{"id":"https://openalex.org/W4392450088","doi":"https://doi.org/10.1109/tcad.2024.3373592","title":"Hardware\u2013Software Co-Design Enabling Static and Dynamic Sparse Attention Mechanisms","display_name":"Hardware\u2013Software Co-Design Enabling Static and Dynamic Sparse Attention Mechanisms","publication_year":2024,"publication_date":"2024-03-05","ids":{"openalex":"https://openalex.org/W4392450088","doi":"https://doi.org/10.1109/tcad.2024.3373592"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2024.3373592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3373592","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/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":true,"raw_author_name":"Jieru Zhao","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112496192","display_name":"P.Y. Zeng","orcid":"https://orcid.org/0009-0005-2319-7859"},"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":"Pai Zeng","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043486076","display_name":"Guan Shen","orcid":"https://orcid.org/0000-0002-1264-8715"},"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":"Guan Shen","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377840","display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-5832-0347"},"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":"Quan Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039318240","display_name":"Minyi Guo","orcid":"https://orcid.org/0000-0003-0034-2302"},"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":"Minyi Guo","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5047571832"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":8.0614,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.98502247,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"43","issue":"9","first_page":"2783","last_page":"2796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.996399998664856,"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":0.996399998664856,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9851999878883362,"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/computer-science","display_name":"Computer science","score":0.715212881565094},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5241101980209351},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5148748159408569},{"id":"https://openalex.org/keywords/co-design","display_name":"Co-design","score":0.4869335889816284},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3921813368797302},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3788427710533142},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.345039963722229},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18291547894477844}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715212881565094},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5241101980209351},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5148748159408569},{"id":"https://openalex.org/C180962459","wikidata":"https://www.wikidata.org/wiki/Q1038171","display_name":"Co-design","level":2,"score":0.4869335889816284},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3921813368797302},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3788427710533142},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.345039963722229},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18291547894477844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2024.3373592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3373592","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":[],"awards":[{"id":"https://openalex.org/G5813330169","display_name":null,"funder_award_id":"62102249","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8136545603","display_name":null,"funder_award_id":"62232015","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1983394510","https://openalex.org/W2141389982","https://openalex.org/W2889048825","https://openalex.org/W2896457183","https://openalex.org/W2915716523","https://openalex.org/W2923014074","https://openalex.org/W2963748441","https://openalex.org/W2970106668","https://openalex.org/W2970777192","https://openalex.org/W2979826702","https://openalex.org/W2980282514","https://openalex.org/W3015468748","https://openalex.org/W3047848469","https://openalex.org/W3094502228","https://openalex.org/W3096567388","https://openalex.org/W3096609285","https://openalex.org/W3106298483","https://openalex.org/W3131922516","https://openalex.org/W3139633126","https://openalex.org/W3159727696","https://openalex.org/W3173787059","https://openalex.org/W3176714321","https://openalex.org/W3205192296","https://openalex.org/W3206453033","https://openalex.org/W3211525823","https://openalex.org/W4214686755","https://openalex.org/W4280582299","https://openalex.org/W4293025165","https://openalex.org/W4295838474","https://openalex.org/W4296473245","https://openalex.org/W4308083526","https://openalex.org/W4313007769","https://openalex.org/W4323654151","https://openalex.org/W4360831795","https://openalex.org/W4363671827","https://openalex.org/W4375928954","https://openalex.org/W4380881077","https://openalex.org/W4384648639","https://openalex.org/W4385245566","https://openalex.org/W6754279437","https://openalex.org/W6755207826","https://openalex.org/W6761628794","https://openalex.org/W6763509872","https://openalex.org/W6766978945","https://openalex.org/W6768817161","https://openalex.org/W6770018571","https://openalex.org/W6771070734","https://openalex.org/W6771626834","https://openalex.org/W6774418012","https://openalex.org/W6776048684","https://openalex.org/W6778883912","https://openalex.org/W6781533629","https://openalex.org/W6838276489","https://openalex.org/W6852252866","https://openalex.org/W6854308872"],"related_works":["https://openalex.org/W2115140794","https://openalex.org/W2041120224","https://openalex.org/W1504320321","https://openalex.org/W2067902980","https://openalex.org/W2548529098","https://openalex.org/W4312275919","https://openalex.org/W2338293335","https://openalex.org/W2039378765","https://openalex.org/W2614685449","https://openalex.org/W283879968"],"abstract_inverted_index":{"The":[0,179],"attention":[1,26,40,89,109],"mechanisms":[2,90],"of":[3,17,81],"transformers":[4],"effectively":[5],"extract":[6],"pertinent":[7],"information":[8],"from":[9],"the":[10,14,35],"input":[11,150],"sequence.":[12],"However,":[13,64],"quadratic":[15,36],"complexity":[16,37],"self-attention":[18],"incurs":[19],"heavy":[20],"computational":[21],"and":[22,31,44,48,56,86,106,111,119,138,152,166],"memory":[23],"burdens.":[24],"Sparse":[25],"techniques,":[27],"including":[28],"both":[29],"static":[30,47,85,105,144],"dynamic":[32,49,87,107,172],"sparsity,":[33],"reduce":[34],"by":[38],"computing":[39],"on":[41,146,174],"partial":[42],"queries":[43],"keys.":[45],"These":[46],"methods":[50],"exhibit":[51],"a":[52,98],"trade-off":[53],"between":[54],"efficiency":[55],"adaptability,":[57],"making":[58],"them":[59,82],"applicable":[60],"to":[61,115,131,159],"different":[62],"scenarios.":[63],"existing":[65],"accelerators":[66],"either":[67],"target":[68],"specific":[69],"domains":[70],"or":[71],"encounter":[72],"performance":[73],"degradation":[74],"when":[75],"dealing":[76],"with":[77,148,176],"long":[78,149],"sequences.":[79,178],"None":[80],"can":[83,112],"enable":[84],"sparse":[88,108],"simultaneously.":[91],"To":[92],"this":[93],"end,":[94],"we":[95],"propose":[96],"SALO2,":[97],"hardware-software":[99],"co-design":[100],"framework":[101],"that":[102,123],"facilitates":[103],"efficient":[104],"computations":[110],"be":[113],"applied":[114],"various":[116],"scenarios,":[117],"tasks,":[118],"inputs.":[120],"Experiments":[121],"show":[122],"SALO2":[124],"achieves":[125,153],"104.80x,":[126],"13.65x,":[127],"1.38x":[128],"speedup":[129,157],"compared":[130,158],"Intel":[132,160],"Xeon":[133,161],"CPU,":[134,162],"NVIDIA":[135,163],"RTX4090":[136,164],"GPU,":[137,165],"SALO":[139],"(the":[140,168],"SOTA":[141,169],"accelerator":[142,170],"exploiting":[143,171],"sparsity)":[145,173],"tasks":[147,175],"sequences,":[151],"76.17x,":[154],"8.98x,":[155],"1.71x":[156],"Sanger":[167],"shorter":[177],"source":[180],"code":[181],"is":[182],"available":[183],"at":[184],"https://github.com/sjtu-zhao-lab/SALO.githttps://github.com/sjtu-zhao-lab/SALO.git.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}