{"id":"https://openalex.org/W2289880787","doi":"https://doi.org/10.1145/2854038.2854046","title":"Exploiting recent SIMD architectural advances for irregular applications","display_name":"Exploiting recent SIMD architectural advances for irregular applications","publication_year":2016,"publication_date":"2016-02-29","ids":{"openalex":"https://openalex.org/W2289880787","doi":"https://doi.org/10.1145/2854038.2854046","mag":"2289880787"},"language":"en","primary_location":{"id":"doi:10.1145/2854038.2854046","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2854038.2854046","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2854038.2854046?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2854038.2854046?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030481157","display_name":"Linchuan Chen","orcid":"https://orcid.org/0000-0002-8527-5841"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Linchuan Chen","raw_affiliation_strings":["Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070002691","display_name":"Peng Jiang","orcid":"https://orcid.org/0000-0001-7743-6062"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng Jiang","raw_affiliation_strings":["Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025342178","display_name":"Gagan Agrawal","orcid":"https://orcid.org/0000-0002-2923-5327"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gagan Agrawal","raw_affiliation_strings":["Ohio State University, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030481157"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":7.7114,"has_fulltext":true,"cited_by_count":41,"citation_normalized_percentile":{"value":0.97476349,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"47","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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":0.9998000264167786,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9976999759674072,"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/parallel-computing","display_name":"Parallel computing","score":0.8900303244590759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.885242223739624},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.854921817779541},{"id":"https://openalex.org/keywords/mimd","display_name":"MIMD","score":0.8507533073425293},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8091681003570557},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.5099507570266724},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4655874967575073},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.44881126284599304},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42298799753189087},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.41295963525772095},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22524350881576538}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8900303244590759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.885242223739624},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.854921817779541},{"id":"https://openalex.org/C21032095","wikidata":"https://www.wikidata.org/wiki/Q1149237","display_name":"MIMD","level":2,"score":0.8507533073425293},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8091681003570557},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.5099507570266724},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4655874967575073},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.44881126284599304},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42298799753189087},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.41295963525772095},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22524350881576538},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2854038.2854046","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2854038.2854046","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2854038.2854046?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2854038.2854046","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2854038.2854046","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2854038.2854046?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Symposium on Code Generation and Optimization","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8486538762","display_name":null,"funder_award_id":"CCF-1526386","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2289880787.pdf","grobid_xml":"https://content.openalex.org/works/W2289880787.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W1581657066","https://openalex.org/W1964730929","https://openalex.org/W1965830721","https://openalex.org/W1969970763","https://openalex.org/W1971343078","https://openalex.org/W1980140364","https://openalex.org/W1985291160","https://openalex.org/W1987840949","https://openalex.org/W1994609277","https://openalex.org/W1997162567","https://openalex.org/W2005838699","https://openalex.org/W2006962349","https://openalex.org/W2035080386","https://openalex.org/W2040281526","https://openalex.org/W2066636486","https://openalex.org/W2070232376","https://openalex.org/W2072680607","https://openalex.org/W2087479145","https://openalex.org/W2089672258","https://openalex.org/W2094333709","https://openalex.org/W2109473404","https://openalex.org/W2111784516","https://openalex.org/W2120385681","https://openalex.org/W2128539477","https://openalex.org/W2130426318","https://openalex.org/W2151764765","https://openalex.org/W2160484893","https://openalex.org/W2167927436","https://openalex.org/W2755088640","https://openalex.org/W4237819810","https://openalex.org/W4249140283","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1980986440","https://openalex.org/W3158884034","https://openalex.org/W2163078645","https://openalex.org/W4388314704","https://openalex.org/W2014030893","https://openalex.org/W1971361763","https://openalex.org/W2399578218","https://openalex.org/W2167983067","https://openalex.org/W156928674","https://openalex.org/W2125719717"],"abstract_inverted_index":{"A":[0],"broad":[1],"class":[2,55],"of":[3,27,32,56,73,200],"applications":[4,82],"involve":[5],"indirect":[6,84],"or":[7],"datadependent":[8],"memory":[9,85],"accesses":[10,86],"and":[11,39,113,121,134,167,190],"are":[12,45],"referred":[13],"to":[14,68,129,139,157,180,195,202,226],"as":[15,49,51,90],"irregular":[16,74,188],"applications.":[17,57,75],"Recent":[18],"developments":[19],"in":[20,137,171],"SIMD":[21,29,33,120,166],"architectures":[22],"\u2013":[23,44],"specifically,":[24],"the":[25,78,160],"emergence":[26],"wider":[28],"lanes,":[30],"combination":[31],"parallelism":[34],"with":[35,83,175],"many-core":[36],"MIMD":[37,122,168],"parallelism,":[38],"more":[40],"flexible":[41],"programming":[42],"APIs":[43],"providing":[46],"new":[47],"opportunities":[48],"well":[50],"challenges":[52],"for":[53],"this":[54,59],"In":[58],"paper,":[60],"we":[61,94],"propose":[62],"a":[63,206,219],"general":[64],"opti-":[65],"mization":[66],"methodology,":[67,98],"effectively":[69],"optimize":[70],"different":[71],"subclasses":[72],"Based":[76],"on":[77,187],"observation":[79],"that":[80],"all":[81],"can":[87],"be":[88],"viewed":[89],"sparse":[91,140],"matrix":[92,141,185],"computations,":[93],"design":[95],"an":[96,197],"optimization":[97,183],"which":[99],"includes":[100],"three":[101],"sub-steps:":[102],"1)":[103],"locality":[104],"enhancement":[105],"through":[106],"tiling,":[107],"2)":[108],"data":[109],"access":[110],"pattern":[111],"identification,":[112],"3)":[114],"write":[115],"conflict":[116],"removal":[117],"at":[118,205],"both":[119,165],"levels.":[123],"This":[124],"method":[125],"has":[126],"been":[127],"applied":[128],"unstructured":[130],"grids,":[131],"molecular":[132],"dynamics,":[133],"graph":[135,191],"applications,":[136],"addition":[138],"computations.":[142],"The":[143],"speedups":[144],"achieved":[145],"by":[146,224],"our":[147,176,214],"single":[148],"threaded":[149],"vectorized":[150],"code":[151,154],"over":[152],"serial":[153],"is":[155,178,193],"up":[156,179,201,225],"9.05,":[158],"whereas":[159],"overall":[161],"speedup":[162,199],"while":[163],"utilizing":[164],"(61":[169],"cores":[170],"Intel":[172],"Xeon":[173],"Phi)":[174],"approach":[177,215],"467.1.":[181],"Further":[182],"using":[184,213],"reordering":[186],"reductions":[189],"algorithms":[192],"able":[194],"achieve":[196],"incremental":[198],"1.69,":[203],"though":[204],"relatively":[207],"high":[208],"preprocessing":[209],"cost.":[210],"Moreover,":[211],"SpMM":[212],"outperforms":[216],"routines":[217],"from":[218],"highly":[220],"optimized":[221],"commercial":[222],"library":[223],"2.81x.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}