{"id":"https://openalex.org/W2289773844","doi":"https://doi.org/10.1109/tcad.2015.2488491","title":"An Optimal Microarchitecture for Stencil Computation Acceleration Based on Nonuniform Partitioning of Data Reuse Buffers","display_name":"An Optimal Microarchitecture for Stencil Computation Acceleration Based on Nonuniform Partitioning of Data Reuse Buffers","publication_year":2015,"publication_date":"2015-10-08","ids":{"openalex":"https://openalex.org/W2289773844","doi":"https://doi.org/10.1109/tcad.2015.2488491","mag":"2289773844"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2015.2488491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2015.2488491","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/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":false,"raw_author_name":"Jason Cong","raw_affiliation_strings":["Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432722","display_name":"Peng Li","orcid":"https://orcid.org/0000-0002-5983-2384"},"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":"Peng Li","raw_affiliation_strings":["Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050841063","display_name":"Bingjun Xiao","orcid":null},"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":"Bingjun Xiao","raw_affiliation_strings":["Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100364122","display_name":"Peng Zhang","orcid":"https://orcid.org/0000-0002-3456-1848"},"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":"Peng Zhang","raw_affiliation_strings":["Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California at Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":1.9354,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86562528,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"35","issue":"3","first_page":"407","last_page":"418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design 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/T10904","display_name":"Embedded Systems Design 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/T10054","display_name":"Parallel Computing and Optimization 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":0.9995999932289124,"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/stencil","display_name":"Stencil","score":0.85223388671875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8248291611671448},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7942394018173218},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.5596134662628174},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5468522906303406},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5406979322433472},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5236701369285583},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.31760936975479126},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14478865265846252},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.14146479964256287}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.85223388671875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8248291611671448},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7942394018173218},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.5596134662628174},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5468522906303406},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5406979322433472},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5236701369285583},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.31760936975479126},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14478865265846252},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.14146479964256287}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2015.2488491","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2015.2488491","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W28521761","https://openalex.org/W643803686","https://openalex.org/W1967996906","https://openalex.org/W1970141743","https://openalex.org/W1974274517","https://openalex.org/W1974386461","https://openalex.org/W1977813547","https://openalex.org/W1999085092","https://openalex.org/W2028342110","https://openalex.org/W2036779190","https://openalex.org/W2089530136","https://openalex.org/W2105042925","https://openalex.org/W2110902796","https://openalex.org/W2115572397","https://openalex.org/W2141280299","https://openalex.org/W2143230897","https://openalex.org/W2146757388","https://openalex.org/W2165689945","https://openalex.org/W2166029537","https://openalex.org/W2907434606","https://openalex.org/W3151034118","https://openalex.org/W4243297508"],"related_works":["https://openalex.org/W2003798513","https://openalex.org/W2151764765","https://openalex.org/W2890431355","https://openalex.org/W4376875029","https://openalex.org/W2315600872","https://openalex.org/W3149084271","https://openalex.org/W4247008888","https://openalex.org/W2150319905","https://openalex.org/W2039378765","https://openalex.org/W2097757554"],"abstract_inverted_index":{"High-level":[0],"synthesis":[1],"(HLS)":[2],"tools":[3],"have":[4],"made":[5],"significant":[6],"progress":[7],"in":[8,138],"compiling":[9],"high-level":[10],"descriptions":[11],"of":[12,73,90,113,131],"computation":[13,22,165],"into":[14],"highly":[15],"pipelined":[16],"register-transfer":[17],"level":[18],"specifications.":[19],"The":[20],"high-throughput":[21],"raises":[23],"a":[24,99,105,144,168],"high":[25],"data":[26,30,41,74],"demand.":[27],"To":[28],"prevent":[29],"accesses":[31,63,150],"from":[32,151],"being":[33],"the":[34,55,96,110,123,128,163],"bottleneck,":[35],"on-chip":[36],"memories":[37],"are":[38],"used":[39],"as":[40,104],"reuse":[42,75],"buffers":[43,76],"to":[44,53,64,79,108,147,158],"reduce":[45],"off-chip":[46],"accesses.":[47],"Also":[48],"memory":[49,56,62,66,71,92,115,125,132],"partitioning":[50,72],"is":[51,77],"explored":[52],"increase":[54],"bandwidth":[57],"by":[58],"scheduling":[59],"multiple":[60],"simultaneous":[61],"different":[65],"banks.":[67],"Prior":[68],"work":[69],"on":[70],"limited":[78],"uniform":[80],"partitioning.":[81,93,116],"In":[82],"this":[83],"paper,":[84],"we":[85],"perform":[86],"an":[87,154],"early-stage":[88],"exploration":[89],"nonuniform":[91,114],"We":[94,142],"use":[95],"stencil":[97,149],"computation,":[98,152],"popular":[100],"communication-intensive":[101],"application":[102],"domain,":[103],"case":[106],"study":[107],"show":[109],"potential":[111],"benefits":[112],"Our":[117],"novel":[118],"method":[119],"can":[120],"always":[121],"achieve":[122],"minimum":[124,129],"size":[126],"and":[127,153],"number":[130],"banks,":[133],"which":[134],"cannot":[135],"be":[136],"guaranteed":[137],"any":[139],"prior":[140],"work.":[141],"develop":[143],"generalized":[145],"microarchitecture":[146,161],"decouple":[148],"automated":[155],"design":[156],"flow":[157],"integrate":[159],"our":[160],"with":[162],"HLS-generated":[164],"kernel":[166],"for":[167],"complete":[169],"accelerator.":[170]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
