{"id":"https://openalex.org/W3132532188","doi":"https://doi.org/10.1145/3437801.3441599","title":"EGEMM-TC","display_name":"EGEMM-TC","publication_year":2021,"publication_date":"2021-02-17","ids":{"openalex":"https://openalex.org/W3132532188","doi":"https://doi.org/10.1145/3437801.3441599","mag":"3132532188"},"language":"en","primary_location":{"id":"doi:10.1145/3437801.3441599","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437801.3441599","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437801.3441599","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3437801.3441599","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102793122","display_name":"Boyuan Feng","orcid":"https://orcid.org/0000-0003-1941-5137"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Boyuan Feng","raw_affiliation_strings":["University of California"],"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101589099","display_name":"Yuke Wang","orcid":"https://orcid.org/0000-0002-0360-8738"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuke Wang","raw_affiliation_strings":["University of California"],"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103032013","display_name":"Guoyang Chen","orcid":"https://orcid.org/0000-0002-5531-8986"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guoyang Chen","raw_affiliation_strings":["Alibaba Group US Inc"],"affiliations":[{"raw_affiliation_string":"Alibaba Group US Inc","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100426678","display_name":"Weifeng Zhang","orcid":"https://orcid.org/0000-0002-4529-1679"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weifeng Zhang","raw_affiliation_strings":["Alibaba Group US Inc"],"affiliations":[{"raw_affiliation_string":"Alibaba Group US Inc","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110042813","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0001-6945-7437"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["University of California"],"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048052285","display_name":"Yufei Ding","orcid":"https://orcid.org/0000-0002-8716-5793"},"institutions":[{"id":"https://openalex.org/I2803209242","display_name":"University of California System","ror":"https://ror.org/00pjdza24","country_code":"US","type":"education","lineage":["https://openalex.org/I2803209242"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yufei Ding","raw_affiliation_strings":["University of California"],"affiliations":[{"raw_affiliation_string":"University of California","institution_ids":["https://openalex.org/I2803209242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5102793122"],"corresponding_institution_ids":["https://openalex.org/I2803209242"],"apc_list":null,"apc_paid":null,"fwci":5.6592,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":{"value":0.968271,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"278","last_page":"291"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9977999925613403,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.992900013923645,"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/speedup","display_name":"Speedup","score":0.8136022686958313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8118078708648682},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6567891836166382},{"id":"https://openalex.org/keywords/emulation","display_name":"Emulation","score":0.6481260657310486},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6267880797386169},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5597640872001648},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5485115051269531},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5401275753974915},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4732264280319214},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4675435423851013},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4442228674888611},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2993052005767822},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08411392569541931}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8136022686958313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8118078708648682},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6567891836166382},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.6481260657310486},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6267880797386169},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5597640872001648},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5485115051269531},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5401275753974915},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4732264280319214},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4675435423851013},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4442228674888611},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2993052005767822},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08411392569541931},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3437801.3441599","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437801.3441599","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437801.3441599","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-132976","is_oa":false,"landing_page_url":"https://repository.hkust.edu.hk/ir/Record/1783.1-132976","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3437801.3441599","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437801.3441599","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437801.3441599","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3132532188.pdf","grobid_xml":"https://content.openalex.org/works/W3132532188.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1528572881","https://openalex.org/W1971868176","https://openalex.org/W1981663184","https://openalex.org/W1997230820","https://openalex.org/W2012407419","https://openalex.org/W2026791237","https://openalex.org/W2028960610","https://openalex.org/W2030828780","https://openalex.org/W2090156379","https://openalex.org/W2093723220","https://openalex.org/W2093843662","https://openalex.org/W2106191211","https://openalex.org/W2119352997","https://openalex.org/W2164363152","https://openalex.org/W2580538010","https://openalex.org/W2765781408","https://openalex.org/W2796649226","https://openalex.org/W2901549770","https://openalex.org/W2902032143","https://openalex.org/W2913790721","https://openalex.org/W2920798074","https://openalex.org/W2949251082","https://openalex.org/W2963122961","https://openalex.org/W2970601456","https://openalex.org/W3012526378","https://openalex.org/W3043303806","https://openalex.org/W3104528661"],"related_works":["https://openalex.org/W2023938924","https://openalex.org/W2374102355","https://openalex.org/W2095778784","https://openalex.org/W2130748128","https://openalex.org/W4327930469","https://openalex.org/W2002833390","https://openalex.org/W2791204867","https://openalex.org/W4285504855","https://openalex.org/W2165086284","https://openalex.org/W2374747925"],"abstract_inverted_index":{"Nvidia":[0],"Tensor":[1,21,42,50,81,91,106,187],"Cores":[2,22,43,51,82,188],"achieve":[3,96,151,190],"high":[4,31,97],"performance":[5,135],"with":[6,30,83],"half-precision":[7],"matrix":[8],"inputs":[9],"tailored":[10],"towards":[11],"deep":[12],"learning":[13],"workloads.":[14],"However,":[15],"this":[16,35],"limits":[17],"the":[18,25,47,59,100,105,111,116,159,163,184,196],"application":[19],"of":[20,27,49,68,90,186],"especially":[23],"in":[24],"area":[26],"scientific":[28,54,139,175],"computing":[29,55,140,176],"precision":[32,60],"requirements.":[33,61],"In":[34],"paper,":[36],"we":[37],"build":[38],"Emulated":[39],"GEMM":[40],"on":[41,80,152,166,173,201],"(EGEMM-TC)":[44],"to":[45,52,74,95,103,114,129,195],"extend":[46],"usage":[48,185],"accelerate":[53],"applications":[56,177],"without":[57],"compromising":[58],"First,":[62],"EGEMM-TC":[63,86,123,149,181],"employs":[64],"an":[65],"extendable":[66],"workflow":[67],"hardware":[69],"profiling":[70],"and":[71,110,119,142,155,162,189],"operation":[72],"design":[73],"generate":[75],"a":[76,88,125],"lightweight":[77],"emulation":[78,117],"algorithm":[79],"extended-precision.":[84],"Second,":[85],"exploits":[87],"set":[89],"Core":[92,107],"kernel":[93],"optimizations":[94,113],"performance,":[98],"including":[99],"highly-efficient":[101],"tensorization":[102],"exploit":[104],"memory":[108,120],"architecture":[109],"instruction-level":[112],"coordinate":[115],"computation":[118],"access.":[121],"Third,":[122],"incorporates":[124],"hardware-aware":[126],"analytic":[127],"model":[128],"offer":[130],"large":[131],"flexibility":[132],"for":[133],"automatic":[134],"tuning":[136],"across":[137],"various":[138],"workloads":[141],"input":[143],"datasets.":[144],"Extensive":[145],"evaluations":[146],"show":[147],"that":[148,180],"can":[150,182],"average":[153],"3.13\u00d7":[154],"11.18\u00d7":[156],"speedup":[157,193],"over":[158],"cuBLAS":[160],"kernels":[161,165],"CUDA-SDK":[164],"CUDA":[167,202],"Cores,":[168],"respectively.":[169],"Our":[170],"case":[171],"study":[172],"several":[174],"further":[178],"confirms":[179],"generalize":[183],"about":[191],"1.8\u00d7":[192],"compared":[194],"hand-tuned,":[197],"highly-optimized":[198],"implementations":[199],"running":[200],"Cores.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2021-03-01T00:00:00"}