{"id":"https://openalex.org/W4410321788","doi":"https://doi.org/10.1145/3725798.3725802","title":"ACTA: Automatic Configuration of the Tensor Memory Accelerator for High-End GPUs","display_name":"ACTA: Automatic Configuration of the Tensor Memory Accelerator for High-End GPUs","publication_year":2025,"publication_date":"2025-03-01","ids":{"openalex":"https://openalex.org/W4410321788","doi":"https://doi.org/10.1145/3725798.3725802"},"language":"en","primary_location":{"id":"doi:10.1145/3725798.3725802","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725798.3725802","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725798.3725802","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3725798.3725802","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117528024","display_name":"Nicol\u00e1s Meseguer","orcid":"https://orcid.org/0000-0002-2243-0744"},"institutions":[{"id":"https://openalex.org/I80180929","display_name":"Universidad de Murcia","ror":"https://ror.org/03p3aeb86","country_code":"ES","type":"education","lineage":["https://openalex.org/I80180929"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nicol\u00e1s Meseguer","raw_affiliation_strings":["Universidad de Murcia, Murcia, Spain"],"raw_orcid":"https://orcid.org/0000-0002-2243-0744","affiliations":[{"raw_affiliation_string":"Universidad de Murcia, Murcia, Spain","institution_ids":["https://openalex.org/I80180929"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041025969","display_name":"Yifan Sun","orcid":"https://orcid.org/0000-0003-3532-6521"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Sun","raw_affiliation_strings":["William &amp; Mary, Williamsburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0003-3532-6521","affiliations":[{"raw_affiliation_string":"William &amp; Mary, Williamsburg, Virginia, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009910914","display_name":"Michael Pellauer","orcid":"https://orcid.org/0000-0002-5305-4307"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Pellauer","raw_affiliation_strings":["NVIDIA, Boston, USA"],"raw_orcid":"https://orcid.org/0000-0002-5305-4307","affiliations":[{"raw_affiliation_string":"NVIDIA, Boston, USA","institution_ids":["https://openalex.org/I111088046","https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007832959","display_name":"Jos\u00e9 Luis Abell\u00e1n","orcid":"https://orcid.org/0000-0003-3550-720X"},"institutions":[{"id":"https://openalex.org/I80180929","display_name":"Universidad de Murcia","ror":"https://ror.org/03p3aeb86","country_code":"ES","type":"education","lineage":["https://openalex.org/I80180929"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 L. Abell\u00e1n","raw_affiliation_strings":["Universidad de Murcia, Murcia, Spain"],"raw_orcid":"https://orcid.org/0000-0003-3550-720X","affiliations":[{"raw_affiliation_string":"Universidad de Murcia, Murcia, Spain","institution_ids":["https://openalex.org/I80180929"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010840475","display_name":"Manuel E. Acacio","orcid":"https://orcid.org/0000-0003-0935-4078"},"institutions":[{"id":"https://openalex.org/I80180929","display_name":"Universidad de Murcia","ror":"https://ror.org/03p3aeb86","country_code":"ES","type":"education","lineage":["https://openalex.org/I80180929"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Manuel E. Acacio","raw_affiliation_strings":["Universidad de Murcia, Murcia, Spain"],"raw_orcid":"https://orcid.org/0000-0003-0935-4078","affiliations":[{"raw_affiliation_string":"Universidad de Murcia, Murcia, Spain","institution_ids":["https://openalex.org/I80180929"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06258693,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21","last_page":"27"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9907000064849854,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9902999997138977,"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":0.7473785281181335},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5653005838394165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473785281181335},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5653005838394165}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725798.3725802","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725798.3725802","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725798.3725802","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3725798.3725802","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725798.3725802","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725798.3725802","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th Workshop on General Purpose Processing Using GPU","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1175115578","display_name":null,"funder_award_id":"AEI//10.13039/501100011033/","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G1622782223","display_name":null,"funder_award_id":"MCIN/AEI/10","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G210041235","display_name":null,"funder_award_id":"MCIN /AEI/ 10.13039/501100011033","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2262748287","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G2601397997","display_name":null,"funder_award_id":"10.13039/501100011033","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G300979063","display_name":null,"funder_award_id":"10.13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G34346518","display_name":null,"funder_award_id":"MCIN/AEI/10.13039/501 100 011 033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3681454997","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4042783231","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G410571670","display_name":null,"funder_award_id":"10.13039/501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G425668148","display_name":null,"funder_award_id":".13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G451917667","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G5080475149","display_name":null,"funder_award_id":"10.13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G5539308778","display_name":null,"funder_award_id":"AEI/10.13039/501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G5967599077","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6033112984","display_name":null,"funder_award_id":"MICIU/AEI/10","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"},{"id":"https://openalex.org/G6151357664","display_name":null,"funder_award_id":"AEI 10.13039/501100011033","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7488172652","display_name":null,"funder_award_id":"RYC2021-031966-I","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G929308097","display_name":null,"funder_award_id":"MCIN/ AEI/ 10.13039/501100011033","funder_id":"https://openalex.org/F4320335322","funder_display_name":"European Regional Development Fund"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410321788.pdf","grobid_xml":"https://content.openalex.org/works/W4410321788.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2098118692","https://openalex.org/W2100168029","https://openalex.org/W2152956697","https://openalex.org/W2163027735","https://openalex.org/W2171399035","https://openalex.org/W2289252105","https://openalex.org/W2794887017","https://openalex.org/W2895553128","https://openalex.org/W2925491732","https://openalex.org/W2952928793","https://openalex.org/W3181975841","https://openalex.org/W4231970275","https://openalex.org/W4308968707","https://openalex.org/W4324292875","https://openalex.org/W4389476360","https://openalex.org/W4393407047"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Achieving":[0],"peak":[1],"GPU":[2,62,108,137],"performance":[3,114,141],"requires":[4],"optimizing":[5,135],"data":[6],"locality":[7],"and":[8,16,28,56,73,79,87,93,131],"asynchronous":[9],"execution":[10],"to":[11],"minimize":[12],"memory":[13,86],"access":[14],"costs":[15],"overlap":[17,84],"computation":[18],"with":[19,142],"transfers.While":[20],"features":[21],"like":[22],"the":[23,47,61,69,95],"Tensor":[24,48],"Memory":[25,49],"Accelerator":[26],"(TMA)":[27],"warp":[29],"specialization":[30],"address":[31],"these":[32],"challenges,":[33],"their":[34],"complexity":[35,92],"often":[36],"limits":[37],"programmers.In":[38],"this":[39],"work,":[40],"we":[41],"present":[42],"ACTA":[43,66,112,128],"(Automatic":[44],"Configuration":[45],"of":[46,107,117],"Accelerator),":[50],"a":[51,104,123,129],"software":[52],"library":[53],"that":[54,111],"simplifies":[55],"optimizes":[57],"TMA":[58],"usage.By":[59],"leveraging":[60],"Specification":[63],"Table":[64],"(GST),":[65],"dynamically":[67],"determines":[68],"optimal":[70],"tile":[71],"sizes":[72],"queue":[74],"configurations":[75],"for":[76,97,134],"each":[77],"kernel":[78],"architecture.Its":[80],"algorithm":[81],"ensures":[82],"efficient":[83,132],"between":[85],"computation,":[88],"drastically":[89],"reducing":[90],"programming":[91,145],"eliminating":[94],"need":[96],"exhaustive":[98,118],"design":[99],"space":[100],"exploration.Our":[101],"evaluation":[102],"across":[103],"diverse":[105],"set":[106],"kernels":[109],"demonstrates":[110],"achieves":[113],"within":[115],"2.78%":[116],"tuning":[119],"while":[120],"requiring":[121],"only":[122],"single":[124],"configuration":[125],"pass.This":[126],"makes":[127],"practical":[130],"solution":[133],"modern":[136],"workloads,":[138],"combining":[139],"near-optimal":[140],"significantly":[143],"reduced":[144],"effort.":[146]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
