{"id":"https://openalex.org/W4416146776","doi":"https://doi.org/10.1145/3712285.3759895","title":"KAMI: Communication-Avoiding General Matrix Multiplication within a Single GPU","display_name":"KAMI: Communication-Avoiding General Matrix Multiplication within a Single GPU","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416146776","doi":"https://doi.org/10.1145/3712285.3759895"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759895","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712285.3759895","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090264879","display_name":"Hemeng Wang","orcid":"https://orcid.org/0009-0008-9879-5951"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hemeng Wang","raw_affiliation_strings":["SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100895521","display_name":"Yang Du","orcid":"https://orcid.org/0009-0001-2799-2201"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Du","raw_affiliation_strings":["SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017593137","display_name":"Ship\u2010Peng Li","orcid":"https://orcid.org/0009-0002-0175-2143"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sidu Li","raw_affiliation_strings":["SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061593868","display_name":"Xiangyuan Tian","orcid":"https://orcid.org/0009-0007-1950-6481"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowen Tian","raw_affiliation_strings":["SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060999547","display_name":"Qingxiao Sun","orcid":"https://orcid.org/0000-0003-2927-362X"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingxiao Sun","raw_affiliation_strings":["SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100444152","display_name":"Weifeng Liu","orcid":"https://orcid.org/0000-0002-2150-5759"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Liu","raw_affiliation_strings":["SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SSSLab, Dept. of CST, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5090264879"],"corresponding_institution_ids":["https://openalex.org/I204553293"],"apc_list":null,"apc_paid":null,"fwci":4.5405,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95075125,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1572","last_page":"1589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7067000269889832,"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":0.7067000269889832,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.04740000143647194,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.042399998754262924,"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/matrix-multiplication","display_name":"Matrix multiplication","score":0.5568000078201294},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.5544999837875366},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.37720000743865967},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.3384999930858612},{"id":"https://openalex.org/keywords/multiplication-algorithm","display_name":"Multiplication algorithm","score":0.30730000138282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6381999850273132},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5568000078201294},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.5544999837875366},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5117999911308289},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.46219998598098755},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42669999599456787},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C201290732","wikidata":"https://www.wikidata.org/wiki/Q130762","display_name":"Multiplication algorithm","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2637999951839447},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25600001215934753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759895","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3712285.3759895","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":98,"referenced_works":["https://openalex.org/W1947563839","https://openalex.org/W1964031104","https://openalex.org/W1973305402","https://openalex.org/W1974978766","https://openalex.org/W1978642402","https://openalex.org/W1982811641","https://openalex.org/W1986834688","https://openalex.org/W1991300616","https://openalex.org/W2004642969","https://openalex.org/W2007259720","https://openalex.org/W2010747199","https://openalex.org/W2021280432","https://openalex.org/W2021450636","https://openalex.org/W2028045344","https://openalex.org/W2033130314","https://openalex.org/W2041792040","https://openalex.org/W2043904766","https://openalex.org/W2057081399","https://openalex.org/W2061397794","https://openalex.org/W2073061372","https://openalex.org/W2084379367","https://openalex.org/W2099021415","https://openalex.org/W2099611016","https://openalex.org/W2102291960","https://openalex.org/W2104281151","https://openalex.org/W2104373803","https://openalex.org/W2111717213","https://openalex.org/W2119370163","https://openalex.org/W2142496304","https://openalex.org/W2148542244","https://openalex.org/W2157237396","https://openalex.org/W2159138721","https://openalex.org/W2162322364","https://openalex.org/W2163674731","https://openalex.org/W2163688235","https://openalex.org/W2164946224","https://openalex.org/W2168931017","https://openalex.org/W2170716619","https://openalex.org/W2251876340","https://openalex.org/W2252007067","https://openalex.org/W2282989799","https://openalex.org/W2410272182","https://openalex.org/W2410432900","https://openalex.org/W2412152731","https://openalex.org/W2493665548","https://openalex.org/W2520178508","https://openalex.org/W2565516521","https://openalex.org/W2582955817","https://openalex.org/W2613618711","https://openalex.org/W2622428623","https://openalex.org/W2735462031","https://openalex.org/W2737067755","https://openalex.org/W2745269232","https://openalex.org/W2767319308","https://openalex.org/W2767612671","https://openalex.org/W2768065515","https://openalex.org/W2787034813","https://openalex.org/W2942021433","https://openalex.org/W2952013349","https://openalex.org/W2963137752","https://openalex.org/W2963724807","https://openalex.org/W2983162098","https://openalex.org/W2988070836","https://openalex.org/W3035592585","https://openalex.org/W3084619881","https://openalex.org/W3128928546","https://openalex.org/W3136528982","https://openalex.org/W3138530731","https://openalex.org/W3152511518","https://openalex.org/W3175878603","https://openalex.org/W3192143344","https://openalex.org/W3199939468","https://openalex.org/W3206916567","https://openalex.org/W4239025233","https://openalex.org/W4310563332","https://openalex.org/W4317787787","https://openalex.org/W4324292875","https://openalex.org/W4367171414","https://openalex.org/W4385581934","https://openalex.org/W4386764095","https://openalex.org/W4388031352","https://openalex.org/W4388101094","https://openalex.org/W4388102819","https://openalex.org/W4388661983","https://openalex.org/W4388662066","https://openalex.org/W4389486751","https://openalex.org/W4390692401","https://openalex.org/W4392884779","https://openalex.org/W4394698884","https://openalex.org/W4399145720","https://openalex.org/W4400907330","https://openalex.org/W4405390006","https://openalex.org/W4405754808","https://openalex.org/W4405754817","https://openalex.org/W4405756173","https://openalex.org/W4406214914","https://openalex.org/W4410406801","https://openalex.org/W4416155381"],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"general":[1],"matrix-matrix":[2],"multiplication":[3],"(GEMM)":[4],"has":[5,18],"attracted":[6],"significant":[7],"research":[8],"attention":[9],"in":[10,32],"HPC":[11],"and":[12,34],"AI":[13],"workloads.":[14],"While":[15],"large-scale":[16],"GEMM":[17,36],"nearly":[19],"achieved":[20],"the":[21],"peak":[22],"floating-point":[23],"performance":[24],"of":[25],"GPUs,":[26],"substantial":[27],"opportunities":[28],"for":[29],"optimization":[30],"remain":[31],"small":[33],"batched":[35],"operations.":[37]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-11-12T00:00:00"}