{"id":"https://openalex.org/W7116383847","doi":"https://doi.org/10.1007/s42979-025-04575-0","title":"High-Performance Mixed-Precision Matrix Multiplication via Tile-Centric Design on Modern Architectures","display_name":"High-Performance Mixed-Precision Matrix Multiplication via Tile-Centric Design on Modern Architectures","publication_year":2025,"publication_date":"2025-12-20","ids":{"openalex":"https://openalex.org/W7116383847","doi":"https://doi.org/10.1007/s42979-025-04575-0"},"language":"en","primary_location":{"id":"doi:10.1007/s42979-025-04575-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s42979-025-04575-0","pdf_url":null,"source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","raw_type":"journal-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":null,"display_name":"Qiao Zhang","orcid":"https://orcid.org/0000-0002-6690-194X"},"institutions":[{"id":"https://openalex.org/I47838141","display_name":"Saint Louis University","ror":"https://ror.org/01p7jjy08","country_code":"US","type":"education","lineage":["https://openalex.org/I47838141"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qiao Zhang","raw_affiliation_strings":["Saint Louis University, Saint Louis, USA"],"raw_orcid":"https://orcid.org/0000-0002-6690-194X","affiliations":[{"raw_affiliation_string":"Saint Louis University, Saint Louis, USA","institution_ids":["https://openalex.org/I47838141"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013947843","display_name":"Rabab Alomairy","orcid":"https://orcid.org/0000-0001-9911-6094"},"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"]},{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA","US"],"is_corresponding":false,"raw_author_name":"Rabab Alomairy","raw_affiliation_strings":["King Abdullah University of Science and Technology, Thuwal, Kingdom of Saudi Arabia","Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology, Thuwal, Kingdom of Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120945594","display_name":"Dali Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dali Wang","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, USA","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063687318","display_name":"Zhihao Gu","orcid":"https://orcid.org/0000-0002-2004-6431"},"institutions":[{"id":"https://openalex.org/I47838141","display_name":"Saint Louis University","ror":"https://ror.org/01p7jjy08","country_code":"US","type":"education","lineage":["https://openalex.org/I47838141"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuowei Gu","raw_affiliation_strings":["Saint Louis University, Saint Louis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saint Louis University, Saint Louis, USA","institution_ids":["https://openalex.org/I47838141"]}]},{"author_position":"last","author":{"id":null,"display_name":"Qinglei Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I47838141","display_name":"Saint Louis University","ror":"https://ror.org/01p7jjy08","country_code":"US","type":"education","lineage":["https://openalex.org/I47838141"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qinglei Cao","raw_affiliation_strings":["Saint Louis University, Saint Louis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saint Louis University, Saint Louis, USA","institution_ids":["https://openalex.org/I47838141"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47838141"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":null,"fwci":2.0573,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.88994475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"7","issue":"1","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":0.44850000739097595,"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":0.44850000739097595,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.10980000346899033,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.08429999649524689,"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/leverage","display_name":"Leverage (statistics)","score":0.6299999952316284},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6226999759674072},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5454999804496765},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5228999853134155},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.45350000262260437},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.42080000042915344},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.4099000096321106},{"id":"https://openalex.org/keywords/underpinning","display_name":"Underpinning","score":0.3431999981403351}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7035999894142151},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6299999952316284},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6226999759674072},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5928999781608582},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5228999853134155},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5178999900817871},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.45350000262260437},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43299999833106995},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.42080000042915344},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.4099000096321106},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3513000011444092},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3434000015258789},{"id":"https://openalex.org/C2780871342","wikidata":"https://www.wikidata.org/wiki/Q7883752","display_name":"Underpinning","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30489999055862427},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s42979-025-04575-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s42979-025-04575-0","pdf_url":null,"source":{"id":"https://openalex.org/S4210174798","display_name":"SN Computer Science","issn_l":"2661-8907","issn":["2661-8907","2662-995X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SN Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/164427","is_oa":false,"landing_page_url":"https://hdl.handle.net/1721.1/164427","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Springer Nature Singapore","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8953196406364441}],"awards":[{"id":"https://openalex.org/G7783422017","display_name":null,"funder_award_id":"2451577","funder_id":"https://openalex.org/F4320337563","funder_display_name":"Division of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320337563","display_name":"Division of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W1841592590","https://openalex.org/W1915071989","https://openalex.org/W1966385318","https://openalex.org/W1975818677","https://openalex.org/W1977146902","https://openalex.org/W1983292127","https://openalex.org/W1988201922","https://openalex.org/W2004206314","https://openalex.org/W2020804487","https://openalex.org/W2056999868","https://openalex.org/W2087440962","https://openalex.org/W2111593426","https://openalex.org/W2121893797","https://openalex.org/W2122747952","https://openalex.org/W2124480634","https://openalex.org/W2410272182","https://openalex.org/W2570458281","https://openalex.org/W2606722458","https://openalex.org/W2766943539","https://openalex.org/W2808102735","https://openalex.org/W2895305554","https://openalex.org/W2903376718","https://openalex.org/W2964027192","https://openalex.org/W2994914294","https://openalex.org/W2998512843","https://openalex.org/W2998672756","https://openalex.org/W3025017204","https://openalex.org/W3036899338","https://openalex.org/W3097443356","https://openalex.org/W3108141724","https://openalex.org/W3125739096","https://openalex.org/W3132277775","https://openalex.org/W3138530731","https://openalex.org/W3165254043","https://openalex.org/W3215228131","https://openalex.org/W4236558082","https://openalex.org/W4248722156","https://openalex.org/W4248806677","https://openalex.org/W4285503969","https://openalex.org/W4321636543","https://openalex.org/W4380434592","https://openalex.org/W4385249512","https://openalex.org/W4385572286","https://openalex.org/W4387676057","https://openalex.org/W4388855622","https://openalex.org/W4400838144","https://openalex.org/W4403510987","https://openalex.org/W4405754839","https://openalex.org/W4405755978","https://openalex.org/W4414639270","https://openalex.org/W7110222648"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-12-21T00:00:00"}
