{"id":"https://openalex.org/W4318541582","doi":"https://doi.org/10.1145/3575693.3575742","title":"WACO: Learning Workload-Aware Co-optimization of the Format and Schedule of a Sparse Tensor Program","display_name":"WACO: Learning Workload-Aware Co-optimization of the Format and Schedule of a Sparse Tensor Program","publication_year":2023,"publication_date":"2023-01-27","ids":{"openalex":"https://openalex.org/W4318541582","doi":"https://doi.org/10.1145/3575693.3575742"},"language":"en","primary_location":{"id":"doi:10.1145/3575693.3575742","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3575693.3575742","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3575693.3575742","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 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","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/10.1145/3575693.3575742","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061627890","display_name":"Jaeyeon Won","orcid":"https://orcid.org/0000-0002-3082-4348"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jaeyeon Won","raw_affiliation_strings":["Massachusetts Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034476447","display_name":"Charith Mendis","orcid":"https://orcid.org/0000-0002-8140-2321"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charith Mendis","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024384625","display_name":"Joel Emer","orcid":null},"institutions":[{"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"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joel S. Emer","raw_affiliation_strings":["Massachusetts Institute of Technology, USA / NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA / NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046791216","display_name":"Saman Amarasinghe","orcid":"https://orcid.org/0000-0002-7231-7643"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saman Amarasinghe","raw_affiliation_strings":["Massachusetts Institute of Technology, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"920","last_page":"934"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.996999979019165,"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":0.996999979019165,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8319884538650513},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.7459460496902466},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.5769861340522766},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5149391293525696},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.42315351963043213},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4226270318031311},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4109541177749634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3549680709838867},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3210655450820923},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10817724466323853},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10513162612915039}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319884538650513},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.7459460496902466},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.5769861340522766},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5149391293525696},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.42315351963043213},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4226270318031311},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4109541177749634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3549680709838867},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3210655450820923},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10817724466323853},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10513162612915039},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3575693.3575742","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3575693.3575742","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3575693.3575742","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 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/147826","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/147826","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/147826/1/3575693.3575742.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM|Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"http://purl.org/eprint/type/ConferencePaper"},{"id":"pmh:oai:dspace.mit.edu:1721.1/152757","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/152757","pdf_url":"https://dspace.mit.edu/bitstream/1721.1/152757/1/won-jaeyeon-sm-eecs-2023-thesis.pdf","source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"}],"best_oa_location":{"id":"doi:10.1145/3575693.3575742","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3575693.3575742","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3575693.3575742","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 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1279283373","display_name":null,"funder_award_id":"HR0011-20-9-0017","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G3330912664","display_name":null,"funder_award_id":"CCF-2107244","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4175439218","display_name":"Collaborative Research: SHF: Medium: Spatial Multi-Tenant Neural Acceleration for Next Generation Datacenters","funder_award_id":"2107244","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6650245637","display_name":null,"funder_award_id":"HR0011-18-3-0007","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8073515163","display_name":null,"funder_award_id":"DE-SC0008923","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G8839178245","display_name":null,"funder_award_id":"DE-SC0008923","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4318541582.pdf","grobid_xml":"https://content.openalex.org/works/W4318541582.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W1489951562","https://openalex.org/W1987840949","https://openalex.org/W2003117296","https://openalex.org/W2049487370","https://openalex.org/W2053999255","https://openalex.org/W2091883426","https://openalex.org/W2096070062","https://openalex.org/W2099625934","https://openalex.org/W2100218206","https://openalex.org/W2129287653","https://openalex.org/W2143331230","https://openalex.org/W2461193710","https://openalex.org/W2471164860","https://openalex.org/W2590246587","https://openalex.org/W2788264912","https://openalex.org/W2887930195","https://openalex.org/W2898123186","https://openalex.org/W2905135312","https://openalex.org/W2914631005","https://openalex.org/W2940862705","https://openalex.org/W2954217418","https://openalex.org/W2961619211","https://openalex.org/W2963125977","https://openalex.org/W2963265099","https://openalex.org/W2963469388","https://openalex.org/W2965706220","https://openalex.org/W2981758446","https://openalex.org/W2997411837","https://openalex.org/W3037261029","https://openalex.org/W3098650335","https://openalex.org/W3108012228","https://openalex.org/W3121402054","https://openalex.org/W3129727110","https://openalex.org/W3132695675","https://openalex.org/W3192336523","https://openalex.org/W4251637954"],"related_works":["https://openalex.org/W986318368","https://openalex.org/W2000785801","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W2620865396","https://openalex.org/W2414054180"],"abstract_inverted_index":{"In":[0,97],"this":[1,30,65],"paper,":[2],"we":[3],"present":[4],"WACO,":[5],"a":[6,17,22,36,46,68,82,92,125,142,164],"novel":[7,107],"method":[8],"of":[9,16,35,45,76,104,173],"co-optimizing":[10],"the":[11,14,33,43,52,55,58,77,86,89,100,119,171],"format":[12,87,121],"and":[13,57,80,88,116,122,139,167,181,189],"schedule":[15,90,95,123],"given":[18,126],"sparsity":[19,53,78,127,147],"pattern":[20,79],"in":[21,29,63],"sparse":[23,47,69],"tensor":[24,48],"program.":[25],"A":[26],"core":[27],"challenge":[28],"paper":[31],"is":[32,66],"design":[34],"lightweight":[37],"cost":[38],"model":[39],"that":[40,153],"accurately":[41,117],"predicts":[42],"runtime":[44],"program":[49],"by":[50],"considering":[51],"pattern,":[54],"format,":[56],"schedule.":[59],"The":[60],"key":[61],"idea":[62],"addressing":[64],"exploiting":[67],"convolutional":[70],"network":[71],"to":[72,170],"learn":[73],"meaningful":[74],"features":[75],"embedding":[81],"coupled":[83],"behavior":[84],"between":[85],"using":[91,144],"specially":[93],"designed":[94],"template.":[96],"addition,":[98],"within":[99],"enormous":[101],"search":[102,108],"space":[103],"co-optimization,":[105],"our":[106],"strategy,":[109],"an":[110],"approximate":[111],"nearest":[112],"neighbor":[113],"search,":[114],"efficiently":[115],"retrieves":[118],"best":[120,172],"for":[124,132],"pattern.":[128],"We":[129],"evaluated":[130],"WACO":[131,154,176],"four":[133,156,174],"different":[134,146],"algorithms":[135],"(SpMV,":[136],"SpMM,":[137,187],"SDDMM,":[138,188],"MTTKRP)":[140],"on":[141,185],"CPU":[143],"726":[145],"patterns.":[148],"Our":[149],"experimental":[150],"results":[151],"showed":[152],"outperformed":[155],"state-of-the-art":[157],"baselines,":[158,175],"Intel":[159],"MKL,":[160],"BestFormat,":[161],"TACO":[162],"with":[163],"default":[165],"schedule,":[166],"ASpT.":[168],"Compared":[169],"achieved":[177],"1.43\u00d7,":[178],"1.18\u00d7,":[179],"1.14\u00d7,":[180],"1.27\u00d7":[182],"average":[183],"speedups":[184],"SpMV,":[186],"MTTKRP,":[190],"respectively.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}