{"id":"https://openalex.org/W4403636247","doi":"https://doi.org/10.1109/tc.2024.3483633","title":"Allspark: Workload Orchestration for Visual Transformers on Processing In-Memory Systems","display_name":"Allspark: Workload Orchestration for Visual Transformers on Processing In-Memory Systems","publication_year":2024,"publication_date":"2024-10-22","ids":{"openalex":"https://openalex.org/W4403636247","doi":"https://doi.org/10.1109/tc.2024.3483633"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2024.3483633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3483633","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","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/A5094246411","display_name":"Mengke Ge","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mengke Ge","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669438","display_name":"Junpeng Wang","orcid":"https://orcid.org/0000-0002-8810-3172"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junpeng Wang","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111154158","display_name":"Binhan Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binhan Chen","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113152317","display_name":"Yingjian Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingjian Zhong","raw_affiliation_strings":["Anhui University, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100549009","display_name":"Haitao Du","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitao Du","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China (USTC), Hefei, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China (USTC), Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423614","display_name":"Song Chen","orcid":"https://orcid.org/0000-0003-0341-3428"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Chen","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103907350","display_name":"Yi Kang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Kang","raw_affiliation_strings":["Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5094246411"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9653,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75850044,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"74","issue":"2","first_page":"427","last_page":"441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9894000291824341,"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":0.9894000291824341,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9815999865531921,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.98089998960495,"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":0.7861957550048828},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6050349473953247},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.5934092998504639},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3582949638366699},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3393342196941376},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2596592903137207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7861957550048828},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6050349473953247},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.5934092998504639},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3582949638366699},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3393342196941376},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2596592903137207},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2024.3483633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2024.3483633","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1085865041","display_name":null,"funder_award_id":"92473114","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2034861439","https://openalex.org/W2097577132","https://openalex.org/W2118231264","https://openalex.org/W2605347906","https://openalex.org/W2606722458","https://openalex.org/W2794532328","https://openalex.org/W2935331687","https://openalex.org/W2940862705","https://openalex.org/W2980104813","https://openalex.org/W3085277063","https://openalex.org/W3094502228","https://openalex.org/W3097528158","https://openalex.org/W3100710793","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3159727696","https://openalex.org/W3192336523","https://openalex.org/W3213412675","https://openalex.org/W4213019189","https://openalex.org/W4214686755","https://openalex.org/W4220972538","https://openalex.org/W4221001402","https://openalex.org/W4239722617","https://openalex.org/W4280496502","https://openalex.org/W4280562683","https://openalex.org/W4285601701","https://openalex.org/W4297097426","https://openalex.org/W4311609527","https://openalex.org/W4313007769","https://openalex.org/W4323519269","https://openalex.org/W4360831795","https://openalex.org/W4380881063","https://openalex.org/W4380881077","https://openalex.org/W4385192563","https://openalex.org/W4385245566","https://openalex.org/W4389692499","https://openalex.org/W6788001715","https://openalex.org/W6794345597","https://openalex.org/W6796237581","https://openalex.org/W6803680838","https://openalex.org/W6850927664"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W79913212","https://openalex.org/W2094884983","https://openalex.org/W2378898096","https://openalex.org/W560952460","https://openalex.org/W2290927522","https://openalex.org/W4283579741","https://openalex.org/W3066706303"],"abstract_inverted_index":{"The":[0],"advent":[1],"of":[2,117,149,187,242,248],"Transformers":[3,101,228],"has":[4],"revolutionized":[5],"computer":[6],"vision,":[7],"offering":[8],"a":[9,53,121,130,154,178],"powerful":[10],"alternative":[11],"to":[12,56,111,201,232],"convolutional":[13],"neural":[14],"networks":[15],"(CNNs),":[16],"especially":[17],"with":[18,59,82,136],"the":[19,30,63,114,147,150,184,191,195],"local":[20,27],"attention":[21],"mechanism":[22],"that":[23,214],"excels":[24],"at":[25,106],"capturing":[26],"structures":[28],"within":[29],"input":[31],"and":[32,47,128,133,140,198,245],"achieve":[33],"state-of-the-art":[34],"performance.":[35],"Processing":[36],"in-memory":[37],"(PIM)":[38],"architecture":[39],"offers":[40],"extensive":[41],"parallelism,":[42],"low":[43],"data":[44,138,142,169],"movement":[45],"costs,":[46],"scalable":[48],"memory":[49],"bandwidth,":[50],"making":[51],"it":[52],"promising":[54],"solution":[55],"accelerate":[57],"Transformer":[58],"memory-intensive":[60],"operations.":[61],"However,":[62],"crucial":[64],"issue":[65],"lies":[66],"in":[67],"efficiently":[68],"deploying":[69],"an":[70,160],"entire":[71],"model":[72,152],"onto":[73],"resource-limited":[74,155],"PIM":[75,103,157,192,211,237],"system":[76,158,193,238],"while":[77],"parallelizing":[78],"each":[79],"transformer":[80],"block":[81],"potentially":[83],"many":[84],"computational":[85,126,188],"branches":[86,189],"based":[87],"on":[88,96,102,153,190,208],"local-attention":[89],"mechanisms.":[90],"We":[91],"present":[92],"Allspark,":[93],"which":[94,182],"focuses":[95],"workload":[97],"orchestration":[98],"for":[99,125,225],"visual":[100,227],"systems,":[104],"aiming":[105],"minimizing":[107],"inference":[108,223],"latency.":[109],"Firstly,":[110],"fully":[112],"utilize":[113],"massive":[115],"parallelism":[116],"PIM,":[118],"Allspark":[119,145,176,215],"employs":[120],"fine-grained":[122],"partitioning":[123],"scheme":[124],"branches,":[127],"formats":[129],"systematic":[131],"layout":[132,197],"interleaved":[134],"dataflow":[135],"maximized":[137],"locality":[139],"reduced":[141],"movement.":[143],"Secondly,":[144],"formulates":[146],"scheduling":[148],"complete":[151],"distributed":[156],"as":[159,167],"integer":[161],"linear":[162],"programming":[163],"(ILP)":[164],"problem.":[165],"Thirdly,":[166],"local-global":[168],"interactions":[170],"exhibit":[171],"complex":[172],"yet":[173],"regular":[174],"dependencies,":[175],"provides":[177],"two-stage":[179],"placement":[180,186],"method,":[181],"simplifies":[183],"challenging":[185],"into":[194],"structured":[196],"greedy-based":[199],"binding,":[200],"minimize":[202],"NoC":[203],"communication":[204],"costs.":[205],"Extensive":[206],"experiments":[207],"3D-stacked":[209],"DRAM-based":[210],"systems":[212],"show":[213],"brings":[216],"<inline-formula><tex-math":[217,219,221,243,249,251,253],"notation=\"LaTeX\">$1.2\\times$</tex-math></inline-formula>":[218],"notation=\"LaTeX\">$\\sim$</tex-math></inline-formula>":[220,252],"notation=\"LaTeX\">$24.0\\times$</tex-math></inline-formula>":[222],"speedup":[224],"various":[226],"over":[229],"baselines.":[230],"Compared":[231],"Nvidia":[233],"V100":[234],"GPU,":[235],"Allspark-enriched":[236],"yields":[239],"average":[240],"speedups":[241],"notation=\"LaTeX\">$2.3\\times$</tex-math></inline-formula>":[244],"energy":[246],"savings":[247],"notation=\"LaTeX\">$20\\times$</tex-math></inline-formula>":[250],"notation=\"LaTeX\">$55\\times$</tex-math></inline-formula>.":[254]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}