{"id":"https://openalex.org/W4391958657","doi":"https://doi.org/10.1145/3627535.3638471","title":"Tetris: Accelerating Sparse Convolution by Exploiting Memory Reuse on GPU","display_name":"Tetris: Accelerating Sparse Convolution by Exploiting Memory Reuse on GPU","publication_year":2024,"publication_date":"2024-02-20","ids":{"openalex":"https://openalex.org/W4391958657","doi":"https://doi.org/10.1145/3627535.3638471"},"language":"en","primary_location":{"id":"doi:10.1145/3627535.3638471","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627535.3638471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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/A5002821986","display_name":"Xiaoyan Liu","orcid":"https://orcid.org/0000-0003-1453-6642"},"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":"Xiaoyan Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1453-6642","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xuegui Zheng","orcid":"https://orcid.org/0009-0005-4635-7309"},"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":"Xuegui Zheng","raw_affiliation_strings":["Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-4635-7309","affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018705589","display_name":"Hailong Yang","orcid":"https://orcid.org/0000-0003-1101-7927"},"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/A5074183877","display_name":"Zhongzhi Luan","orcid":"https://orcid.org/0000-0002-7186-0556"},"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":"last","author":{"id":"https://openalex.org/A5079362609","display_name":"Depei Qian","orcid":"https://orcid.org/0000-0002-5382-1473"},"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":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":0.5259,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64468522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9954000115394592,"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"}},{"id":"https://openalex.org/T12676","display_name":"Machine Learning and ELM","score":0.9940000176429749,"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/speedup","display_name":"Speedup","score":0.8795663118362427},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8301122188568115},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6500762104988098},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6335924863815308},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6110996007919312},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5120595097541809},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4628746807575226},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4572981297969818},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4380406439304352},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42828547954559326},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4219997823238373},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.35317349433898926},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.33319807052612305},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28923875093460083},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2335023283958435},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1426323652267456}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8795663118362427},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8301122188568115},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6500762104988098},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6335924863815308},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6110996007919312},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5120595097541809},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4628746807575226},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4572981297969818},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4380406439304352},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42828547954559326},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4219997823238373},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35317349433898926},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33319807052612305},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28923875093460083},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2335023283958435},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1426323652267456},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"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/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"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/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":1,"locations":[{"id":"doi:10.1145/3627535.3638471","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3627535.3638471","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G4039879177","display_name":null,"funder_award_id":"U23B2020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5121250256","display_name":null,"funder_award_id":"2023YFB3001801","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5774836301","display_name":"\u9ad8\u6027\u80fd\u3001\u9ad8\u53ef\u6269\u5c55\u548c\u9ad8\u53ef\u79fb\u690d\u7684Stencil\u4ee3\u7801\u751f\u6210\u548c\u4f18\u5316\u6846\u67b6\u7814\u7a76","funder_award_id":"62072018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6139273093","display_name":null,"funder_award_id":"62322201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6466530554","display_name":null,"funder_award_id":"YWF-23-L-1121","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8014835415","display_name":null,"funder_award_id":"U22A2028","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1588915715","https://openalex.org/W1928489786","https://openalex.org/W2047547750","https://openalex.org/W2108598243","https://openalex.org/W2148570406","https://openalex.org/W2194775991","https://openalex.org/W2605739168","https://openalex.org/W2626696598","https://openalex.org/W2736230459","https://openalex.org/W2736953746","https://openalex.org/W2767274246","https://openalex.org/W2898106867","https://openalex.org/W2935849356","https://openalex.org/W2944008497","https://openalex.org/W2963122961","https://openalex.org/W2979439447","https://openalex.org/W3004543888","https://openalex.org/W3007757893","https://openalex.org/W3034368386","https://openalex.org/W3122598445","https://openalex.org/W3138154797","https://openalex.org/W3162542754","https://openalex.org/W3170485195","https://openalex.org/W3177452048","https://openalex.org/W3184606595","https://openalex.org/W3202303936","https://openalex.org/W3206453033","https://openalex.org/W4220701587","https://openalex.org/W4224319921","https://openalex.org/W4240168186","https://openalex.org/W4244330903","https://openalex.org/W4281658036","https://openalex.org/W4318540786","https://openalex.org/W4318541582"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476","https://openalex.org/W3157543420"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"success":[7],"in":[8],"various":[9],"application":[10],"fields.":[11],"Although":[12],"model":[13],"compression":[14],"techniques":[15],"mitigate":[16],"the":[17,25,76,85,107,136,140],"ever-increasing":[18],"resource":[19],"demands":[20],"of":[21,80,139],"large":[22],"CNN":[23],"models,":[24],"compressed":[26],"models":[27],"usually":[28],"exhibit":[29],"irregular":[30,108],"memory":[31,86,109],"access":[32],"and":[33,100,129,154],"unstructured":[34,113],"sparsity,":[35],"which":[36],"are":[37],"difficult":[38],"for":[39,70],"dominant":[40],"operators":[41],"such":[42,55],"as":[43,56],"sparse":[44,66,81,141],"convolution":[45,67,82,142,152],"to":[46,83,88,105,123,134],"achieve":[47],"expected":[48],"performance":[49,159],"speedup":[50],"on":[51],"popular":[52],"inference":[53],"platforms":[54],"GPU.":[57,71],"In":[58],"this":[59],"paper,":[60],"we":[61],"propose":[62],"Tetris,":[63],"an":[64],"efficient":[65],"approach":[68],"optimized":[69],"Tetris":[72,149],"first":[73],"fully":[74],"exploits":[75],"input":[77],"reuse":[78],"opportunity":[79],"reduce":[84],"accesses":[87,110],"global":[89],"memory.":[90],"It":[91,115],"then":[92],"adopts":[93],"a":[94,101,118,130],"stride":[95],"packed":[96],"filter":[97,119],"(SPF)":[98],"format":[99],"bank-sensing":[102],"reorganization":[103],"scheme":[104],"eliminate":[106],"caused":[111],"by":[112],"sparsity.":[114],"also":[116],"leverages":[117],"group":[120],"reorder":[121],"technique":[122],"address":[124],"load":[125],"imbalance":[126],"among":[127],"threads,":[128],"parameter":[131],"tuning":[132],"method":[133],"determine":[135],"optimal":[137],"parameters":[138],"implementation.":[143],"The":[144],"experiment":[145],"results":[146],"show":[147],"that":[148],"outperforms":[150],"dense/sparse":[151],"libraries":[153],"cutting-edge":[155],"implementations":[156],"with":[157],"promising":[158],"speedup.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}