{"id":"https://openalex.org/W2998709103","doi":"https://doi.org/10.1145/3365663","title":"Extracting SIMD Parallelism from Recursive Task-Parallel Programs","display_name":"Extracting SIMD Parallelism from Recursive Task-Parallel Programs","publication_year":2019,"publication_date":"2019-12-26","ids":{"openalex":"https://openalex.org/W2998709103","doi":"https://doi.org/10.1145/3365663","mag":"2998709103"},"language":"en","primary_location":{"id":"doi:10.1145/3365663","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3365663","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-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/A5058025888","display_name":"Bin Ren","orcid":"https://orcid.org/0000-0002-4116-5237"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bin Ren","raw_affiliation_strings":["William 8 Mary, Pacific Northwest National Laboratory"],"affiliations":[{"raw_affiliation_string":"William 8 Mary, Pacific Northwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033569223","display_name":"Shruthi Balakrishna","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shruthi Balakrishna","raw_affiliation_strings":["Purdue University"],"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043064742","display_name":"Youngjoon Jo","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Youngjoon Jo","raw_affiliation_strings":["Purdue University"],"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006650430","display_name":"Sriram Krishnamoorthy","orcid":"https://orcid.org/0000-0002-4682-1002"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sriram Krishnamoorthy","raw_affiliation_strings":["Pacific Northwest National Laboratory"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035990793","display_name":"Kunal Agrawal","orcid":"https://orcid.org/0000-0001-5882-6647"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunal Agrawal","raw_affiliation_strings":["Washington University in St. Louis"],"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075916086","display_name":"Milind Kulkarni","orcid":"https://orcid.org/0000-0001-6827-345X"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milind Kulkarni","raw_affiliation_strings":["Purdue University"],"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5058025888"],"corresponding_institution_ids":["https://openalex.org/I142606810"],"apc_list":null,"apc_paid":null,"fwci":0.2408,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52987216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"6","issue":"4","first_page":"1","last_page":"37"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9977999925613403,"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":0.8561651110649109},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8226569890975952},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.7618635892868042},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.6687495112419128},{"id":"https://openalex.org/keywords/task-parallelism","display_name":"Task parallelism","score":0.6428627967834473},{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.6423702239990234},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6375622749328613},{"id":"https://openalex.org/keywords/instruction-level-parallelism","display_name":"Instruction-level parallelism","score":0.5310264825820923},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.44777911901474},{"id":"https://openalex.org/keywords/parallel-processing","display_name":"Parallel processing","score":0.4350164830684662},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42303434014320374},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.4221665859222412},{"id":"https://openalex.org/keywords/parallel-programming-model","display_name":"Parallel programming model","score":0.4140864908695221},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4131208062171936},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.28462979197502136},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15181833505630493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8561651110649109},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8226569890975952},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.7618635892868042},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.6687495112419128},{"id":"https://openalex.org/C42992933","wikidata":"https://www.wikidata.org/wiki/Q691169","display_name":"Task parallelism","level":3,"score":0.6428627967834473},{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.6423702239990234},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6375622749328613},{"id":"https://openalex.org/C140763907","wikidata":"https://www.wikidata.org/wiki/Q2714055","display_name":"Instruction-level parallelism","level":3,"score":0.5310264825820923},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.44777911901474},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.4350164830684662},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42303434014320374},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.4221665859222412},{"id":"https://openalex.org/C137364921","wikidata":"https://www.wikidata.org/wiki/Q27929394","display_name":"Parallel programming model","level":3,"score":0.4140864908695221},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4131208062171936},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.28462979197502136},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15181833505630493},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3365663","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3365663","pdf_url":null,"source":{"id":"https://openalex.org/S2483380313","display_name":"ACM Transactions on Parallel Computing","issn_l":"2329-4949","issn":["2329-4949","2329-4957"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Parallel Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G3859105124","display_name":null,"funder_award_id":"CCF-1150013 (CAREER), CCF-1439126, CCF-1150036 (CAREER), and CCF-1439062","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1536852470","https://openalex.org/W1595310945","https://openalex.org/W1968057111","https://openalex.org/W1972090741","https://openalex.org/W1984222112","https://openalex.org/W1985074935","https://openalex.org/W1991709203","https://openalex.org/W1996541179","https://openalex.org/W2002209075","https://openalex.org/W2013246077","https://openalex.org/W2015288732","https://openalex.org/W2038276550","https://openalex.org/W2040281526","https://openalex.org/W2043106819","https://openalex.org/W2057363235","https://openalex.org/W2057623365","https://openalex.org/W2061989483","https://openalex.org/W2063765234","https://openalex.org/W2067313328","https://openalex.org/W2089672258","https://openalex.org/W2095407217","https://openalex.org/W2102307937","https://openalex.org/W2104861744","https://openalex.org/W2111194344","https://openalex.org/W2113643095","https://openalex.org/W2118031182","https://openalex.org/W2120497510","https://openalex.org/W2125338937","https://openalex.org/W2131296084","https://openalex.org/W2132598270","https://openalex.org/W2132774949","https://openalex.org/W2136952590","https://openalex.org/W2142761843","https://openalex.org/W2151224499","https://openalex.org/W2152812278","https://openalex.org/W2159523287","https://openalex.org/W2162726111","https://openalex.org/W2172013743","https://openalex.org/W2240152262","https://openalex.org/W2260499435","https://openalex.org/W2464141386","https://openalex.org/W2478667927","https://openalex.org/W2523448744","https://openalex.org/W2581189719","https://openalex.org/W2768826296","https://openalex.org/W2883965613","https://openalex.org/W3005224176","https://openalex.org/W3010528205","https://openalex.org/W3032842880","https://openalex.org/W3213145857","https://openalex.org/W4214596219","https://openalex.org/W4231595696","https://openalex.org/W4253999189","https://openalex.org/W4254519017","https://openalex.org/W6661242115"],"related_works":["https://openalex.org/W4240606930","https://openalex.org/W2526302199","https://openalex.org/W2003935582","https://openalex.org/W2950520577","https://openalex.org/W3007272028","https://openalex.org/W2040503315","https://openalex.org/W1501159154","https://openalex.org/W2009213655","https://openalex.org/W2468095077","https://openalex.org/W2378666660"],"abstract_inverted_index":{"The":[0],"pursuit":[1],"of":[2,10,53,73,92,107,162],"computational":[3],"efficiency":[4],"has":[5],"led":[6],"to":[7,15,29,65],"the":[8,51,79],"proliferation":[9],"throughput-oriented":[11,66],"hardware,":[12],"from":[13],"GPUs":[14],"increasingly":[16],"wide":[17],"vector":[18,108,122,133],"units":[19],"on":[20,95,128],"commodity":[21,96],"processors":[22],"and":[23,125],"accelerators.":[24],"This":[25,68],"hardware":[26],"is":[27],"designed":[28],"execute":[30],"data-parallel":[31],"computations":[32],"in":[33,83,150],"a":[34,71,158],"vectorized":[35],"manner":[36],"efficiently.":[37],"However,":[38],"many":[39],"algorithms":[40,60],"are":[41,61,155],"more":[42],"naturally":[43],"expressed":[44],"as":[45,135,137],"divide-and-conquer,":[46],"recursive,":[47,84],"task-parallel":[48,85,93,116],"computations.":[49],"In":[50],"absence":[52],"data":[54,80],"parallelism,":[55],"it":[56],"seems":[57],"that":[58,77,103],"such":[59],"not":[62],"well":[63,136],"suited":[64],"architectures.":[67],"article":[69],"presents":[70],"set":[72],"novel":[74],"code":[75],"transformations":[76,88],"expose":[78],"parallelism":[81],"latent":[82],"programs.":[86,163],"These":[87],"facilitate":[89],"straightforward":[90],"vectorization":[91,153],"programs":[94],"hardware.":[97],"We":[98,143],"also":[99],"present":[100],"scheduling":[101],"policies":[102],"maintain":[104],"high":[105],"utilization":[106,124],"resources":[109],"while":[110],"limiting":[111],"space":[112],"usage.":[113],"Across":[114],"several":[115],"benchmarks,":[117],"we":[118],"demonstrate":[119],"both":[120],"efficient":[121],"resource":[123],"substantial":[126],"speedup":[127],"chips":[129],"using":[130,139],"Intel\u2019s":[131,140],"SSE4.2":[132],"units,":[134],"accelerators":[138],"AVX512":[141],"units.":[142],"then":[144],"show":[145],"through":[146],"rigorous":[147],"sampling":[148],"that,":[149],"practice,":[151],"our":[152],"techniques":[154],"effective":[156],"for":[157],"much":[159],"larger":[160],"class":[161]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}