{"id":"https://openalex.org/W4403407616","doi":"https://doi.org/10.1109/tcad.2024.3446718","title":"SpMMPlu-Pro: An Enhanced Compiler Plug-In for Efficient SpMM and Sparsity Propagation Algorithm","display_name":"SpMMPlu-Pro: An Enhanced Compiler Plug-In for Efficient SpMM and Sparsity Propagation Algorithm","publication_year":2024,"publication_date":"2024-08-20","ids":{"openalex":"https://openalex.org/W4403407616","doi":"https://doi.org/10.1109/tcad.2024.3446718"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2024.3446718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3446718","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":"https://openalex.org/A5102989014","display_name":"Shiyuan Huang","orcid":"https://orcid.org/0000-0002-8086-6802"},"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":"Shiyuan Huang","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, CHN"],"raw_orcid":"https://orcid.org/0000-0002-8086-6802","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, CHN","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017670541","display_name":"Fangxin Liu","orcid":"https://orcid.org/0000-0002-8769-293X"},"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":"Fangxin Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, CHN"],"raw_orcid":"https://orcid.org/0000-0002-8769-293X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, CHN","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065875464","display_name":"Tao Yang","orcid":"https://orcid.org/0000-0002-2276-4023"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["Huawei Technologies Company Ltd., Shenzhen, China","Huawei Technologies Co. Ltd, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Technologies Company Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Technologies Co. Ltd, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107269495","display_name":"Zongwu Wang","orcid":"https://orcid.org/0009-0003-2157-4927"},"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":"Zongwu Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, CHN"],"raw_orcid":"https://orcid.org/0009-0003-2157-4927","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, CHN","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030493839","display_name":"Ning Yang","orcid":"https://orcid.org/0009-0004-6964-8910"},"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":"Ning Yang","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, CHN"],"raw_orcid":"https://orcid.org/0009-0004-6964-8910","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, CHN","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053801300","display_name":"Li Jiang","orcid":"https://orcid.org/0000-0002-7353-8798"},"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":"Li Jiang","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, CHN"],"raw_orcid":"https://orcid.org/0000-0002-7353-8798","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, CHN","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3147,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.77500692,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"44","issue":"2","first_page":"669","last_page":"683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.9297000169754028,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11245","display_name":"Advanced Numerical Analysis Techniques","score":0.9297000169754028,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9003999829292297,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7889331579208374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7166502475738525},{"id":"https://openalex.org/keywords/plug-and-play","display_name":"Plug and play","score":0.5945567488670349},{"id":"https://openalex.org/keywords/plug-in","display_name":"Plug-in","score":0.572130560874939},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5363544225692749},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5250006914138794},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.26593780517578125},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19329306483268738}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7889331579208374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7166502475738525},{"id":"https://openalex.org/C2780070844","wikidata":"https://www.wikidata.org/wiki/Q857815","display_name":"Plug and play","level":2,"score":0.5945567488670349},{"id":"https://openalex.org/C4924752","wikidata":"https://www.wikidata.org/wiki/Q184148","display_name":"Plug-in","level":2,"score":0.572130560874939},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5363544225692749},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5250006914138794},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26593780517578125},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19329306483268738}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2024.3446718","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3446718","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G506747494","display_name":null,"funder_award_id":"No.18ZR1421400","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G5952030521","display_name":null,"funder_award_id":"62402311","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6491625391","display_name":null,"funder_award_id":"No. 61834006","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/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2009654791","https://openalex.org/W2126004407","https://openalex.org/W2590246587","https://openalex.org/W2794952988","https://openalex.org/W2898123186","https://openalex.org/W2914631005","https://openalex.org/W2964337156","https://openalex.org/W2980186997","https://openalex.org/W2999347085","https://openalex.org/W3016832937","https://openalex.org/W3081168214","https://openalex.org/W3090912412","https://openalex.org/W3091920657","https://openalex.org/W3122286897","https://openalex.org/W3130660608","https://openalex.org/W3132695675","https://openalex.org/W3139203094","https://openalex.org/W3159727696","https://openalex.org/W3177452048","https://openalex.org/W3204021316","https://openalex.org/W3206453033","https://openalex.org/W3212488865","https://openalex.org/W4200477077","https://openalex.org/W4206634569","https://openalex.org/W4214834240","https://openalex.org/W4255450819","https://openalex.org/W4285104934","https://openalex.org/W4293024985","https://openalex.org/W4307068480","https://openalex.org/W4312121047","https://openalex.org/W4312191446","https://openalex.org/W4312275547","https://openalex.org/W4327911434","https://openalex.org/W4383753658","https://openalex.org/W4386764318","https://openalex.org/W4393145428","https://openalex.org/W4393406920","https://openalex.org/W6738642365","https://openalex.org/W6751349269","https://openalex.org/W6761628794","https://openalex.org/W6766978945","https://openalex.org/W6776048684","https://openalex.org/W6781533629"],"related_works":["https://openalex.org/W47352601","https://openalex.org/W3025520020","https://openalex.org/W2095769150","https://openalex.org/W2279095528","https://openalex.org/W2352394813","https://openalex.org/W2360042170","https://openalex.org/W2368465758","https://openalex.org/W2064029199","https://openalex.org/W2108894446","https://openalex.org/W4223592178"],"abstract_inverted_index":{"Sparse":[0],"matrix-matrix":[1],"multiplication":[2],"(SpMM)":[3],"is":[4],"a":[5,99,138],"fundamental":[6],"operation":[7],"widely":[8],"used":[9],"in":[10,67],"deep":[11],"neural":[12,168],"networks":[13],"(DNNs)":[14],"and":[15,55,116,140,156,194,201,219,223,230,259],"high-performance":[16],"computing.":[17],"Many":[18],"compilation":[19],"studies":[20],"have":[21],"optimized":[22],"the":[23,35,51,61,72,110,133,148,154,161,173,192,203,208,226,256,268,273],"kernel":[24],"code":[25],"of":[26,53,150,163,176,247],"SpMM":[27,46,68],"to":[28,71,85,153,166,272],"achieve":[29],"better":[30],"performance":[31],"gains.":[32],"However,":[33],"on":[34,43,58,198,225,255,267],"one":[36,151],"hand,":[37,63],"these":[38,76],"efforts":[39],"often":[40],"focus":[41],"solely":[42],"optimizing":[44],"individual":[45],"operations,":[47],"without":[48],"fully":[49,131,159],"considering":[50],"influence":[52],"preceding":[54],"subsequent":[56],"operators":[57],"SpMM.":[59],"On":[60],"other":[62],"when":[64],"dense":[65,77,274],"regions":[66],"require":[69],"accumulation":[70,175],"same":[73],"output":[74],"location,":[75],"matrix":[78],"multiplications":[79],"must":[80],"be":[81],"executed":[82],"sequentially,":[83],"leading":[84],"significant":[86],"overhead":[87],"from":[88,128],"atomic":[89,180,204],"additions":[90],"or":[91,182],"thread":[92,183],"synchronization.":[93],"In":[94],"this":[95],"article,":[96],"we":[97,185],"propose":[98,186],"novel":[100],"compiler":[101],"plug-in":[102],"for":[103],"efficient":[104],"SpMM,":[105],"named":[106],"SpMMPlu-Pro.":[107],"SpMMPlu-Pro":[108,136,216,238],"inherits":[109],"sparse":[111,117,134],"intermediate":[112],"representation":[113,119],"(Sparse":[114],"IR)":[115],"pattern":[118],"[meta-operation":[120],"(meta-op)]":[121],"as":[122,124],"well":[123],"five":[125],"optimization":[126,205],"passes":[127],"SpMMPlu.":[129],"To":[130,171],"utilize":[132],"properties,":[135],"implements":[137],"forward":[139],"backward":[141],"cross-layer":[142],"sparsity":[143,149,165,241],"propagation":[144],"algorithm,":[145],"which":[146],"propagates":[147],"layer":[152],"front":[155],"back":[157],"layers,":[158],"releasing":[160],"potential":[162],"utilizing":[164],"accelerate":[167],"network":[169],"inference.":[170],"alleviate":[172],"inefficient":[174],"meta-ops":[177],"caused":[178],"by":[179],"addition":[181],"synchronization,":[184],"two":[187],"complementary":[188],"scheduling":[189],"schemes:":[190],"1)":[191],"segmentation":[193],"grouping":[195],"algorithm":[196],"based":[197],"automatic":[199],"search":[200],"2)":[202],"method":[206],"through":[207],"meta-op":[209],"data":[210],"flow":[211],"graph":[212],"restructure.":[213],"We":[214],"integrated":[215],"into":[217],"MindSpore":[218],"tested":[220],"its":[221],"effectiveness":[222],"scalability":[224],"NVIDIA":[227],"V100":[228,257],"GPU":[229,258],"Huawei":[231],"Ascend":[232,269],"910.":[233],"The":[234],"results":[235],"show":[236],"that":[237],"supports":[239],"various":[240],"patterns,":[242],"achieving":[243],"an":[244],"average":[245],"speedup":[246],"<inline-formula":[248,260],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[249,261],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[250,262],"<tex-math":[251,263],"notation=\"LaTeX\">$4.10\\times":[252],"$":[253,265],"</tex-math></inline-formula>":[254,266],"notation=\"LaTeX\">$4.35\\times":[264],"910":[270],"compared":[271],"counterpart.":[275]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}