{"id":"https://openalex.org/W2983655274","doi":"https://doi.org/10.1145/3295500.3356162","title":"A versatile software systolic execution model for GPU memory-bound kernels","display_name":"A versatile software systolic execution model for GPU memory-bound kernels","publication_year":2019,"publication_date":"2019-11-07","ids":{"openalex":"https://openalex.org/W2983655274","doi":"https://doi.org/10.1145/3295500.3356162","mag":"2983655274"},"language":"en","primary_location":{"id":"doi:10.1145/3295500.3356162","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3295500.3356162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.06154","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100338479","display_name":"Peng Chen","orcid":"https://orcid.org/0000-0003-1244-3151"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Peng Chen","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002208999","display_name":"Mohamed Wahib","orcid":"https://orcid.org/0000-0002-7165-2095"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mohamed Wahib","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036711476","display_name":"Shinichiro Takizawa","orcid":"https://orcid.org/0000-0001-8028-7328"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinichiro Takizawa","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082259794","display_name":"Ryousei Takano","orcid":"https://orcid.org/0000-0002-4341-3505"},"institutions":[{"id":"https://openalex.org/I73613424","display_name":"National Institute of Advanced Industrial Science and Technology","ror":"https://ror.org/01703db54","country_code":"JP","type":"government","lineage":["https://openalex.org/I73613424"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryousei Takano","raw_affiliation_strings":["National Institute of Advanced Industrial Science and Technology"],"affiliations":[{"raw_affiliation_string":"National Institute of Advanced Industrial Science and Technology","institution_ids":["https://openalex.org/I73613424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100634486","display_name":"Satoshi Matsuoka","orcid":"https://orcid.org/0000-0003-1910-8532"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Matsuoka","raw_affiliation_strings":["RIKEN Center for Computational, Science, Hyogo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational, Science, Hyogo, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100338479"],"corresponding_institution_ids":["https://openalex.org/I73613424"],"apc_list":null,"apc_paid":null,"fwci":2.706,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.90308595,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"81"},"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":0.9994000196456909,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8483853340148926},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8130277395248413},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4930567443370819},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.42829763889312744},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32218724489212036},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25796765089035034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8483853340148926},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8130277395248413},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4930567443370819},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.42829763889312744},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32218724489212036},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25796765089035034}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3295500.3356162","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3295500.3356162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.06154","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.06154","pdf_url":"https://arxiv.org/pdf/1907.06154","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.06154","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.06154","pdf_url":"https://arxiv.org/pdf/1907.06154","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W88130292","https://openalex.org/W192356505","https://openalex.org/W1492882524","https://openalex.org/W1495278797","https://openalex.org/W1506424797","https://openalex.org/W1536852470","https://openalex.org/W1565435192","https://openalex.org/W1575104486","https://openalex.org/W1598202309","https://openalex.org/W1662114873","https://openalex.org/W1667652561","https://openalex.org/W1820993528","https://openalex.org/W1963965124","https://openalex.org/W1994622644","https://openalex.org/W1995642220","https://openalex.org/W1999448593","https://openalex.org/W2003798513","https://openalex.org/W2017369466","https://openalex.org/W2039378765","https://openalex.org/W2039417226","https://openalex.org/W2051495459","https://openalex.org/W2072118886","https://openalex.org/W2074367725","https://openalex.org/W2077143534","https://openalex.org/W2077442019","https://openalex.org/W2092863163","https://openalex.org/W2093319010","https://openalex.org/W2093843662","https://openalex.org/W2099758780","https://openalex.org/W2110195531","https://openalex.org/W2110656410","https://openalex.org/W2113190809","https://openalex.org/W2122677725","https://openalex.org/W2129170915","https://openalex.org/W2131359566","https://openalex.org/W2160406723","https://openalex.org/W2176106924","https://openalex.org/W2183420951","https://openalex.org/W2415973476","https://openalex.org/W2471164860","https://openalex.org/W2493822152","https://openalex.org/W2580538010","https://openalex.org/W2606722458","https://openalex.org/W2620106252","https://openalex.org/W2785874054","https://openalex.org/W2796649226","https://openalex.org/W2889543163","https://openalex.org/W2891890103","https://openalex.org/W2898630465","https://openalex.org/W2902566644","https://openalex.org/W2903775786","https://openalex.org/W2913533776","https://openalex.org/W2920318637","https://openalex.org/W2920798074","https://openalex.org/W2953212265","https://openalex.org/W2953993523","https://openalex.org/W2987684178","https://openalex.org/W3099448935","https://openalex.org/W3100822741","https://openalex.org/W3149084271","https://openalex.org/W3152295672","https://openalex.org/W4211076202","https://openalex.org/W4242314113","https://openalex.org/W4244305136","https://openalex.org/W4249464734","https://openalex.org/W4285719527","https://openalex.org/W4302296459","https://openalex.org/W4399166738"],"related_works":["https://openalex.org/W2005148983","https://openalex.org/W2012954338","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W3189307731","https://openalex.org/W1428699136","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1998560227","https://openalex.org/W2149263892"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,22,42,64],"versatile":[4],"high-performance":[5],"execution":[6],"model,":[7],"inspired":[8],"by":[9,29],"systolic":[10,23],"arrays,":[11],"for":[12,33,63],"memory-bound":[13],"regular":[14],"kernels":[15,69,78],"running":[16],"on":[17,103,125,132],"CUDA-enabled":[18],"GPUs.":[19,136],"We":[20,36,53],"formulate":[21],"model":[24,51,62],"that":[25,70],"shifts":[26],"partial":[27],"sums":[28],"CUDA":[30],"warp":[31],"primitives":[32],"the":[34,49,55,60,88,104],"computation.":[35],"also":[37,76],"employ":[38],"register":[39],"files":[40],"as":[41],"cache":[43],"resource":[44],"in":[45,73,81],"order":[46],"to":[47],"operate":[48],"entire":[50],"efficiently.":[52],"demonstrate":[54],"effectiveness":[56],"and":[57,75,99,111,120,134],"versatility":[58],"of":[59,67,116],"proposed":[61],"wide":[65],"variety":[66],"stencil":[68,92],"appear":[71],"commonly":[72],"HPC,":[74],"convolution":[77,115],"(increasingly":[79],"important":[80],"deep":[82],"learning":[83],"workloads).":[84],"Our":[85],"algorithm":[86,123],"outperforms":[87],"top":[89],"reported":[90],"state-of-the-art":[91],"implementations,":[93],"including":[94],"implementations":[95],"with":[96],"sophisticated":[97],"temporal":[98],"spatial":[100],"blocking":[101],"techniques,":[102],"two":[105],"latest":[106],"Nvidia":[107],"architectures:":[108],"Tesla":[109],"V100":[110,133],"P100.":[112],"For":[113],"2D":[114],"general":[117],"filter":[118],"sizes":[119],"shapes,":[121],"our":[122],"is":[124],"average":[126],"2.5\u00d7":[127],"faster":[128],"than":[129],"Nvidia's":[130],"NPP":[131],"P100":[135]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}