{"id":"https://openalex.org/W4282050611","doi":"https://doi.org/10.1109/fccm53951.2022.9786203","title":"Managing HBM Bandwidth on Multi-Die FPGAs with FPGA Overlay NoCs","display_name":"Managing HBM Bandwidth on Multi-Die FPGAs with FPGA Overlay NoCs","publication_year":2022,"publication_date":"2022-05-15","ids":{"openalex":"https://openalex.org/W4282050611","doi":"https://doi.org/10.1109/fccm53951.2022.9786203"},"language":"en","primary_location":{"id":"doi:10.1109/fccm53951.2022.9786203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm53951.2022.9786203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 30th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","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/A5052459587","display_name":"Srinirdheeshwar Kuttuva Prakash","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Srinirdheeshwar Kuttuva Prakash","raw_affiliation_strings":["University of Waterloo,Canada","University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042701714","display_name":"Hiren Patel","orcid":"https://orcid.org/0000-0003-1128-8110"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hiren Patel","raw_affiliation_strings":["University of Waterloo,Canada","University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015534628","display_name":"Nachiket Kapre","orcid":"https://orcid.org/0000-0002-2187-0406"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nachiket Kapre","raw_affiliation_strings":["University of Waterloo,Canada","University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":1.0,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.9939000010490417,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8042004108428955},{"id":"https://openalex.org/keywords/crossbar-switch","display_name":"Crossbar switch","score":0.7986148595809937},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6791177988052368},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5886314511299133},{"id":"https://openalex.org/keywords/network-on-a-chip","display_name":"Network on a chip","score":0.5063704252243042},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4770224094390869},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47697457671165466},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.4599984586238861},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.41720932722091675},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.38667523860931396},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.2155398428440094},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.18313652276992798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8042004108428955},{"id":"https://openalex.org/C29984679","wikidata":"https://www.wikidata.org/wiki/Q1929149","display_name":"Crossbar switch","level":2,"score":0.7986148595809937},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6791177988052368},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5886314511299133},{"id":"https://openalex.org/C128519102","wikidata":"https://www.wikidata.org/wiki/Q339554","display_name":"Network on a chip","level":2,"score":0.5063704252243042},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4770224094390869},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47697457671165466},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.4599984586238861},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.41720932722091675},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.38667523860931396},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2155398428440094},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.18313652276992798},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fccm53951.2022.9786203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fccm53951.2022.9786203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 30th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1501077214","https://openalex.org/W1644436786","https://openalex.org/W1984520032","https://openalex.org/W2042876290","https://openalex.org/W2276268482","https://openalex.org/W2600117321","https://openalex.org/W2763060343","https://openalex.org/W2890463535","https://openalex.org/W2907463061","https://openalex.org/W2924049058","https://openalex.org/W2952675288","https://openalex.org/W3008233227","https://openalex.org/W3034855459","https://openalex.org/W3093557412","https://openalex.org/W3133347161","https://openalex.org/W3158095734","https://openalex.org/W6755094243","https://openalex.org/W6760927017","https://openalex.org/W6794806100"],"related_works":["https://openalex.org/W2145932742","https://openalex.org/W1874409533","https://openalex.org/W2554791727","https://openalex.org/W1981395029","https://openalex.org/W2576538540","https://openalex.org/W1757304091","https://openalex.org/W2152379259","https://openalex.org/W2099993311","https://openalex.org/W2226270586","https://openalex.org/W223007697"],"abstract_inverted_index":{"We":[0,157],"can":[1,143,192],"improve":[2,193],"HBM":[3,22,45,74,77,105,131,153],"bandwidth":[4,37,132],"distribution":[5],"and":[6,93,167,173,181,201],"utilization":[7],"on":[8],"a":[9,34,56,91,126],"multi-die":[10],"FPGA":[11,49],"like":[12],"Xilinx":[13,24,152,161],"Alveo":[14,25,162],"U280":[15,26,163],"by":[16,90,196],"using":[17,170],"Overlay":[18,113,190],"Network-on-Chips":[19],"(NoCs).":[20],"The":[21,96,137],"in":[23,51,160],"offers":[27,125],"8":[28],"GB":[29],"of":[30,38,103,140,151],"memory":[31],"capacity":[32],"with":[33,119,164],"theoretical":[35],"maximum":[36],"460":[39],"GBps,":[40],"but":[41,107],"exposed":[42],"all":[43,134],"the":[44,48,66,104,141,148,194],"ports":[46],"to":[47,61,72,146,203],"fabric":[50],"only":[52],"one":[53],"die.":[54],"As":[55],"result,":[57],"computing":[58],"elements":[59],"assigned":[60],"other":[62],"dies":[63],"must":[64],"use":[65],"scarce":[67],"Super":[68],"Long":[69],"Lines":[70],"(SLLs)":[71],"access":[73],"bandwidth.":[75],"Furthermore,":[76],"is":[78],"fractured":[79],"internally":[80],"into":[81],"thirty-two":[82],"smaller":[83],"memories":[84],"called":[85],"pseudo":[86],"channels,":[87],"connected":[88],"together":[89],"hardened":[92],"performance-limited":[94],"crossbar.":[95],"crossbar":[97,150],"enables":[98],"global":[99,155],"accesses":[100],"from":[101],"any":[102],"ports,":[106],"introduces":[108],"several":[109],"throughput":[110,195],"bottlenecks.":[111],"An":[112],"Hybrid":[114,168],"NoC":[115,118,142],"combining":[116],"Hoplite":[117],"Butterfly":[120],"Fat":[121],"Trees":[122],"(BFT)":[123],"NoCs":[124,191],"high-performance":[127],"solution":[128],"for":[129,154,198,205],"distributing":[130],"across":[133],"three":[135],"dies.":[136],"routing":[138],"capability":[139],"be":[144],"modified":[145],"supplant":[147],"internal":[149],"accesses.":[156],"demonstrate":[158],"this":[159],"BFT,":[165],"Hoplite,":[166],"NoC,":[169],"synthetic":[171,199],"benchmarks":[172,200],"two":[174],"application-based":[175],"benchmarks,":[176],"Dense":[177],"matrix-matrix":[178],"multiplication":[179,184],"(DMM)":[180],"Sparse":[182],"Matrix-Vector":[183],"(SPMV).":[185],"Our":[186],"experiments":[187],"show":[188],"that":[189],"1.26\u00d7":[197],"up":[202],"1.4\u00d7":[204],"SpMV":[206],"workloads.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
