{"id":"https://openalex.org/W4414639270","doi":"https://doi.org/10.1007/978-3-031-97196-9_15","title":"Leveraging Hardware-Aware Computation in\u00a0Mixed-Precision Matrix Multiply: A Tile-Centric Approach","display_name":"Leveraging Hardware-Aware Computation in\u00a0Mixed-Precision Matrix Multiply: A Tile-Centric Approach","publication_year":2025,"publication_date":"2025-09-30","ids":{"openalex":"https://openalex.org/W4414639270","doi":"https://doi.org/10.1007/978-3-031-97196-9_15"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-97196-9_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-97196-9_15","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","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/A5100357522","display_name":"Qiao Zhang","orcid":"https://orcid.org/0000-0002-3509-8103"},"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":"Qiao Zhang","raw_affiliation_strings":["Saint Louis University, St. Louis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saint Louis University, St. 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, Saudi Arabia","Massachusetts Institute of Technology, Cambridge, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology, Thuwal, 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/A5101543640","display_name":"Dali Wang","orcid":"https://orcid.org/0000-0001-6806-5108"},"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, St. Louis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saint Louis University, St. Louis, USA","institution_ids":["https://openalex.org/I47838141"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031048186","display_name":"Qinglei Cao","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":"Qinglei Cao","raw_affiliation_strings":["Saint Louis University, St. Louis, MO, USA","Saint Louis University, St. Louis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Saint Louis University, St. Louis, MO, USA","institution_ids":["https://openalex.org/I47838141"]},{"raw_affiliation_string":"Saint Louis University, St. Louis, USA","institution_ids":["https://openalex.org/I47838141"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031048186"],"corresponding_institution_ids":["https://openalex.org/I47838141"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":3.0301,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91236089,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"174","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6309999823570251},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.625},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5449000000953674},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5289999842643738},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5281999707221985},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.49779999256134033},{"id":"https://openalex.org/keywords/double-precision-floating-point-format","display_name":"Double-precision floating-point format","score":0.4528000056743622},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.42579999566078186},{"id":"https://openalex.org/keywords/underpinning","display_name":"Underpinning","score":0.4081000089645386},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.38929998874664307}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8871999979019165},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6309999823570251},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.625},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5449000000953674},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5289999842643738},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5281999707221985},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.49779999256134033},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4918000102043152},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.47870001196861267},{"id":"https://openalex.org/C35912277","wikidata":"https://www.wikidata.org/wiki/Q1243369","display_name":"Double-precision floating-point format","level":3,"score":0.4528000056743622},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.43779999017715454},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43220001459121704},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.42579999566078186},{"id":"https://openalex.org/C2780871342","wikidata":"https://www.wikidata.org/wiki/Q7883752","display_name":"Underpinning","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.38929998874664307},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3582000136375427},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C44060867","wikidata":"https://www.wikidata.org/wiki/Q12129","display_name":"Parsec","level":3,"score":0.3244999945163727},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.3237000107765198},{"id":"https://openalex.org/C2982832238","wikidata":"https://www.wikidata.org/wiki/Q5531640","display_name":"General purpose","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C128099668","wikidata":"https://www.wikidata.org/wiki/Q573952","display_name":"Lazy evaluation","level":3,"score":0.3174999952316284},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3057999908924103},{"id":"https://openalex.org/C163834973","wikidata":"https://www.wikidata.org/wiki/Q2004891","display_name":"Numerical linear algebra","level":3,"score":0.30160000920295715},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.30059999227523804},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C146044194","wikidata":"https://www.wikidata.org/wiki/Q5157334","display_name":"Computational photography","level":4,"score":0.2816999852657318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27649998664855957},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C2780870223","wikidata":"https://www.wikidata.org/wiki/Q1004415","display_name":"Runtime system","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2655999958515167},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.2606000006198883}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-97196-9_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-97196-9_15","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1966385318","https://openalex.org/W1983292127","https://openalex.org/W2056999868","https://openalex.org/W2121893797","https://openalex.org/W2122747952","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/W3097443356","https://openalex.org/W3108141724","https://openalex.org/W3125739096","https://openalex.org/W3132277775","https://openalex.org/W3165254043","https://openalex.org/W3215228131","https://openalex.org/W4248722156","https://openalex.org/W4248806677","https://openalex.org/W4285503969","https://openalex.org/W4321636543","https://openalex.org/W4385249512","https://openalex.org/W4387676057","https://openalex.org/W4388855622","https://openalex.org/W4403510987","https://openalex.org/W4405754839","https://openalex.org/W4405755978"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
