{"id":"https://openalex.org/W2913790721","doi":"https://doi.org/10.1145/3293883.3295734","title":"A coordinated tiling and batching framework for efficient GEMM on GPUs","display_name":"A coordinated tiling and batching framework for efficient GEMM on GPUs","publication_year":2019,"publication_date":"2019-02-05","ids":{"openalex":"https://openalex.org/W2913790721","doi":"https://doi.org/10.1145/3293883.3295734","mag":"2913790721"},"language":"en","primary_location":{"id":"doi:10.1145/3293883.3295734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293883.3295734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming","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/A5114246744","display_name":"Xiuhong Li","orcid":"https://orcid.org/0000-0002-4896-121X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiuhong Li","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049910854","display_name":"Shengen Yan","orcid":"https://orcid.org/0009-0005-3858-7972"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengen Yan","raw_affiliation_strings":["SenseTime Incorporation"],"affiliations":[{"raw_affiliation_string":"SenseTime Incorporation","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066116482","display_name":"Liancheng Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liancheng Jia","raw_affiliation_strings":["Peking University"],"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042677362","display_name":"Yinghan Li","orcid":"https://orcid.org/0000-0001-5057-2347"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yinghan Li","raw_affiliation_strings":["SenseTime Incorporation"],"affiliations":[{"raw_affiliation_string":"SenseTime Incorporation","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114246744"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":9.8747,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.98759651,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9912999868392944,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9866999983787537,"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/computer-science","display_name":"Computer science","score":0.8216575980186462},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7433121204376221},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6693865656852722},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.60826575756073},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5550829172134399},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5168091058731079},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4777076244354248},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4534670114517212},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.37450671195983887},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3590467572212219},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1271461844444275},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08548828959465027}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8216575980186462},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7433121204376221},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6693865656852722},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.60826575756073},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5550829172134399},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5168091058731079},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4777076244354248},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4534670114517212},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.37450671195983887},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3590467572212219},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1271461844444275},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08548828959465027},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3293883.3295734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3293883.3295734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2216152324","display_name":null,"funder_award_id":"61672048 and 61520106004","funder_id":"https://openalex.org/F4320335595","funder_display_name":"National Natural Science Foundation of China-Yunnan Joint Fund"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335595","display_name":"National Natural Science Foundation of China-Yunnan Joint Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1667652561","https://openalex.org/W1863336885","https://openalex.org/W1978642402","https://openalex.org/W1982996921","https://openalex.org/W2041356909","https://openalex.org/W2084309410","https://openalex.org/W2090593986","https://openalex.org/W2093843662","https://openalex.org/W2099021415","https://openalex.org/W2101111919","https://openalex.org/W2134427337","https://openalex.org/W2152517358","https://openalex.org/W2194775991","https://openalex.org/W2232645663","https://openalex.org/W2279098554","https://openalex.org/W2346977986","https://openalex.org/W2499931820","https://openalex.org/W2512431201","https://openalex.org/W2580538010","https://openalex.org/W2605251767","https://openalex.org/W2617819327","https://openalex.org/W2618092901","https://openalex.org/W2619500264","https://openalex.org/W2766166018","https://openalex.org/W2769375938","https://openalex.org/W2773439083","https://openalex.org/W2786544209","https://openalex.org/W2889623620"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W3189307731","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1428699136","https://openalex.org/W1998560227","https://openalex.org/W2085873709","https://openalex.org/W2022772718"],"abstract_inverted_index":{"General":[0],"matrix":[1,31,65,91],"multiplication":[2],"(GEMM)":[3],"plays":[4],"a":[5,9,105,114],"paramount":[6],"role":[7],"in":[8,82],"broad":[10],"range":[11],"of":[12,74,107,120],"domains":[13],"such":[14],"as":[15],"deep":[16,87],"learning,":[17],"scientific":[18],"computing,":[19],"and":[20,35,40,69,76],"image":[21],"processing.":[22],"The":[23,43],"primary":[24],"optimization":[25],"method":[26],"is":[27,67,93],"to":[28,103],"partition":[29],"the":[30,37,48,64,90],"into":[32],"many":[33,83],"tiles":[34,75],"exploit":[36],"parallelism":[38],"within":[39],"between":[41],"tiles.":[42],"tiling":[44],"hierarchy":[45,50],"closely":[46],"mirrors":[47],"thread":[49],"on":[51],"GPUs.":[52],"In":[53],"practice,":[54],"GPUs":[55],"can":[56],"fully":[57],"unleash":[58],"its":[59],"computing":[60],"power":[61],"only":[62],"when":[63],"size":[66,92],"large":[68],"there":[70],"are":[71],"sufficient":[72],"number":[73],"workload":[77],"for":[78,118],"each":[79],"tile.":[80],"However,":[81],"real-world":[84],"applications":[85],"especially":[86],"learning":[88],"domain,":[89],"small.":[94],"To":[95],"this":[96],"end,":[97],"prior":[98],"work":[99],"proposes":[100],"batched":[101],"GEMM":[102],"process":[104],"group":[106],"small":[108],"independent":[109],"GEMMs":[110],"together":[111],"by":[112],"designing":[113],"single":[115],"CUDA":[116],"kernel":[117],"all":[119],"these":[121],"GEMMs.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":5}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}