{"id":"https://openalex.org/W4389491861","doi":"https://doi.org/10.1145/3613424.3614247","title":"MAD MAcce: Supporting Multiply-Add Operations for Democratizing Matrix-Multiplication Accelerators","display_name":"MAD MAcce: Supporting Multiply-Add Operations for Democratizing Matrix-Multiplication Accelerators","publication_year":2023,"publication_date":"2023-10-28","ids":{"openalex":"https://openalex.org/W4389491861","doi":"https://doi.org/10.1145/3613424.3614247"},"language":"en","primary_location":{"id":"doi:10.1145/3613424.3614247","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3614247","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3614247","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3614247","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102922751","display_name":"Seunghwan Sung","orcid":"https://orcid.org/0009-0008-2523-7043"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seunghwan Sung","raw_affiliation_strings":["Yonsei University, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0008-2523-7043","affiliations":[{"raw_affiliation_string":"Yonsei University, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013316593","display_name":"Sujin Susanne Hur","orcid":"https://orcid.org/0009-0000-8475-7040"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sujin Hur","raw_affiliation_strings":["Yonsei University, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0000-8475-7040","affiliations":[{"raw_affiliation_string":"Yonsei University, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064083568","display_name":"S. Kim","orcid":"https://orcid.org/0009-0009-0106-6590"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sungwoo Kim","raw_affiliation_strings":["Yonsei University, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0009-0106-6590","affiliations":[{"raw_affiliation_string":"Yonsei University, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103111147","display_name":"Dongho Ha","orcid":"https://orcid.org/0009-0005-4090-4025"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Dongho Ha","raw_affiliation_strings":["Yonsei University, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0005-4090-4025","affiliations":[{"raw_affiliation_string":"Yonsei University, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015526090","display_name":"Yunho Oh","orcid":"https://orcid.org/0000-0001-6442-3705"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunho Oh","raw_affiliation_strings":["Korea University, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-6442-3705","affiliations":[{"raw_affiliation_string":"Korea University, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017913155","display_name":"Won Woo Ro","orcid":"https://orcid.org/0000-0001-5390-6445"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Won Woo Ro","raw_affiliation_strings":["Yonsei University, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-5390-6445","affiliations":[{"raw_affiliation_string":"Yonsei University, Republic of Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"367","last_page":"379"},"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9950000047683716,"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/computer-science","display_name":"Computer science","score":0.7976551651954651},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.7798236608505249},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7312539219856262},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.7230366468429565},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.664130687713623},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5599241256713867},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5321720242500305},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4959028661251068},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.495326429605484},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4829241931438446},{"id":"https://openalex.org/keywords/multiplication-algorithm","display_name":"Multiplication algorithm","score":0.46807989478111267},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.45231950283050537},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4447602331638336},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.43527740240097046},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2547486424446106},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.23015207052230835},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14108943939208984},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.12853792309761047},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12135729193687439},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06875491142272949}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7976551651954651},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.7798236608505249},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7312539219856262},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.7230366468429565},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.664130687713623},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5599241256713867},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5321720242500305},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4959028661251068},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.495326429605484},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4829241931438446},{"id":"https://openalex.org/C201290732","wikidata":"https://www.wikidata.org/wiki/Q130762","display_name":"Multiplication algorithm","level":3,"score":0.46807989478111267},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.45231950283050537},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4447602331638336},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.43527740240097046},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2547486424446106},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.23015207052230835},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14108943939208984},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.12853792309761047},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12135729193687439},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06875491142272949},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3613424.3614247","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3614247","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3614247","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3613424.3614247","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3613424.3614247","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3613424.3614247","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"56th Annual IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/2"}],"awards":[{"id":"https://openalex.org/G1950449498","display_name":null,"funder_award_id":"2021-0-00853","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8333790877","display_name":null,"funder_award_id":"NRF-2021R1A2B5B01002932","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320315121","display_name":"Samsung Advanced Institute of Technology","ror":null},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389491861.pdf","grobid_xml":"https://content.openalex.org/works/W4389491861.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2001962164","https://openalex.org/W2080592089","https://openalex.org/W2085193043","https://openalex.org/W2111530316","https://openalex.org/W2149234156","https://openalex.org/W2171268876","https://openalex.org/W2273440736","https://openalex.org/W2895305554","https://openalex.org/W2901549770","https://openalex.org/W2955738001","https://openalex.org/W2963989532","https://openalex.org/W2979340153","https://openalex.org/W2980186997","https://openalex.org/W3042610241","https://openalex.org/W3044913359","https://openalex.org/W3046751266","https://openalex.org/W3092319711","https://openalex.org/W3104528661","https://openalex.org/W3115527251","https://openalex.org/W3130106255","https://openalex.org/W3130554079","https://openalex.org/W3132532188","https://openalex.org/W3176818990","https://openalex.org/W3201073812","https://openalex.org/W3205883294","https://openalex.org/W3206857466","https://openalex.org/W3206916567","https://openalex.org/W3208633927","https://openalex.org/W3212663212","https://openalex.org/W4213195788","https://openalex.org/W4225869830","https://openalex.org/W4280633999","https://openalex.org/W4282004837","https://openalex.org/W4283025350","https://openalex.org/W4285106078","https://openalex.org/W4308090436","https://openalex.org/W4309672181","https://openalex.org/W4380881150","https://openalex.org/W4392981569"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Modern":[0],"GPUs":[1,68],"commonly":[2],"employ":[3],"specialized":[4],"matrix":[5,11,38],"multiplication":[6],"units":[7],"(MXUs)":[8],"to":[9,24,47,58],"accelerate":[10],"multiplication,":[12],"the":[13,26],"core":[14],"computation":[15],"of":[16],"deep":[17],"learning":[18],"workloads.":[19],"However,":[20],"it":[21],"is":[22,45],"challenging":[23],"exploit":[25],"MXUs":[27,62],"for":[28,70],"GPGPU":[29],"applications":[30],"whose":[31],"fundamental":[32],"algorithms":[33,52],"do":[34],"not":[35],"rely":[36],"on":[37],"multiplication.":[39],"Furthermore,":[40],"an":[41],"additional":[42],"programming":[43],"effort":[44],"necessary":[46],"tailor":[48],"existing":[49],"code":[50],"or":[51,56],"using":[53],"dedicated":[54],"APIs":[55],"libraries":[57],"utilize":[59],"MXUs.":[60],"Therefore,":[61],"are":[63],"often":[64],"underutilized":[65],"even":[66],"when":[67],"hunger":[69],"higher":[71],"throughput.":[72]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
