{"id":"https://openalex.org/W4391047420","doi":"https://doi.org/10.1145/3627535.3638489","title":"Fast Kronecker Matrix-Matrix Multiplication on GPUs","display_name":"Fast Kronecker Matrix-Matrix Multiplication on GPUs","publication_year":2024,"publication_date":"2024-02-20","ids":{"openalex":"https://openalex.org/W4391047420","doi":"https://doi.org/10.1145/3627535.3638489"},"language":"en","primary_location":{"id":"doi:10.1145/3627535.3638489","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627535.3638489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.10187","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034240415","display_name":"Abhinav Jangda","orcid":"https://orcid.org/0000-0002-4849-6776"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abhinav Jangda","raw_affiliation_strings":["Microsoft Research, Redmond, Washington, United States of America"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, Washington, United States of America","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065809431","display_name":"Mohit Yadav","orcid":"https://orcid.org/0009-0004-7487-6811"},"institutions":[{"id":"https://openalex.org/I177605424","display_name":"Amherst College","ror":"https://ror.org/028vqfs63","country_code":"US","type":"education","lineage":["https://openalex.org/I177605424"]},{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Yadav","raw_affiliation_strings":["Manning College of Information & Computer Sciences, University of Massachusetts Amherst, Amherst, Massachusetts, USA"],"affiliations":[{"raw_affiliation_string":"Manning College of Information & Computer Sciences, University of Massachusetts Amherst, Amherst, Massachusetts, USA","institution_ids":["https://openalex.org/I177605424","https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034240415"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":0.4962,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55102551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"390","last_page":"403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9983000159263611,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9871000051498413,"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/kronecker-product","display_name":"Kronecker product","score":0.8944706916809082},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.8330491781234741},{"id":"https://openalex.org/keywords/kronecker-delta","display_name":"Kronecker delta","score":0.6770193576812744},{"id":"https://openalex.org/keywords/transpose","display_name":"Transpose","score":0.6499987840652466},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.6150788068771362},{"id":"https://openalex.org/keywords/tensor-product","display_name":"Tensor product","score":0.5867587327957153},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5414606928825378},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.47283750772476196},{"id":"https://openalex.org/keywords/symmetric-matrix","display_name":"Symmetric matrix","score":0.46474120020866394},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4248966574668884},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4243849515914917},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.4111385941505432},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3778175115585327},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.13771581649780273},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.0854659378528595},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07733204960823059}],"concepts":[{"id":"https://openalex.org/C46030957","wikidata":"https://www.wikidata.org/wiki/Q1238125","display_name":"Kronecker product","level":3,"score":0.8944706916809082},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.8330491781234741},{"id":"https://openalex.org/C39482219","wikidata":"https://www.wikidata.org/wiki/Q192826","display_name":"Kronecker delta","level":2,"score":0.6770193576812744},{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.6499987840652466},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.6150788068771362},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.5867587327957153},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5414606928825378},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.47283750772476196},{"id":"https://openalex.org/C54848796","wikidata":"https://www.wikidata.org/wiki/Q339011","display_name":"Symmetric matrix","level":3,"score":0.46474120020866394},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4248966574668884},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4243849515914917},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.4111385941505432},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3778175115585327},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.13771581649780273},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0854659378528595},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07733204960823059},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3627535.3638489","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627535.3638489","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2401.10187","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.10187","pdf_url":"https://arxiv.org/pdf/2401.10187","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.10187","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.10187","pdf_url":"https://arxiv.org/pdf/2401.10187","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391047420.pdf","grobid_xml":"https://content.openalex.org/works/W4391047420.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W201315547","https://openalex.org/W1598993252","https://openalex.org/W1702387805","https://openalex.org/W1839773802","https://openalex.org/W1862558588","https://openalex.org/W1967329527","https://openalex.org/W2006973305","https://openalex.org/W2034692228","https://openalex.org/W2039747889","https://openalex.org/W2051325990","https://openalex.org/W2056999868","https://openalex.org/W2089086379","https://openalex.org/W2119595900","https://openalex.org/W2137135057","https://openalex.org/W2153215853","https://openalex.org/W2168748809","https://openalex.org/W2252007067","https://openalex.org/W2293244628","https://openalex.org/W2340879669","https://openalex.org/W2466677533","https://openalex.org/W2471966094","https://openalex.org/W2588061952","https://openalex.org/W2753515784","https://openalex.org/W2788909472","https://openalex.org/W2805328290","https://openalex.org/W2885972351","https://openalex.org/W2891431244","https://openalex.org/W2893995718","https://openalex.org/W2911495555","https://openalex.org/W2963137752","https://openalex.org/W2963482281","https://openalex.org/W2984305089","https://openalex.org/W2990138404","https://openalex.org/W3004555699","https://openalex.org/W3044796228","https://openalex.org/W3082511454","https://openalex.org/W3099221095","https://openalex.org/W3101321165","https://openalex.org/W3136481171","https://openalex.org/W3160972817","https://openalex.org/W3173462777","https://openalex.org/W3193985311","https://openalex.org/W4211049957","https://openalex.org/W4220690649","https://openalex.org/W4248445937","https://openalex.org/W4293777437","https://openalex.org/W4294562205","https://openalex.org/W4294568934","https://openalex.org/W4307563791","https://openalex.org/W4318539236","https://openalex.org/W6921225092"],"related_works":["https://openalex.org/W123417539","https://openalex.org/W4233239985","https://openalex.org/W2079407403","https://openalex.org/W2060299328","https://openalex.org/W2117336295","https://openalex.org/W2073634779","https://openalex.org/W3102722572","https://openalex.org/W2090103374","https://openalex.org/W1564288589","https://openalex.org/W577870507"],"abstract_inverted_index":{"Kronecker":[0,12],"Matrix-Matrix":[1],"Multiplication":[2],"(Kron-Matmul)":[3],"is":[4,19],"the":[5,11,61],"multiplication":[6],"of":[7,14],"a":[8,20],"matrix":[9,40,45],"with":[10],"Product":[13],"several":[15,52],"smaller":[16],"matrices.":[17],"Kron-Matmul":[18,31,53],"core":[21],"operation":[22],"for":[23],"many":[24],"scientific":[25],"and":[26,43],"machine":[27],"learning":[28],"computations.":[29],"State-of-the-art":[30],"implementations":[32],"utilize":[33],"existing":[34],"tensor":[35,44],"algebra":[36],"operations,":[37],"such":[38],"as":[39],"multiplication,":[41],"transpose,":[42],"multiplication.":[46],"However,":[47],"this":[48],"design":[49],"choice":[50],"prevents":[51],"specific":[54],"optimizations,":[55],"thus,":[56],"leaving":[57],"significant":[58],"performance":[59],"on":[60],"table.":[62]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}