{"id":"https://openalex.org/W4405440056","doi":"https://doi.org/10.1109/tcad.2024.3518413","title":"Enabling Efficient Sparse Multiplications on GPUs With Heuristic Adaptability","display_name":"Enabling Efficient Sparse Multiplications on GPUs With Heuristic Adaptability","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4405440056","doi":"https://doi.org/10.1109/tcad.2024.3518413"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2024.3518413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3518413","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-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":null,"display_name":"Jiaming Xu","orcid":"https://orcid.org/0009-0000-7000-6537"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming Xu","raw_affiliation_strings":["Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-7000-6537","affiliations":[{"raw_affiliation_string":"Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shan Huang","orcid":"https://orcid.org/0009-0005-2012-8540"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Huang","raw_affiliation_strings":["Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-2012-8540","affiliations":[{"raw_affiliation_string":"Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068894182","display_name":"Jinhao Li","orcid":"https://orcid.org/0009-0009-4286-6359"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinhao Li","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-4286-6359","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078367183","display_name":"Guyue Huang","orcid":"https://orcid.org/0000-0002-1280-4781"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Guyue Huang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385336","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-2093-1788"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, China"],"raw_orcid":"https://orcid.org/0000-0003-2093-1788","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic and Computer Engineering, Hong Kong University of Science and Technology, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6108-5157","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102805465","display_name":"Guohao Dai","orcid":"https://orcid.org/0000-0002-8464-0130"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohao Dai","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8464-0130","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7901,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.72976553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"44","issue":"6","first_page":"2226","last_page":"2239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9919999837875366,"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":0.9919999837875366,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9843999743461609,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.9789999723434448,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/adaptability","display_name":"Adaptability","score":0.8311693072319031},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6587648391723633},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.632262647151947},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6208299398422241},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3938680589199066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20030122995376587}],"concepts":[{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.8311693072319031},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6587648391723633},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.632262647151947},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6208299398422241},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3938680589199066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20030122995376587},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcad.2024.3518413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3518413","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-146871","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-146871","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":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G2045798616","display_name":null,"funder_award_id":"62325405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6121003335","display_name":null,"funder_award_id":"24QB2706200","funder_id":"https://openalex.org/F4320327803","funder_display_name":"Shanghai Rising-Star Program"},{"id":"https://openalex.org/G6803541034","display_name":null,"funder_award_id":"U21B2031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8262591375","display_name":null,"funder_award_id":"62104128","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327803","display_name":"Shanghai Rising-Star Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1482680420","https://openalex.org/W1820389309","https://openalex.org/W2088866486","https://openalex.org/W2128853364","https://openalex.org/W2301386596","https://openalex.org/W2767274246","https://openalex.org/W2808128431","https://openalex.org/W2887822915","https://openalex.org/W2914631005","https://openalex.org/W2921480401","https://openalex.org/W2951135776","https://openalex.org/W2964337156","https://openalex.org/W2964357930","https://openalex.org/W2999347085","https://openalex.org/W3090912412","https://openalex.org/W3108012228","https://openalex.org/W3129727110","https://openalex.org/W3130660608","https://openalex.org/W3132695675","https://openalex.org/W3157531038","https://openalex.org/W4247828381","https://openalex.org/W4327911434","https://openalex.org/W4395106472","https://openalex.org/W4401090539","https://openalex.org/W4404401018","https://openalex.org/W6677580257","https://openalex.org/W6726873649","https://openalex.org/W6736126653","https://openalex.org/W6751349269","https://openalex.org/W6760045743","https://openalex.org/W6763341371","https://openalex.org/W6810665531","https://openalex.org/W6848451824"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2357124094","https://openalex.org/W2387399993","https://openalex.org/W2389739210","https://openalex.org/W2348924972","https://openalex.org/W2365736347","https://openalex.org/W2047454415","https://openalex.org/W2070040999"],"abstract_inverted_index":{"Sparse":[0],"matrix-vector/matrix":[1],"multiplication,":[2,286],"namely":[3],"SpMMul,":[4],"has":[5],"become":[6],"a":[7,142,196,221],"fundamental":[8],"operation":[9],"during":[10],"model":[11,198],"inference":[12],"in":[13,47,60,71,149],"various":[14,204],"domains.":[15],"Previous":[16,43,117],"studies":[17,118],"have":[18],"explored":[19],"numerous":[20],"optimizations":[21],"to":[22,26,103,107,199,289,313],"accelerate":[23],"it.":[24],"However,":[25],"enable":[27,200],"efficient":[28,102],"end-to-end":[29],"inference,":[30],"the":[31,52,68,136,185,214,299],"following":[32],"challenges":[33],"remain":[34],"unsolved:":[35],"1)":[36,154],"incomplete":[37],"design":[38,156,171,195],"space":[39,54,157],"and":[40,50,73,92,111,131,162,177,206,219,234,236,249,260,268,283,287],"time-consuming":[41],"preprocessing.":[42,166],"methods":[44],"optimize":[45],"SpMMul":[46,148],"limited":[48],"loops":[49],"neglect":[51],"potential":[53],"exploration":[55],"for":[56,147,279],"further":[57],"optimization,":[58],"resulting":[59],">30%":[61],"waste":[62],"of":[63,225,241],"computing":[64],"power.":[65],"In":[66],"addition,":[67],"preprocessing":[69],"overhead":[70],"SparseTIR":[72],"DTC-SpMM":[74],"is":[75],"<inline-formula":[76,242,250,261,269,290,314],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[77,243,251,262,270,291,315],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[78,244,252,263,271,292,316],"<tex-math":[79,245,253,264,272,293,317],"notation=\"LaTeX\">$1000\\times":[80],"$":[81,247,255,266,274,295,319],"</tex-math></inline-formula>":[82,248,256,267,275,296,320],"larger":[83],"than":[84],"sparse":[85,280,284],"computing;":[86],"2)":[87,188],"incompatibility":[88],"between":[89],"static":[90,96],"dataflow":[91,97],"dynamic":[93],"input.":[94],"A":[95],"can":[98],"not":[99],"always":[100],"be":[101],"all":[104,226],"input,":[105],"leading":[106],">80%":[108],"performance":[109,115,121,210,223],"loss;":[110],"3)":[112,207],"simplistic":[113],"algorithm":[114,191,201,209],"analysis.":[116,211],"primarily":[119],"analyze":[120],"from":[122,216],"algorithmic":[123],"advantages,":[124],"without":[125,165],"considering":[126,203],"other":[127],"aspects":[128],"like":[129],"hardware":[130],"data":[132],"features.":[133],"To":[134],"tackle":[135],"above":[137],"challenges,":[138],"we":[139],"present":[140,220],"DA-SpMMul,":[141],"Data-Aware":[143],"heuristic":[144,197],"GPU":[145],"implementation":[146],"multiplatforms.":[150],"DA-SpMMul":[151,228,310],"creatively":[152],"proposes:":[153],"complete":[155],"based":[158,173],"on":[159,174,181,231,322],"theoretical":[160,175],"computations":[161,176],"nontrivial":[163,179],"implementations":[164,180],"We":[167,194,212],"propose":[168],"three":[169],"orthogonal":[170],"principles":[172],"provide":[178],"standard":[182],"formats,":[183],"eliminating":[184],"complex":[186],"preprocessing;":[187],"feature-enabled":[189],"adaptive":[190],"selection":[192,202],"mechanism.":[193],"features;":[205],"comprehensive":[208,222],"extract":[213],"features":[215],"multiple":[217],"perspectives":[218],"analysis":[224],"algorithms.":[227],"supports":[229],"PyTorch":[230],"both":[232],"NVIDIA":[233,258],"AMD":[235,277],"achieves":[237,311],"an":[238],"average":[239],"speedup":[240,297,321],"notation=\"LaTeX\">$3.33\\times":[246],"notation=\"LaTeX\">$3.02\\times":[254],"over":[257,276],"cuSPARSE,":[259],"notation=\"LaTeX\">$12.05\\times":[265],"notation=\"LaTeX\">$8.32\\times":[273],"rocSPARSE":[278],"matrix-vector":[281],"multiplication":[282],"matrix-matrix":[285],"up":[288,312],"notation=\"LaTeX\">$1.48\\times":[294],"against":[298],"state-of-the-art":[300],"open-source":[301],"algorithm.":[302],"Integrated":[303],"with":[304],"graph":[305],"neural":[306],"network":[307],"framework,":[308],"PyG,":[309],"notation=\"LaTeX\">$1.22\\times":[318],"GCN":[323],"inference.":[324]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}
