{"id":"https://openalex.org/W4390317766","doi":"https://doi.org/10.1145/3633462","title":"Exploring Data Layout for Sparse Tensor Times Dense Matrix on GPUs","display_name":"Exploring Data Layout for Sparse Tensor Times Dense Matrix on GPUs","publication_year":2023,"publication_date":"2023-12-28","ids":{"openalex":"https://openalex.org/W4390317766","doi":"https://doi.org/10.1145/3633462"},"language":"en","primary_location":{"id":"doi:10.1145/3633462","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3633462","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3633462","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3633462","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029449217","display_name":"Khalid Ahmad","orcid":"https://orcid.org/0000-0002-5966-5774"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Khalid Ahmad","raw_affiliation_strings":["University of Utah, USA"],"affiliations":[{"raw_affiliation_string":"University of Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071926570","display_name":"Cris Cecka","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cris Cecka","raw_affiliation_strings":["NVIDIA Corporation, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024606205","display_name":"Michael Garland","orcid":"https://orcid.org/0000-0001-6093-7602"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Garland","raw_affiliation_strings":["NVIDIA Corporation, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Corporation, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030152493","display_name":"Mary Hall","orcid":"https://orcid.org/0000-0002-3058-7573"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mary Hall","raw_affiliation_strings":["University of Utah, USA"],"affiliations":[{"raw_affiliation_string":"University of Utah, USA","institution_ids":["https://openalex.org/I223532165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029449217"],"corresponding_institution_ids":["https://openalex.org/I223532165"],"apc_list":null,"apc_paid":null,"fwci":0.8667,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.70410628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"21","issue":"1","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9998999834060669,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973000288009644,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.9825999736785889,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7541123628616333},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6631165146827698},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6229085922241211},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5326604247093201},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5146278142929077},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4907568395137787},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3410460650920868},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13634651899337769},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12386119365692139},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.12076488137245178},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.0971466600894928}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7541123628616333},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6631165146827698},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6229085922241211},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5326604247093201},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5146278142929077},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4907568395137787},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3410460650920868},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13634651899337769},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12386119365692139},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.12076488137245178},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0971466600894928},{"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3633462","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3633462","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3633462","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3633462","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3633462","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3633462","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"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 Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390317766.pdf","grobid_xml":"https://content.openalex.org/works/W4390317766.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1480958225","https://openalex.org/W1964195795","https://openalex.org/W1985312666","https://openalex.org/W2013912476","https://openalex.org/W2014807599","https://openalex.org/W2022219663","https://openalex.org/W2024165284","https://openalex.org/W2610373075","https://openalex.org/W2808128431","https://openalex.org/W2886162485","https://openalex.org/W2914631005","https://openalex.org/W3028129830","https://openalex.org/W3098408187","https://openalex.org/W3131137184","https://openalex.org/W3164929383","https://openalex.org/W4236418138","https://openalex.org/W4382677476"],"related_works":["https://openalex.org/W3202552726","https://openalex.org/W2279642117","https://openalex.org/W4321636545","https://openalex.org/W4387560237","https://openalex.org/W4285148873","https://openalex.org/W2045476623","https://openalex.org/W2076468490","https://openalex.org/W2023476765","https://openalex.org/W2081219400","https://openalex.org/W2805810264"],"abstract_inverted_index":{"An":[0],"important":[1],"sparse":[2,68,122,132],"tensor":[3,13,33,41,69,77,123],"computation":[4],"is":[5,10,18,107],"sparse-tensor-dense-matrix":[6],"multiplication":[7,24],"(SpTM),":[8],"which":[9],"used":[11],"in":[12],"decomposition":[14],"and":[15],"applications.":[16],"SpTM":[17,52],"a":[19,31,39,44,113],"multi-dimensional":[20],"analog":[21],"to":[22,42,50,64,117],"sparse-matrix-dense-matrix":[23],"(SpMM).":[25],"In":[26],"this":[27],"article,":[28],"we":[29,111],"employ":[30],"hierarchical":[32,76],"data":[34,78],"layout":[35],"that":[36,92],"can":[37,94],"unfold":[38],"multidimensional":[40],"derive":[43],"2D":[45],"matrix,":[46],"making":[47],"it":[48],"possible":[49],"compute":[51],"using":[53],"SpMM":[54,62,74,93],"kernel":[55,125],"implementations":[56,63],"for":[57],"GPUs.":[58],"We":[59],"compare":[60],"two":[61],"the":[65,99,104,119,131],"state-of-the-art":[66],"PASTA":[67,96],"contraction":[70,124],"implementation":[71],"using:":[72],"(1)":[73],"with":[75],"layout;":[79],"and,":[80],"(2)":[81],"unfolding":[82],"followed":[83],"by":[84],"an":[85],"invocation":[86],"of":[87,98,103,130],"cuSPARSE\u2019s":[88],"SpMM.":[89],"Results":[90],"show":[91],"outperform":[95],"70.9%":[97],"time,":[100],"but":[101],"none":[102],"three":[105],"approaches":[106],"best":[108,120],"overall.":[109],"Therefore,":[110],"use":[112],"decision":[114],"tree":[115],"classifier":[116],"identify":[118],"performing":[121],"based":[126],"on":[127],"precomputed":[128],"properties":[129],"tensor.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}