{"id":"https://openalex.org/W2476249155","doi":"https://doi.org/10.1109/hpsr.2016.7525662","title":"P4GPU: Acceleration of programmable data plane using a CPU-GPU heterogeneous architecture","display_name":"P4GPU: Acceleration of programmable data plane using a CPU-GPU heterogeneous architecture","publication_year":2016,"publication_date":"2016-06-01","ids":{"openalex":"https://openalex.org/W2476249155","doi":"https://doi.org/10.1109/hpsr.2016.7525662","mag":"2476249155"},"language":"en","primary_location":{"id":"doi:10.1109/hpsr.2016.7525662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpsr.2016.7525662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 17th International Conference on High Performance Switching and Routing (HPSR)","raw_type":"proceedings-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/A5101732106","display_name":"Peilong Li","orcid":"https://orcid.org/0000-0002-1325-2667"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peilong Li","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of Massachusetts, Lowell"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Massachusetts, Lowell","institution_ids":["https://openalex.org/I133738476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003621523","display_name":"Yan Luo","orcid":"https://orcid.org/0000-0002-5301-5092"},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Luo","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering, University of Massachusetts, Lowell"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, University of Massachusetts, Lowell","institution_ids":["https://openalex.org/I133738476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101732106"],"corresponding_institution_ids":["https://openalex.org/I133738476"],"apc_list":null,"apc_paid":null,"fwci":1.2613,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78333647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"168","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","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"}},"topics":[{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","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/T10714","display_name":"Software-Defined Networks and 5G","score":0.9993000030517578,"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":0.9991999864578247,"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":0.8012599945068359},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.775405764579773},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6418383121490479},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.572160005569458},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5138697624206543},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.49744322896003723},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.468520849943161},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.45847395062446594},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.4518510699272156},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36478686332702637},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.32525843381881714},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3134838044643402},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.2735990285873413},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.24021315574645996},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.12408006191253662},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10912132263183594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8012599945068359},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.775405764579773},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6418383121490479},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.572160005569458},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5138697624206543},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.49744322896003723},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.468520849943161},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.45847395062446594},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.4518510699272156},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36478686332702637},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.32525843381881714},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3134838044643402},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2735990285873413},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.24021315574645996},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.12408006191253662},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10912132263183594},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpsr.2016.7525662","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpsr.2016.7525662","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 17th International Conference on High Performance Switching and Routing (HPSR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":15,"referenced_works":["https://openalex.org/W1139426851","https://openalex.org/W1435603161","https://openalex.org/W1919739679","https://openalex.org/W1968801809","https://openalex.org/W1994926493","https://openalex.org/W2057717673","https://openalex.org/W2083953017","https://openalex.org/W2089874955","https://openalex.org/W2111734949","https://openalex.org/W2139751271","https://openalex.org/W2165634007","https://openalex.org/W4248245037","https://openalex.org/W4253731216","https://openalex.org/W6628400919","https://openalex.org/W6640044220"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"The":[0],"programmability":[1],"of":[2,10,18,44,58,112,125],"the":[3,11,16,42,91,97,110,123,143,148,158],"network":[4,74],"data":[5,31,49],"plane":[6,32,50],"has":[7],"become":[8],"one":[9],"most":[12],"desirable":[13],"features":[14],"within":[15],"context":[17],"software":[19],"defined":[20,48],"networks,":[21],"with":[22,169],"P4":[23,47,88,136],"serving":[24],"as":[25],"a":[26,46,52,60,63,67,79,87,135],"domain-specific":[27],"language":[28],"for":[29,72,101],"defining":[30],"processing.":[33],"In":[34,115],"this":[35],"work,":[36],"we":[37],"are":[38],"motivated":[39],"to":[40,51,85,108,121,138],"address":[41],"challenges":[43],"mapping":[45],"heterogeneous":[53,145],"programmable":[54],"hardware":[55],"architecture":[56,71],"consisting":[57],"both":[59],"CPU":[61,126],"and":[62,104,127,132,166,176],"GPU,":[64],"which":[65],"includes":[66],"salient":[68],"parallel":[69],"SIMD":[70],"processing":[73],"flows.":[75],"We":[76,94],"first":[77],"design":[78],"toolset":[80,131],"that":[81,157],"can":[82],"be":[83],"used":[84],"map":[86],"program":[89,137],"onto":[90],"proposed":[92],"architecture.":[93,146],"then":[95],"optimize":[96],"GPU":[98,128,161],"kernel":[99],"designs":[100],"\u201cmatch-action\u201d":[102],"primitives":[103],"present":[105],"latency-hiding":[106],"techniques":[107],"reduce":[109],"overheads":[111],"CPU/GPU":[113],"communication.":[114],"addition,":[116],"load":[117],"balancing":[118],"is":[119],"investigated":[120],"maximize":[122],"utilization":[124],"resources.":[129],"Our":[130],"optimizations":[133],"allow":[134],"render":[139],"promising":[140],"performance":[141],"on":[142,152],"given":[144],"Specifically,":[147],"experimental":[149],"results":[150],"collected":[151],"our":[153],"prototype":[154],"systems":[155],"show":[156],"automatically":[159],"configured":[160],"kernels":[162],"achieve":[163],"scalable":[164],"lookup":[165],"classification":[167],"speeds":[168],"420":[170],"million":[171,180],"IP":[172],"lookups":[173],"per":[174,182],"second,":[175],"more":[177],"than":[178],"60":[179],"classifications":[181],"second":[183],"(for":[184],"4K":[185],"firewall":[186],"rules).":[187]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}