{"id":"https://openalex.org/W4386764318","doi":"https://doi.org/10.1109/dac56929.2023.10247957","title":"SpMMPlu: A Compiler Plug-in with Sparse IR for Efficient Sparse Matrix Multiplication","display_name":"SpMMPlu: A Compiler Plug-in with Sparse IR for Efficient Sparse Matrix Multiplication","publication_year":2023,"publication_date":"2023-07-09","ids":{"openalex":"https://openalex.org/W4386764318","doi":"https://doi.org/10.1109/dac56929.2023.10247957"},"language":"en","primary_location":{"id":"doi:10.1109/dac56929.2023.10247957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac56929.2023.10247957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 60th ACM/IEEE Design Automation Conference (DAC)","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/A5022287798","display_name":"Tao Yang","orcid":"https://orcid.org/0000-0001-8588-9483"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]},{"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/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]}],"countries":["CN","GB"],"is_corresponding":true,"raw_author_name":"Tao Yang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Huawei Technologies Co., Ltd","Shanghai Qi Zhi Institute, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018885973","display_name":"Yiyuan Zhou","orcid":"https://orcid.org/0000-0002-5463-5429"},"institutions":[{"id":"https://openalex.org/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]},{"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","GB"],"is_corresponding":false,"raw_author_name":"Yiyuan Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China","Huawei Technologies Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035380772","display_name":"Qidong Tang","orcid":null},"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":"Qidong Tang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432905","display_name":"Feng Xu","orcid":"https://orcid.org/0000-0002-7966-818X"},"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/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]}],"countries":["CN","GB"],"is_corresponding":false,"raw_author_name":"Feng Xu","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Huawei Technologies Co., Ltd","Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032840693","display_name":"Hui Ma","orcid":"https://orcid.org/0000-0002-5272-8226"},"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":"Hui Ma","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047571832","display_name":"Jieru Zhao","orcid":"https://orcid.org/0000-0001-8211-2812"},"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":"Jieru Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","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/I4210160618","display_name":"Huawei Technologies (United Kingdom)","ror":"https://ror.org/056gzgs71","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210160618"]},{"id":"https://openalex.org/I4210122302","display_name":"ShangHai JiAi Genetics & IVF Institute","ror":"https://ror.org/02rgbry52","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210122302"]},{"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","GB"],"is_corresponding":false,"raw_author_name":"Li Jiang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Qi Zhi Institute, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China","MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","Huawei Technologies Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Qi Zhi Institute, Shanghai, China","institution_ids":["https://openalex.org/I4210122302"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Huawei Technologies Co., Ltd","institution_ids":["https://openalex.org/I4210160618"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5022287798"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I4210122302","https://openalex.org/I4210160618"],"apc_list":null,"apc_paid":null,"fwci":0.9272,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72079146,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9973000288009644,"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":0.9973000288009644,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9954000115394592,"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"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8619227409362793},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6299406886100769},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6028029918670654},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.567134439945221},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5443827509880066},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5199664831161499},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.47986477613449097},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09153565764427185}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8619227409362793},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6299406886100769},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6028029918670654},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.567134439945221},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5443827509880066},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5199664831161499},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.47986477613449097},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09153565764427185},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dac56929.2023.10247957","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac56929.2023.10247957","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 60th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2276892413","https://openalex.org/W2285660444","https://openalex.org/W2625457103","https://openalex.org/W2804032941","https://openalex.org/W2883603666","https://openalex.org/W2963000224","https://openalex.org/W3005658451","https://openalex.org/W3015468748","https://openalex.org/W3019166713","https://openalex.org/W3081168214","https://openalex.org/W3091920657","https://openalex.org/W3122286897","https://openalex.org/W3130660608","https://openalex.org/W3133862166","https://openalex.org/W3159727696","https://openalex.org/W3177452048","https://openalex.org/W3206453033","https://openalex.org/W4200477077","https://openalex.org/W4287704453","https://openalex.org/W4295312788","https://openalex.org/W4323654151","https://openalex.org/W6725543821","https://openalex.org/W6751349269","https://openalex.org/W6753553560","https://openalex.org/W6761628794","https://openalex.org/W6766978945","https://openalex.org/W6776048684","https://openalex.org/W6781533629","https://openalex.org/W6791447287","https://openalex.org/W6803284503"],"related_works":["https://openalex.org/W1515810787","https://openalex.org/W2293771254","https://openalex.org/W3121828480","https://openalex.org/W2039875226","https://openalex.org/W4221142455","https://openalex.org/W2032786851","https://openalex.org/W2914631005","https://openalex.org/W2952630098","https://openalex.org/W3132517792","https://openalex.org/W4285148873"],"abstract_inverted_index":{"Sparsity":[0],"is":[1,23,72,112],"becoming":[2],"arguably":[3],"the":[4,69,89,120,137,145,257],"most":[5],"critical":[6],"dimension":[7],"to":[8,27,48,180,197,223,256],"explore":[9],"for":[10,59,94,164,186,202],"efficiency":[11],"and":[12,33,63,91,144,168,212,219,227,241,248],"scalability":[13],"as":[14,140],"deep":[15,98],"learning":[16,99],"models":[17],"grow":[18],"significantly":[19],"larger.":[20],"Particularly,":[21],"pruning":[22],"a":[24,81,113,130,174,243],"common":[25],"method":[26,179],"reduce":[28],"redundant":[29],"computations":[30],"in":[31,96,155,158,195],"attention-based":[32],"convolution-based":[34],"models.":[35],"The":[36,108,229],"induced":[37],"sparse":[38],"matrix":[39,106],"multiplication":[40],"(SpMM)":[41],"normally":[42],"requires":[43],"domain-specific":[44],"hardware":[45,70,138],"architecture":[46,71],"(DSA)":[47],"eliminate":[49],"unnecessary":[50],"zero-valued":[51],"computations.":[52],"However,":[53],"generating":[54],"an":[55,74,182,199],"optimal":[56],"kernel":[57,204],"code":[58,169,205],"SpMM":[60,95,121,203],"on":[61,127,215],"general-purpose":[62],"ISA-based":[64],"spatial":[65],"accelerators":[66],"without":[67],"changing":[68],"still":[73],"open":[75],"problem.In":[76],"this":[77],"paper,":[78],"we":[79,172],"propose":[80,173],"compiler":[82,100,151],"plug-in":[83],"named":[84],"SpMMPlu,":[85,234],"which":[86],"can":[87,160,236],"extend":[88],"representation":[90],"optimization":[92],"ability":[93],"current":[97],"frameworks":[101],"that":[102,232],"only":[103],"support":[104,237],"dense":[105,258],"multiplication.":[107],"key":[109],"of":[110,136,148],"SpMMPlu":[111,196,209],"flexible":[114],"intermediate":[115],"representation\u2014":[116],"Sparse":[117,184],"IR,":[118],"representing":[119],"with":[122,129,233],"various":[123,238],"sparsity":[124,188,239],"patterns":[125,240],"based":[126],"meta-ops":[128],"multi-level":[131],"structure.":[132],"Meta-op":[133],"takes":[134],"abstraction":[135],"intrinsic":[139],"its":[141,165,225],"minimum":[142],"granularity,":[143],"powerful":[146],"optimizers":[147],"existing":[149],"NN":[150],"backends":[152],"(e.g.,":[153],"Auto-schedule":[154],"TVM,":[156],"AKG":[157],"MindSpore)":[159],"be":[161],"easily":[162],"reused":[163],"computational":[166],"scheduling":[167],"generation.":[170,206],"Moreover,":[171],"two-step":[175],"(segmentation":[176],"&":[177],"grouping)":[178],"achieve":[181],"efficient":[183],"IR":[185],"each":[187],"pattern.":[189],"Only":[190],"three":[191],"passes":[192],"are":[193],"added":[194],"provide":[198],"automatic":[200],"solution":[201],"We":[207],"embed":[208],"into":[210],"MindSpore":[211,235],"do":[213],"experiments":[214],"NVIDIA":[216],"V100":[217,246],"GPU":[218],"Huawei":[220],"Ascend":[221],"910":[222],"verify":[224],"effectiveness":[226],"scalability.":[228],"results":[230],"show":[231],"deliver":[242],"1.93\u00d7":[244],"(on":[245,250],"GPU)":[247],"2.21\u00d7":[249],"AScend":[251],"910)":[252],"speedup":[253],"averagely":[254],"compared":[255],"counterpart.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}