{"id":"https://openalex.org/W2051334781","doi":"https://doi.org/10.1109/hipc.2013.6799109","title":"Accelerating Strassen-Winograd's matrix multiplication algorithm on GPUs","display_name":"Accelerating Strassen-Winograd's matrix multiplication algorithm on GPUs","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W2051334781","doi":"https://doi.org/10.1109/hipc.2013.6799109","mag":"2051334781"},"language":"en","primary_location":{"id":"doi:10.1109/hipc.2013.6799109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2013.6799109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th Annual International Conference on High Performance Computing","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/A5029715982","display_name":"Pai-Wei Lai","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pai-Wei Lai","raw_affiliation_strings":["Dept. of Computer Science and Engineering, The Ohio State University","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085526499","display_name":"Humayun Arafat","orcid":null},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Humayun Arafat","raw_affiliation_strings":["Dept. of Computer Science and Engineering, The Ohio State University","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007976782","display_name":"Venmugil Elango","orcid":"https://orcid.org/0000-0002-7031-9020"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venmugil Elango","raw_affiliation_strings":["Dept. of Computer Science and Engineering, The Ohio State University","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["Dept. of Computer Science and Engineering, The Ohio State University","Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, The Ohio State University","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Ohio State Univ., Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029715982"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":1.8913,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.85929828,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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/T12303","display_name":"Tensor decomposition and applications","score":0.996399998664856,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/strassen-algorithm","display_name":"Strassen algorithm","score":0.9880210161209106},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8570965528488159},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7749518156051636},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6821586489677429},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6805843114852905},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5249050855636597},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5015039443969727},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4770326316356659},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12989559769630432}],"concepts":[{"id":"https://openalex.org/C39096654","wikidata":"https://www.wikidata.org/wiki/Q728507","display_name":"Strassen algorithm","level":4,"score":0.9880210161209106},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8570965528488159},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749518156051636},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6821586489677429},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6805843114852905},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5249050855636597},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5015039443969727},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4770326316356659},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12989559769630432},{"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipc.2013.6799109","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2013.6799109","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"20th Annual International Conference on High Performance Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1970548269","https://openalex.org/W1979740015","https://openalex.org/W1996487631","https://openalex.org/W2002257715","https://openalex.org/W2004916460","https://openalex.org/W2023724794","https://openalex.org/W2035476608","https://openalex.org/W2040832766","https://openalex.org/W2058790613","https://openalex.org/W2064941923","https://openalex.org/W2120489629","https://openalex.org/W2145889866","https://openalex.org/W2166323765","https://openalex.org/W2478352205","https://openalex.org/W3139307873","https://openalex.org/W3141650078","https://openalex.org/W4256483581","https://openalex.org/W6675758723"],"related_works":["https://openalex.org/W2794923745","https://openalex.org/W3159529979","https://openalex.org/W2392023973","https://openalex.org/W3196932171","https://openalex.org/W4226309051","https://openalex.org/W2923029190","https://openalex.org/W2907215606","https://openalex.org/W2127872620","https://openalex.org/W3014127403","https://openalex.org/W2256144436"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"report":[4],"on":[5,50,69],"the":[6,14,41,44,59],"development":[7],"of":[8,13,21,43,61],"an":[9],"efficient":[10],"GPU":[11],"implementation":[12,45],"Strassen-Winograd":[15],"matrix":[16,67],"multiplication":[17],"algorithm":[18,63],"for":[19,64,76,81],"matrices":[20],"arbitrary":[22],"sizes.":[23],"We":[24,39],"utilize":[25],"multi-kernel":[26],"streaming":[27],"to":[28,36,73],"exploit":[29],"concurrency":[30],"across":[31],"sub-matrix":[32],"operations":[33],"in":[34,46],"addition":[35],"intra-operation":[37],"parallelism.":[38],"evaluate":[40],"performance":[42],"comparison":[47],"with":[48,71],"CUBLAS-5.0":[49],"Fermi":[51],"and":[52,78],"Kepler":[53],"GPUs.":[54],"The":[55],"experimental":[56],"results":[57],"demonstrate":[58],"usefulness":[60],"Strassen's":[62],"practically":[65],"relevant":[66],"sizes":[68],"GPUs,":[70],"up":[72],"1.27X":[74],"speedup":[75,80],"single-precision":[77],"1.42X":[79],"double-precision":[82],"floating":[83],"point":[84],"computation.":[85]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}