{"id":"https://openalex.org/W7125940833","doi":"https://doi.org/10.1145/3774934.3786441","title":"Exploiting Efficient Mapping and Pipelined Execution for Accelerating SpMV on Tensor Cores","display_name":"Exploiting Efficient Mapping and Pipelined Execution for Accelerating SpMV on Tensor Cores","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7125940833","doi":"https://doi.org/10.1145/3774934.3786441"},"language":null,"primary_location":{"id":"doi:10.1145/3774934.3786441","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774934.3786441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"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/A5052897340","display_name":"Kaige Zhang","orcid":"https://orcid.org/0009-0000-3261-3483"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaige Zhang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-3261-3483","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120892615","display_name":"Hailong Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Yang","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1101-7927","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683033","display_name":"Xin You","orcid":"https://orcid.org/0000-0002-5163-4607"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin You","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5163-4607","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianyu Feng","orcid":"https://orcid.org/0000-0002-4830-5482"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyu Feng","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4830-5482","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120935885","display_name":"Yufan Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yufan Xu","raw_affiliation_strings":["Independent Researcher, Cupertino, USA"],"raw_orcid":"https://orcid.org/0000-0002-7787-6460","affiliations":[{"raw_affiliation_string":"Independent Researcher, Cupertino, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120891728","display_name":"Zhongzhi Luan","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongzhi Luan","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7186-0556","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124077592","display_name":"Yi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1829-2817","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062397627","display_name":"D. Fanyue Qian","orcid":null},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Depei Qian","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5382-1473","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08791209,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"245","last_page":"258"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.4480000138282776,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.4480000138282776,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.3828999996185303,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.027799999341368675,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6884999871253967},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6080999970436096},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6021999716758728},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5996000170707703},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4934000074863434},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.453900009393692},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.3671000003814697},{"id":"https://openalex.org/keywords/addressing-mode","display_name":"Addressing mode","score":0.3400999903678894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8460999727249146},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6884999871253967},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6080999970436096},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6021999716758728},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5996000170707703},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5835999846458435},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4934000074863434},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C16901944","wikidata":"https://www.wikidata.org/wiki/Q367183","display_name":"Addressing mode","level":4,"score":0.3400999903678894},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.32850000262260437},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2793000042438507},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C2982832238","wikidata":"https://www.wikidata.org/wiki/Q5531640","display_name":"General purpose","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774934.3786441","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3774934.3786441","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2002555321","https://openalex.org/W2069479716","https://openalex.org/W2073364718","https://openalex.org/W2469279958","https://openalex.org/W2887161653","https://openalex.org/W2921480401","https://openalex.org/W2999347085","https://openalex.org/W3043303806","https://openalex.org/W3090369187","https://openalex.org/W3130554079","https://openalex.org/W3132532188","https://openalex.org/W3175189837","https://openalex.org/W3204140704","https://openalex.org/W4286635279","https://openalex.org/W4309672181","https://openalex.org/W4310563332","https://openalex.org/W4321466355","https://openalex.org/W4321466385","https://openalex.org/W4321636675","https://openalex.org/W4388562477","https://openalex.org/W4388661983","https://openalex.org/W4388667495","https://openalex.org/W4395106472","https://openalex.org/W4400409880","https://openalex.org/W4401408710","https://openalex.org/W4401409142","https://openalex.org/W4403278125","https://openalex.org/W4405756173","https://openalex.org/W4406548153","https://openalex.org/W4410321937","https://openalex.org/W7106674515"],"related_works":[],"abstract_inverted_index":{"Sparse":[0],"matrix-vector":[1],"multiplication":[2],"(SpMV)":[3],"is":[4],"a":[5,95,111,118,127,171],"fundamental":[6],"operation":[7],"in":[8,24],"scientific":[9],"computing,":[10],"machine":[11],"learning,":[12],"and":[13,55,62,70,92,105,153,159,178,184],"graph":[14],"analytics,":[15],"demanding":[16],"efficient":[17,101],"execution":[18],"on":[19,85,138,157,182],"modern":[20],"hardware.":[21],"Recent":[22],"advances":[23],"hardware":[25,134],"accelerators,":[26],"such":[27],"as":[28,124,126],"Tensor":[29,43,73,86,102,113],"Cores,":[30,87],"have":[31],"significantly":[32],"improved":[33],"the":[34,56,81,165],"performance":[35,69,90,172],"of":[36,72,174],"many":[37],"compute-intensive":[38],"workloads.":[39],"However,":[40],"effectively":[41],"utilizing":[42],"Cores":[44],"for":[45,98],"SpMV":[46,83,99,167],"remains":[47],"challenging":[48],"due":[49],"to":[50,67,131,164],"its":[51],"irregular":[52],"sparsity":[53],"patterns":[54],"mismatch":[57],"between":[58],"SpMV\u2019s":[59],"computational":[60],"characteristics":[61],"constrained":[63],"architecture":[64],"design,":[65],"leading":[66],"suboptimal":[68],"underutilization":[71],"Cores.":[74],"In":[75],"this":[76],"paper,":[77],"we":[78],"systematically":[79],"analyze":[80],"state-of-the-art":[82,166],"optimizations":[84],"identify":[88],"key":[89],"bottlenecks,":[91],"propose":[93],"Drawloom,":[94],"Tensor-Core-aware":[96],"framework":[97],"with":[100,117],"Core":[103,114],"mapping":[104,115],"optimized":[106],"pipeline":[107,130],"execution.":[108],"Drawloom":[109,143,169],"leverages":[110],"redesigned":[112],"strategy":[116],"zig-zag":[119],"chained":[120],"sparse":[121],"storage":[122],"format,":[123],"well":[125],"multi-stage":[128],"register":[129],"better":[132],"exploit":[133],"parallelism.":[135],"Our":[136],"evaluation":[137],"SuiteSparse":[139],"dataset":[140],"demonstrates":[141],"that":[142],"outperforms":[144],"cuSPARSE":[145],"by":[146],"2.71\u00d7/1.90\u00d7":[147],"(in":[148,151,155,176,180],"FP16),":[149],"2.95\u00d7/2.39\u00d7":[150],"FP32),":[152],"2.47\u00d7/1.54\u00d7":[154],"FP64)":[156,181],"A100":[158,183],"H100":[160,185],"GPUs,":[161,186],"respectively.":[162,187],"Compared":[163],"implementations,":[168],"achieves":[170],"speedup":[173],"1.26\u00d7/1.18\u00d7":[175],"FP16)":[177],"1.49\u00d7/1.56\u00d7":[179]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-01-29T00:00:00"}