{"id":"https://openalex.org/W2146141543","doi":"https://doi.org/10.1145/2800788","title":"Memory Interface Design for 3D Stencil Kernels on a Massively Parallel Memory System","display_name":"Memory Interface Design for 3D Stencil Kernels on a Massively Parallel Memory System","publication_year":2015,"publication_date":"2015-09-11","ids":{"openalex":"https://openalex.org/W2146141543","doi":"https://doi.org/10.1145/2800788","mag":"2146141543"},"language":"en","primary_location":{"id":"doi:10.1145/2800788","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2800788","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"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 Reconfigurable Technology 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/A5101790023","display_name":"Zheming Jin","orcid":"https://orcid.org/0000-0002-7197-780X"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheming Jin","raw_affiliation_strings":["University of South Carolina, Columbia","University of South Carolina, Columbia;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Carolina, Columbia","institution_ids":["https://openalex.org/I155781252"]},{"raw_affiliation_string":"University of South Carolina, Columbia;","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001266986","display_name":"Jason D. Bakos","orcid":"https://orcid.org/0000-0002-0821-6258"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason D. Bakos","raw_affiliation_strings":["University of South Carolina, Columbia","University of South Carolina, Columbia;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Carolina, Columbia","institution_ids":["https://openalex.org/I155781252"]},{"raw_affiliation_string":"University of South Carolina, Columbia;","institution_ids":["https://openalex.org/I155781252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.08981002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"8","issue":"4","first_page":"1","last_page":"24"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9994999766349792,"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":0.88109290599823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8519812822341919},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.6132840514183044},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5858614444732666},{"id":"https://openalex.org/keywords/registered-memory","display_name":"Registered memory","score":0.5793058276176453},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.5177897214889526},{"id":"https://openalex.org/keywords/interleaved-memory","display_name":"Interleaved memory","score":0.5122305750846863},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.503926694393158},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4524118900299072},{"id":"https://openalex.org/keywords/extended-memory","display_name":"Extended memory","score":0.4433766007423401},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.44246357679367065},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3895692229270935},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3765212893486023},{"id":"https://openalex.org/keywords/computer-memory","display_name":"Computer memory","score":0.24782297015190125},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.2229708433151245},{"id":"https://openalex.org/keywords/memory-controller","display_name":"Memory controller","score":0.2109251618385315},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.11537414789199829}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.88109290599823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8519812822341919},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.6132840514183044},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5858614444732666},{"id":"https://openalex.org/C93446704","wikidata":"https://www.wikidata.org/wiki/Q449328","display_name":"Registered memory","level":3,"score":0.5793058276176453},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.5177897214889526},{"id":"https://openalex.org/C63511323","wikidata":"https://www.wikidata.org/wiki/Q908936","display_name":"Interleaved memory","level":4,"score":0.5122305750846863},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.503926694393158},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4524118900299072},{"id":"https://openalex.org/C171675096","wikidata":"https://www.wikidata.org/wiki/Q1143380","display_name":"Extended memory","level":4,"score":0.4433766007423401},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.44246357679367065},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3895692229270935},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3765212893486023},{"id":"https://openalex.org/C92855701","wikidata":"https://www.wikidata.org/wiki/Q5830907","display_name":"Computer memory","level":3,"score":0.24782297015190125},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.2229708433151245},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.2109251618385315},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.11537414789199829},{"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:10.1145/2800788","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2800788","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"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 Reconfigurable Technology and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2240665273","display_name":null,"funder_award_id":"0844951","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1493629500","https://openalex.org/W1931987324","https://openalex.org/W1988382391","https://openalex.org/W2012687750","https://openalex.org/W2018034355","https://openalex.org/W2020458826","https://openalex.org/W2029206802","https://openalex.org/W2059843741","https://openalex.org/W2089530136","https://openalex.org/W2096648046","https://openalex.org/W2107114182","https://openalex.org/W2108784402","https://openalex.org/W2110421595","https://openalex.org/W2115172404","https://openalex.org/W2121963261","https://openalex.org/W2130617051","https://openalex.org/W2137383459","https://openalex.org/W2143230897","https://openalex.org/W2146757388","https://openalex.org/W2147832021","https://openalex.org/W2149590159","https://openalex.org/W2151664616","https://openalex.org/W2151917022","https://openalex.org/W2154786353","https://openalex.org/W2160545443","https://openalex.org/W2168582504","https://openalex.org/W2561675875","https://openalex.org/W2728864642","https://openalex.org/W4236504040","https://openalex.org/W4252485253"],"related_works":["https://openalex.org/W2138825797","https://openalex.org/W3008068282","https://openalex.org/W2019238062","https://openalex.org/W1707075782","https://openalex.org/W2185658074","https://openalex.org/W2130320819","https://openalex.org/W4210611780","https://openalex.org/W4233816696","https://openalex.org/W4393076761","https://openalex.org/W1725472669"],"abstract_inverted_index":{"Massively":[0],"parallel":[1,52],"memory":[2,53,79,99,119,141],"systems":[3,54],"are":[4],"designed":[5],"to":[6,31,46,66,138],"deliver":[7],"high":[8,57,71],"bandwidth":[9,43,62],"at":[10],"relatively":[11],"low":[12],"clock":[13],"speed":[14],"for":[15,101,128,133],"memory-intensive":[16],"applications":[17],"implemented":[18],"on":[19,105],"programmable":[20],"logic.":[21,49],"For":[22],"example,":[23],"the":[24,47,73,94,106,117],"Convey":[25,107],"HC-1":[26,108],"provides":[27],"1,024":[28],"DRAM":[29],"banks":[30],"each":[32],"of":[33,44,96,126],"four":[34],"FPGAs":[35],"through":[36],"a":[37,41,77,97,122,139],"full":[38],"crossbar,":[39],"presenting":[40],"peak":[42],"76.8GB/s":[45],"user":[48,74],"Such":[50],"highly":[51,64],"suffer":[55],"from":[56],"latency,":[58],"and":[59,86,131],"their":[60],"effective":[61],"is":[63],"sensitive":[65],"access":[67],"ordering.":[68],"To":[69],"achieve":[70],"performance,":[72],"must":[75],"use":[76],"customized":[78],"interface":[80,100,120],"that":[81,109,116],"combines":[82],"scheduling,":[83],"latency":[84],"hiding,":[85],"data":[87],"reuse.":[88],"In":[89],"this":[90],"article,":[91],"we":[92],"describe":[93],"design":[95],"custom":[98],"3D":[102],"stencil":[103,130,135],"kernels":[104],"incorporates":[110],"these":[111],"features.":[112],"Experimental":[113],"results":[114],"show":[115],"proposed":[118],"achieves":[121],"speedup":[123],"in":[124],"runtime":[125],"2.2":[127],"6-point":[129],"9.5":[132],"27-point":[134],"when":[136],"compared":[137],"naive":[140],"interface.":[142]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
