"id":"https://openalex.org/C96333769","wikidata":"https://www.wikidata.org/wiki/Q907955","display_name":"Graph traversal","level":3,"score":0.7009350061416626},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.653290867805481},{"id":"https://openalex.org/C140745168","wikidata":"https://www.wikidata.org/wiki/Q1210082","display_name":"Tree traversal","level":2,"score":0.6523051857948303},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5409039855003357},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5139052867889404},{"id":"https://openalex.org/C64260653","wikidata":"https://www.wikidata.org/wiki/Q1194864","display_name":"Electronic design automation","level":2,"score":0.4454355239868164},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44006478786468506},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.42666590213775635},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.35820046067237854},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29177361726760864},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24782970547676086},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.12397730350494385},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09161579608917236},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.08464452624320984},{"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1687399.1687501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1687399.1687501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 International Conference on Computer-Aided Design","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1504291959","https://openalex.org/W1506342804","https://openalex.org/W1520511539","https://openalex.org/W1525873409","https://openalex.org/W1967321130","https://openalex.org/W1975338463","https://openalex.org/W1984954427","https://openalex.org/W1994061133","https://openalex.org/W2006447899","https://openalex.org/W2035080386","https://openalex.org/W2045044333","https://openalex.org/W2048796234","https://openalex.org/W2107793705","https://openalex.org/W2110561313","https://openalex.org/W2112708371","https://openalex.org/W2124007994","https://openalex.org/W2128131218","https://openalex.org/W2143006079","https://openalex.org/W2163961680","https://openalex.org/W2167078995","https://openalex.org/W2258419499","https://openalex.org/W2752885492","https://openalex.org/W3145128584","https://openalex.org/W4235342714","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2727953781","https://openalex.org/W2755264124","https://openalex.org/W3176814699","https://openalex.org/W2952476118","https://openalex.org/W2953648974","https://openalex.org/W2120610962","https://openalex.org/W2074140323","https://openalex.org/W1508286210","https://openalex.org/W1501847821","https://openalex.org/W2105812312"],"abstract_inverted_index":{"Recently":[0],"general":[1],"purpose":[2],"computing":[3,70,147,158],"on":[4,136],"graphic":[5],"processing":[6],"units":[7],"(GPUs)":[8],"is":[9,21],"rising":[10],"as":[11,43],"an":[12],"exciting":[13],"new":[14],"trend":[15],"in":[16],"high-performance":[17],"computing.":[18],"Thus":[19],"it":[20],"appealing":[22],"to":[23],"study":[24],"the":[25,104,143],"potential":[26],"of":[27,83,98,101,145,160],"GPU":[28,55,63,137,146],"for":[29,53,65,129],"Electronic":[30],"Design":[31],"Automation":[32],"(EDA)":[33],"applications.":[34],"However,":[35],"EDA":[36,69,84],"generally":[37],"involves":[38],"irregular":[39,68],"data":[40],"structures":[41,159],"such":[42,108],"sparse":[44],"matrix":[45],"and":[46,76,94,114,132],"graph":[47,77],"operations,":[48],"which":[49],"pose":[50],"significant":[51],"challenges":[52],"efficient":[54],"implementations.":[56,138],"In":[57],"this":[58],"paper,":[59],"we":[60],"propose":[61],"highperformance":[62],"implementations":[64,89],"two":[66],"important":[67],"patterns,":[71],"Sparse-Matrix":[72],"Vector":[73],"Product":[74],"(SMVP)":[75],"traversal.":[78],"On":[79],"a":[80,96,109,125],"wide":[81],"range":[82],"problem":[85],"instances,":[86],"our":[87],"SMVP":[88,126],"outperform":[90],"all":[91],"published":[92],"work":[93],"achieve":[95],"speedup":[97,135],"one":[99],"order":[100],"magnitude":[102],"over":[103],"CPU":[105],"baseline.":[106],"Upon":[107],"basis,":[110],"both":[111],"timing":[112],"analysis":[113],"linear":[115],"system":[116],"solution":[117],"can":[118,148],"be":[119,149],"considerably":[120],"accelerated.":[121],"We":[122],"also":[123],"introduce":[124],"based":[127],"formulation":[128],"Breadth-First":[130],"Search":[131],"observe":[133],"considerable":[134],"Our":[139],"results":[140],"suggest":[141],"that":[142],"power":[144],"successfully":[150],"unleashed":[151],"through":[152],"designing":[153],"GPU-friendly":[154],"algorithms":[155],"and/or":[156],"re-organizing":[157],"current":[161],"algorithms.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":11}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
