{"id":"https://openalex.org/W2105042925","doi":"https://doi.org/10.1145/2593069.2593090","title":"An Optimal Microarchitecture for Stencil Computation Acceleration Based on Non-Uniform Partitioning of Data Reuse Buffers","display_name":"An Optimal Microarchitecture for Stencil Computation Acceleration Based on Non-Uniform Partitioning of Data Reuse Buffers","publication_year":2014,"publication_date":"2014-05-27","ids":{"openalex":"https://openalex.org/W2105042925","doi":"https://doi.org/10.1145/2593069.2593090","mag":"2105042925"},"language":"en","primary_location":{"id":"doi:10.1145/2593069.2593090","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2593069.2593090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st Annual Design Automation Conference","raw_type":"proceedings-article"},"type":"conference-paper","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":["Computer Science Dept. &amp; Electrical Engineering Dept., University of California, Los Angeles","Computer Science Dept. & Electrical Engineering Dept., University of California, Los Angeles#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept. &amp; Electrical Engineering Dept., University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Computer Science Dept. & Electrical Engineering Dept., University of California, Los Angeles#TAB#","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":["Computer Science Dept. &amp; Electrical Engineering Dept., University of California, Los Angeles","Computer Science Dept. & Electrical Engineering Dept., University of California, Los Angeles#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept. &amp; Electrical Engineering Dept., University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Computer Science Dept. & Electrical Engineering Dept., University of California, Los Angeles#TAB#","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":["Computer Science Dept. &amp; Electrical Engineering Dept., University of California, Los Angeles","Computer Science Dept. & Electrical Engineering Dept., University of California, Los Angeles#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept. &amp; Electrical Engineering Dept., University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Computer Science Dept. & Electrical Engineering Dept., University of California, Los Angeles#TAB#","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":["Computer Science Dept. &amp; Electrical Engineering Dept., University of California, Los Angeles","Computer Science Dept. & Electrical Engineering Dept., University of California, Los Angeles#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Dept. &amp; Electrical Engineering Dept., University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]},{"raw_affiliation_string":"Computer Science Dept. & Electrical Engineering Dept., University of California, Los Angeles#TAB#","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":2.8214,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.91446142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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":0.9998999834060669,"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":0.9997000098228455,"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":0.8373399972915649},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.812414288520813},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7848399877548218},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.5440562963485718},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5395466685295105},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5042194128036499},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4800471067428589},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.32600629329681396},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1313878893852234},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.11357209086418152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8373399972915649},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.812414288520813},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7848399877548218},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.5440562963485718},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5395466685295105},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5042194128036499},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4800471067428589},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.32600629329681396},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1313878893852234},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.11357209086418152}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2593069.2593090","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2593069.2593090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st Annual Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1974274517","https://openalex.org/W1974386461","https://openalex.org/W1977813547","https://openalex.org/W2028342110","https://openalex.org/W2036779190","https://openalex.org/W2089530136","https://openalex.org/W2110902796","https://openalex.org/W2115572397","https://openalex.org/W2140639562","https://openalex.org/W2141280299","https://openalex.org/W2143230897","https://openalex.org/W2146757388","https://openalex.org/W2165689945","https://openalex.org/W2166029537","https://openalex.org/W3151034118"],"related_works":["https://openalex.org/W2003798513","https://openalex.org/W2890431355","https://openalex.org/W2151764765","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":[8,139],"compiling":[9],"high-level":[10],"descriptions":[11],"of":[12,74,91,114,132],"computation":[13,23,166],"into":[14],"highly":[15],"pipelined":[16],"register-transfer":[17],"level":[18],"(RTL)":[19],"specifications.":[20],"The":[21],"high-throughput":[22],"raises":[24],"a":[25,100,106,145,169],"high":[26],"data":[27,31,42,75],"demand.":[28],"To":[29],"prevent":[30],"accesses":[32,64,151],"from":[33,152],"being":[34],"the":[35,56,97,111,124,129,164],"bottleneck,":[36],"on-chip":[37],"memories":[38],"are":[39],"used":[40],"as":[41,105],"reuse":[43,76],"buffers":[44,77],"to":[45,54,65,80,109,148,159],"reduce":[46],"off-chip":[47],"accesses.":[48],"Also":[49],"memory":[50,57,63,67,72,93,116,126,133],"partitioning":[51,73],"is":[52,78],"explored":[53],"increase":[55],"bandwidth":[58],"by":[59],"scheduling":[60],"multiple":[61],"simultaneous":[62],"different":[66],"banks.":[68],"Prior":[69],"work":[70],"on":[71],"limited":[79],"uniform":[81],"partitioning.":[82,94,117],"In":[83],"this":[84],"paper,":[85],"we":[86],"perform":[87],"an":[88,155],"early-stage":[89],"exploration":[90],"non-uniform":[92,115],"We":[95,143],"use":[96],"stencil":[98,150],"computation,":[99,153],"popular":[101],"communication-intensive":[102],"application":[103],"domain,":[104],"case":[107],"study":[108],"show":[110],"potential":[112],"benefits":[113],"Our":[118],"novel":[119],"method":[120],"can":[121],"always":[122],"achieve":[123],"minimum":[125,130],"size":[127],"and":[128,154],"number":[131],"banks,":[134],"which":[135],"cannot":[136],"be":[137],"guaranteed":[138],"any":[140],"prior":[141],"work.":[142],"develop":[144],"generalized":[146],"microarchitecture":[147,162],"decouple":[149],"automated":[156],"design":[157],"flow":[158],"integrate":[160],"our":[161],"with":[163],"HLS-generated":[165],"kernel":[167],"for":[168],"complete":[170],"accelerator.":[171]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
