{"id":"https://openalex.org/W7162754430","doi":"https://doi.org/10.1145/3817062","title":"Enabling Efficient Vector Processing: A Heterogeneous Vector Architecture with in-SRAM Computing","display_name":"Enabling Efficient Vector Processing: A Heterogeneous Vector Architecture with in-SRAM Computing","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7162754430","doi":"https://doi.org/10.1145/3817062"},"language":"en","primary_location":{"id":"doi:10.1145/3817062","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3817062","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3817062","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137334938","display_name":"Ruoxi Wang","orcid":"https://orcid.org/0009-0009-5154-0086"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruoxi Wang","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology"],"raw_orcid":"https://orcid.org/0009-0009-5154-0086","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025499211","display_name":"Dunbo Zhang","orcid":"https://orcid.org/0009-0001-8854-4752"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang Dunbo","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology"],"raw_orcid":"https://orcid.org/0000-0003-2384-5359","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088092175","display_name":"Shangshang Yao","orcid":"https://orcid.org/0000-0001-7217-1712"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangshang Yao","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology"],"raw_orcid":"https://orcid.org/0000-0001-7217-1712","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137318179","display_name":"Lang Qingjie","orcid":"https://orcid.org/0009-0009-9456-8695"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lang Qingjie","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology"],"raw_orcid":"https://orcid.org/0009-0009-9456-8695","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032144658","display_name":"Junyi Zhu","orcid":"https://orcid.org/0000-0001-5112-5493"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyi Zhu","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology"],"raw_orcid":"https://orcid.org/0009-0004-5299-7890","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109528028","display_name":"Li Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology"],"raw_orcid":"https://orcid.org/0000-0001-9043-2998","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66919968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"2","first_page":"1","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.907800018787384,"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":0.907800018787384,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.017500000074505806,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.013500000350177288,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vector-processor","display_name":"Vector processor","score":0.46050000190734863},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.4512999951839447},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4106000065803528},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.4068000018596649},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.39809998869895935},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.38769999146461487},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.36059999465942383},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.3377000093460083},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3343000113964081}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8711000084877014},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.605400025844574},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4672999978065491},{"id":"https://openalex.org/C161824985","wikidata":"https://www.wikidata.org/wiki/Q919509","display_name":"Vector processor","level":2,"score":0.46050000190734863},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4512999951839447},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4375999867916107},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.4068000018596649},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.36059999465942383},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35740000009536743},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C150495011","wikidata":"https://www.wikidata.org/wiki/Q128392","display_name":"Concurrent computing","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3817062","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3817062","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3817062","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3817062","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.906491219997406,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2086112773","https://openalex.org/W2155729354","https://openalex.org/W2613569094","https://openalex.org/W2801000640","https://openalex.org/W3042944763","https://openalex.org/W3133588229","https://openalex.org/W3155004489","https://openalex.org/W3157657667","https://openalex.org/W4360831845","https://openalex.org/W4393407315","https://openalex.org/W4402269472","https://openalex.org/W4411066161","https://openalex.org/W4413431280","https://openalex.org/W4416445328"],"related_works":[],"abstract_inverted_index":{"The":[0,175],"growing":[1],"demand":[2],"for":[3,110,151,267],"high-performance,":[4],"energy-efficient":[5],"execution":[6],"of":[7,14,26,69,173,208],"data-parallel":[8],"workloads":[9],"has":[10],"driven":[11],"the":[12,23,50,67,78,121,125,149,170,213,239,254],"resurgence":[13],"vector":[15,27,44,105,113,194,217,258,269],"processors,":[16],"yet":[17],"their":[18],"expanding":[19],"instruction":[20,128],"sets":[21],"exacerbate":[22],"area-performance":[24,255],"tradeoff":[25,41,256],"processing":[28],"units":[29],"(VPUs).":[30],"Processing-in-memory":[31],"(PIM)":[32],"technique":[33],"offers":[34,261],"a":[35,70,93,100,104,108,117,180,187,193,262],"promising":[36],"path":[37],"to":[38,82,210,236],"mitigate":[39],"this":[40,90],"by":[42,179,224,234],"offloading":[43],"operations":[45],"near":[46],"data.":[47],"However,":[48],"integrating":[49],"computing-capable":[51],"SRAM":[52],"(C-SRAM)":[53],"with":[54,107,144,242],"conventional":[55],"VPUs":[56],"introduces":[57,116],"significant":[58,206],"architectural":[59,250],"challenges,":[60,89],"including":[61],"inefficient":[62],"coordination":[63],"between":[64,120],"heterogeneous":[65,94,264],"devices,":[66],"lack":[68],"unified":[71],"hardware/software":[72],"interface,":[73],"and":[74,124,133,161,167,182,192,260],"underutilized":[75],"parallelism":[76],"within":[77],"C-SRAM":[79,109,150],"arrays":[80],"due":[81],"unoptimized":[83],"data":[84,159],"handling.":[85],"To":[86],"address":[87],"these":[88],"article":[91],"proposes":[92],"VPU":[95,102],"(HVPU)":[96],"that":[97,201,248],"seamlessly":[98],"integrates":[99],"standard":[101],"inside":[103,148],"processor":[106,122,204],"more":[111],"efficient":[112,268],"processing.":[114,270],"HVPU":[115],"standardized":[118],"interface":[119],"frontend":[123],"C-SRAM,":[126],"enabling":[127],"dispatch,":[129],"dynamic":[130],"hazard":[131],"resolution,":[132],"concurrent":[134],"execution.":[135],"Furthermore,":[136],"it":[137,229],"employs":[138],"multiple":[139],"independent":[140],"PIM":[141,232],"blocks":[142],"coupled":[143],"dual":[145],"controlling":[146],"pipelines":[147],"further":[152],"performance":[153],"improvement.":[154],"This":[155,246],"design":[156],"facilitates":[157],"pipelined":[158],"loading":[160],"computing,":[162],"effectively":[163,252],"hiding":[164],"memory":[165],"latency":[166],"fully":[168],"unlocking":[169],"parallel":[171],"potential":[172],"C-SRAM.":[174],"system":[176,191],"is":[177],"supported":[178],"user-friendly":[181],"generic":[183],"programming":[184],"model":[185],"featuring":[186],"two-layer":[188],"extended":[189],"ISA":[190],"batch":[195],"pipelining":[196],"mechanism.":[197],"Experimental":[198],"results":[199],"show":[200],"our":[202,249],"HVPU-enhanced":[203],"achieves":[205],"speedups":[207],"5.11\u00d7":[209],"39.0\u00d7":[211],"over":[212],"Xuantie-910":[214],"baseline":[215],"on":[216,226,238],"benchmarks,":[218,241],"respectively,":[219],"while":[220],"reducing":[221],"energy":[222],"consumption":[223],"75%":[225],"average.":[227],"Meanwhile,":[228],"outperforms":[230],"state-of-the-art":[231],"accelerators":[233],"1.33\u00d7":[235],"1.97\u00d7":[237],"same":[240],"minimal":[243],"area":[244],"overhead.":[245],"demonstrates":[247],"co-design":[251],"alleviates":[253],"in":[257],"processors":[259],"scalable":[263],"architecture":[265],"template":[266]},"counts_by_year":[],"updated_date":"2026-06-27T06:13:17.587685","created_date":"2026-05-30T00:00:00"}