{"id":"https://openalex.org/W2043607059","doi":"https://doi.org/10.1145/2133382.2133388","title":"A Massively Parallel, Energy Efficient Programmable Accelerator for Learning and Classification","display_name":"A Massively Parallel, Energy Efficient Programmable Accelerator for Learning and Classification","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2043607059","doi":"https://doi.org/10.1145/2133382.2133388","mag":"2043607059"},"language":"en","primary_location":{"id":"doi:10.1145/2133382.2133388","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2133382.2133388","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2133382.2133388","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":false,"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":null,"license_id":null,"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":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2133382.2133388","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028244358","display_name":"Abhinandan Majumdar","orcid":"https://orcid.org/0009-0002-0032-2299"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Abhinandan Majumdar","raw_affiliation_strings":["NEC Laboratories America, Inc"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034416611","display_name":"Srihari Cadambi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srihari Cadambi","raw_affiliation_strings":["NEC Laboratories America, Inc"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041520129","display_name":"Michela Becchi","orcid":"https://orcid.org/0000-0001-8353-2915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michela Becchi","raw_affiliation_strings":["NEC Laboratories America, Inc"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042424184","display_name":"Srimat Chakradhar","orcid":"https://orcid.org/0000-0003-3530-3901"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Srimat T. Chakradhar","raw_affiliation_strings":["NEC Laboratories America, Inc"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110182290","display_name":"Hans Peter Graf","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hans Peter Graf","raw_affiliation_strings":["NEC Laboratories America, Inc"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories America, Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028244358"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.9771,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.9536903,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"9","issue":"1","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9958999752998352,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9937000274658203,"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":0.8664389848709106},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.7335284948348999},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4850863516330719},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.425918847322464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8664389848709106},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.7335284948348999},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4850863516330719},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.425918847322464},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2133382.2133388","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2133382.2133388","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2133382.2133388","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":false,"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":null,"license_id":null,"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:10.1145/2133382.2133388","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2133382.2133388","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2133382.2133388","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":false,"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":null,"license_id":null,"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":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2043607059.pdf","grobid_xml":"https://content.openalex.org/works/W2043607059.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1512098439","https://openalex.org/W1530262073","https://openalex.org/W1534665966","https://openalex.org/W1539715674","https://openalex.org/W1604938182","https://openalex.org/W2017279832","https://openalex.org/W2025423507","https://openalex.org/W2033272178","https://openalex.org/W2096645269","https://openalex.org/W2108157916","https://openalex.org/W2111993661","https://openalex.org/W2112796928","https://openalex.org/W2117130368","https://openalex.org/W2120432001","https://openalex.org/W2121288607","https://openalex.org/W2123749980","https://openalex.org/W2127218421","https://openalex.org/W2138763931","https://openalex.org/W2144857621","https://openalex.org/W2147345262","https://openalex.org/W2150593711","https://openalex.org/W2153387583","https://openalex.org/W2159350554","https://openalex.org/W2161238936","https://openalex.org/W2163198250","https://openalex.org/W2169150396","https://openalex.org/W2172212694","https://openalex.org/W2554051734","https://openalex.org/W2578027111","https://openalex.org/W3150290710","https://openalex.org/W4247913514"],"related_works":["https://openalex.org/W2117141678","https://openalex.org/W2117014006","https://openalex.org/W4233815414","https://openalex.org/W2372170743","https://openalex.org/W1558545464","https://openalex.org/W1984303163","https://openalex.org/W1509211761","https://openalex.org/W119040397","https://openalex.org/W1543798151","https://openalex.org/W2022867548"],"abstract_inverted_index":{"Applications":[0],"that":[1,73,93,211,267],"use":[2],"learning":[3,66,77],"and":[4,14,41,78,91,126,171,245,250,265],"classification":[5,79],"algorithms":[6],"operate":[7],"on":[8,57],"large":[9,47,107],"amounts":[10,108],"of":[11,24,34,43,109,135,263,301],"unstructured":[12],"data,":[13,111],"have":[15],"stringent":[16],"performance":[17,23,56,193,215,248],"constraints.":[18],"For":[19],"such":[20,60,65,83,120],"applications,":[21,67],"the":[22,161,209,213,225,243,304],"general":[25],"purpose":[26],"processors":[27,59],"scales":[28],"poorly":[29],"with":[30,146,179,194,206,232],"data":[31,49,195],"size":[32],"because":[33],"their":[35,94],"limited":[36],"support":[37],"for":[38],"fine-grained":[39],"parallelism":[40],"absence":[42],"software-managed":[44],"caches.":[45],"The":[46],"intermediate":[48,110],"in":[50,142],"these":[51],"applications":[52],"also":[53,198],"limits":[54],"achievable":[55],"many-core":[58],"as":[61,101,121,208],"GPUs.":[62],"To":[63,81],"accelerate":[64],"we":[68,86,296],"present":[69,199],"a":[70,117,143,218,233,259,273,282,292,309],"programmable":[71],"accelerator":[72,210],"can":[74,98],"execute":[75],"multiple":[76],"algorithms.":[80],"architect":[82],"an":[84,200,298],"accelerator,":[85,130],"profile":[87],"five":[88],"representative":[89],"workloads,":[90],"find":[92,266],"computationally":[95],"intensive":[96],"portions":[97],"be":[99],"formulated":[100],"matrix":[102],"or":[103],"vector":[104],"operations":[105],"generating":[106],"which":[112],"are":[113],"then":[114],"reduced":[115],"by":[116],"secondary":[118,162],"operation":[119],"array":[122],"ranking,":[123],"finding":[124],"max/min":[125],"aggregation.":[127],"Our":[128],"proposed":[129],"called":[131],"MAPLE,":[132],"has":[133],"hundreds":[134],"simple":[136],"processing":[137,155],"elements":[138],"(PEs)":[139],"laid":[140],"out":[141],"two-dimensional":[144],"grid,":[145],"two":[147,186],"key":[148],"features.":[149],"First,":[150],"it":[151,268],"uses":[152,167],"dynamic":[153],"in-memory":[154],"where":[156],"on-chip":[157],"memory":[158,183],"blocks":[159],"perform":[160],"reduction":[163],"operations.":[164],"Second,":[165],"MAPLE":[166,189,207,226,264,289],"banked":[168],"off-chip":[169,182],"memory,":[170],"organizes":[172],"its":[173,180,192,229,247],"PEs":[174],"into":[175],"independent":[176],"groups":[177],"each":[178],"own":[181],"bank.":[184],"These":[185],"features":[187],"allow":[188],"to":[190,237,242,291,308],"scale":[191],"size.":[196],"We":[197,257],"Atom":[201],"based":[202],"energy-efficient":[203],"heterogeneous":[204],"system":[205,220],"satisfies":[212],"application\u2019s":[214],"requirements":[216],"at":[217,281],"lower":[219],"power.":[221],"This":[222],"article":[223],"describes":[224],"architecture,":[227],"explores":[228],"design":[230],"space":[231],"simulator,":[234],"illustrates":[235],"how":[236],"automatically":[238],"map":[239],"application":[240],"kernels":[241],"hardware,":[244],"presents":[246],"improvement":[249,300],"energy":[251,299],"benefits":[252],"over":[253,303],"classic":[254],"server-based":[255],"implementations.":[256],"implement":[258],"512-PE":[260],"FPGA":[261],"prototype":[262],"is":[269],"1.5-10x":[270],"faster":[271],"than":[272],"2.5":[274],"GHz":[275,311],"quad-core":[276],"Xeon":[277,305],"processor":[278],"despite":[279],"running":[280],"modest":[283],"125":[284],"MHz":[285],"clock":[286],"rate.":[287],"With":[288],"connected":[290],"1.6GHz":[293],"dual-core":[294],"Atom,":[295],"show":[297],"38-84%":[302],"server":[306],"coupled":[307],"1.3":[310],"240":[312],"core":[313],"Tesla":[314],"GPU.":[315]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}