{"id":"https://openalex.org/W1988382391","doi":"https://doi.org/10.1145/1929943.1929947","title":"Automatic memory partitioning and scheduling for throughput and power optimization","display_name":"Automatic memory partitioning and scheduling for throughput and power optimization","publication_year":2011,"publication_date":"2011-03-01","ids":{"openalex":"https://openalex.org/W1988382391","doi":"https://doi.org/10.1145/1929943.1929947","mag":"1988382391"},"language":"en","primary_location":{"id":"doi:10.1145/1929943.1929947","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1929943.1929947","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"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 Design Automation of Electronic 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/A5016776689","display_name":"Jason Cong","orcid":"https://orcid.org/0000-0003-2887-6963"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jason Cong","raw_affiliation_strings":["University of California, Los Angeles, CA","University of California, Los Angeles. CA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, CA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles. CA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009452553","display_name":"Wei Jiang","orcid":"https://orcid.org/0000-0001-5663-9119"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Jiang","raw_affiliation_strings":["University of California, Los Angeles, CA","University of California, Los Angeles. CA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, CA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles. CA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395453","display_name":"Bin Liu","orcid":"https://orcid.org/0000-0001-9388-0198"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Liu","raw_affiliation_strings":["University of California, Los Angeles, CA","University of California, Los Angeles. CA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, CA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles. CA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100458990","display_name":"Yi Zou","orcid":"https://orcid.org/0000-0002-4382-4670"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Zou","raw_affiliation_strings":["University of California, Los Angeles, CA","University of California, Los Angeles. CA"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles, CA","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"University of California, Los Angeles. CA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5016776689"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":5.1354,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.95755846,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"16","issue":"2","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8909696340560913},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6470903158187866},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5897036790847778},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5494024157524109},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5202847123146057},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5134862065315247},{"id":"https://openalex.org/keywords/computing-with-memory","display_name":"Computing with Memory","score":0.4512476325035095},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.4472893476486206},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4447477459907532},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4337542653083801},{"id":"https://openalex.org/keywords/dynamic-demand","display_name":"Dynamic demand","score":0.4111425280570984},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.3386967182159424},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3330446481704712},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.26522594690322876},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.20633769035339355},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.19822552800178528},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.18391147255897522},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.16804355382919312},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.16505694389343262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8909696340560913},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6470903158187866},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5897036790847778},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5494024157524109},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5202847123146057},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5134862065315247},{"id":"https://openalex.org/C152890283","wikidata":"https://www.wikidata.org/wiki/Q4129922","display_name":"Computing with Memory","level":5,"score":0.4512476325035095},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.4472893476486206},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4447477459907532},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4337542653083801},{"id":"https://openalex.org/C45872418","wikidata":"https://www.wikidata.org/wiki/Q5318966","display_name":"Dynamic demand","level":3,"score":0.4111425280570984},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.3386967182159424},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3330446481704712},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.26522594690322876},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.20633769035339355},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.19822552800178528},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.18391147255897522},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.16804355382919312},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.16505694389343262},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","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/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1929943.1929947","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1929943.1929947","pdf_url":null,"source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"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 Design Automation of Electronic Systems","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.160.1741","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.160.1741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ballade.cs.ucla.edu/~cong/papers/main_ICCAD_09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.9100000262260437,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G5886237766","display_name":null,"funder_award_id":"CNS-0725354","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"}],"funders":[{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494930385","https://openalex.org/W1997182928","https://openalex.org/W2012687750","https://openalex.org/W2024178767","https://openalex.org/W2034928524","https://openalex.org/W2070922326","https://openalex.org/W2082603400","https://openalex.org/W2110421595","https://openalex.org/W2114830647","https://openalex.org/W2117285153","https://openalex.org/W2118245937","https://openalex.org/W2123173853","https://openalex.org/W2123412205","https://openalex.org/W2135464889","https://openalex.org/W2140639562","https://openalex.org/W2147543317","https://openalex.org/W2147832021","https://openalex.org/W2156420848","https://openalex.org/W2165689945","https://openalex.org/W2296760900","https://openalex.org/W4214626551"],"related_works":["https://openalex.org/W3180803030","https://openalex.org/W2169347615","https://openalex.org/W2168550483","https://openalex.org/W2100219285","https://openalex.org/W2092763781","https://openalex.org/W87257424","https://openalex.org/W2369863000","https://openalex.org/W2993507867","https://openalex.org/W2794057488","https://openalex.org/W4297694018"],"abstract_inverted_index":{"Memory":[0],"bottleneck":[1],"has":[2],"become":[3],"a":[4,150,174],"limiting":[5],"factor":[6],"in":[7,16,197,231],"satisfying":[8],"the":[9,119,138,205,210,215,247],"explosive":[10],"demands":[11],"on":[12,122,173,185,246],"performance":[13],"and":[14,41,74,86,141,157],"cost":[15],"modern":[17],"embedded":[18],"system":[19],"design.":[20,217],"Selected":[21],"computation":[22],"kernels":[23,81],"for":[24,82,127,145,160,208],"acceleration":[25],"are":[26,33],"usually":[27],"captured":[28],"by":[29,35,149],"nest":[30],"loops,":[31],"which":[32,69,153],"optimized":[34,198],"state-of-the-art":[36],"techniques":[37],"like":[38],"loop":[39,42,80],"tiling":[40],"pipelining.":[43],"However,":[44],"memory":[45,66,123,139,206,228],"bandwidth":[46,124],"bottlenecks":[47],"prevent":[48],"designs":[49,178],"from":[50],"reaching":[51],"optimal":[52],"throughput":[53,73,84,171,196],"with":[54,179,194,234],"respect":[55],"to":[56,117,136,220],"available":[57],"parallelism.":[58],"In":[59,218],"this":[60],"paper":[61],"we":[62],"present":[63],"an":[64,168],"automatic":[65],"partitioning":[67,140],"technique":[68,224],"can":[70,93,225],"efficiently":[71],"improve":[72],"reduce":[75],"energy":[76],"consumption":[77,213],"of":[78,106,176,214,250],"pipelined":[79],"given":[83,187],"constraints":[85,121],"platform":[87],"requirements.":[88],"Also,":[89],"our":[90,223],"proposed":[91,135],"algorithm":[92,152],"handle":[94],"general":[95],"array":[96,100],"access":[97,229],"beyond":[98],"affine":[99],"references.":[101],"Our":[102],"partition":[103],"scheme":[104],"consists":[105],"two":[107],"steps.":[108],"The":[109,200],"first":[110],"step":[111,202],"considers":[112],"cycle":[113],"accurate":[114],"scheduling":[115,142],"information":[116],"meet":[118],"hard":[120],"requirements":[125],"specifically":[126],"synchronized":[128],"hardware":[129],"designs.":[130,199],"An":[131],"ILP":[132],"formulation":[133],"is":[134,154],"solve":[137],"problem":[143],"optimally":[144],"small":[146],"designs,":[147],"followed":[148],"heuristic":[151],"more":[155],"scalable":[156],"equally":[158],"effective":[159],"solving":[161],"large":[162],"scale":[163],"problems.":[164],"Experimental":[165,239],"results":[166,240],"show":[167,241],"average":[169],"6\u00d7":[170],"improvement":[172],"set":[175,249],"real-world":[177],"moderate":[180],"area":[181],"increase":[182],"(about":[183],"45%":[184],"average),":[186],"that":[188],"less":[189],"resource":[190],"sharing":[191],"opportunities":[192],"exist":[193],"higher":[195],"second":[201],"further":[203],"partitions":[204],"banks":[207],"reducing":[209],"dynamic":[211],"power":[212,244],"final":[216],"contrast":[219],"previous":[221],"approaches,":[222],"statically":[226],"compute":[227],"frequencies":[230],"polynomial":[232],"time":[233],"little":[235],"or":[236],"no":[237],"profiling.":[238],"about":[242],"30%":[243],"reduction":[245],"same":[248],"benchmarks.":[251]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}