{"id":"https://openalex.org/W2970217631","doi":null,"title":"UWB-GCN: Hardware Acceleration of Graph-Convolution-Network through Runtime Workload Rebalancing.","display_name":"UWB-GCN: Hardware Acceleration of Graph-Convolution-Network through Runtime Workload Rebalancing.","publication_year":2019,"publication_date":"2019-08-23","ids":{"openalex":"https://openalex.org/W2970217631","mag":"2970217631"},"language":"en","primary_location":{"id":"mag:2970217631","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1908.10834v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/1908.10834v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078443672","display_name":"Tong Geng","orcid":"https://orcid.org/0000-0002-3644-2922","observed_orcids":["https://orcid.org/0000-0002-3644-2922"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong Geng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3644-2922","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413657","display_name":"Ang Li","orcid":"https://orcid.org/0000-0003-3734-9137","observed_orcids":["https://orcid.org/0000-0003-3734-9137"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ang Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3734-9137","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734913","display_name":"Tianqi Wang","orcid":"https://orcid.org/0000-0002-5921-6565","observed_orcids":["https://orcid.org/0000-0002-5921-6565"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianqi Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5921-6565","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009432979","display_name":"Chunshu Wu","orcid":"https://orcid.org/0009-0006-2039-0853","observed_orcids":["https://orcid.org/0009-0006-2039-0853"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunshu Wu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0006-2039-0853","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414600","display_name":"Yanfei Li","orcid":"https://orcid.org/0000-0003-0812-2339","observed_orcids":["https://orcid.org/0000-0003-0812-2339"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanfei Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0812-2339","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041853964","display_name":"Antonino Tumeo","orcid":"https://orcid.org/0000-0001-9452-120X","observed_orcids":["https://orcid.org/0000-0001-9452-120X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonino Tumeo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021051610","display_name":"Martin Herbordt","orcid":"https://orcid.org/0000-0002-3443-9113","observed_orcids":["https://orcid.org/0000-0002-3443-9113"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martin C. Herbordt","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3443-9113","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.46219998598098755,"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":0.46219998598098755,"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":0.1851000040769577,"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/T12292","display_name":"Graph Theory and Algorithms","score":0.147599995136261,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/graph-convolutional-networks","display_name":"graph convolutional networks","score":0.9980000257492065},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"hardware acceleration","score":0.9259999990463257},{"id":"https://openalex.org/keywords/load-balancing","display_name":"load balancing","score":0.6589999794960022},{"id":"https://openalex.org/keywords/auto-tuning","display_name":"auto-tuning","score":0.8949999809265137},{"id":"https://openalex.org/keywords/fpga","display_name":"FPGA","score":0.49900001287460327},{"id":"https://openalex.org/keywords/dynamic-workload-distribution","display_name":"dynamic workload distribution","score":0.6600000262260437},{"id":"https://openalex.org/keywords/remote-switching","display_name":"remote switching","score":0.8460000157356262},{"id":"https://openalex.org/keywords/processing-element-utilization","display_name":"processing element utilization","score":0.7250000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8084189891815186},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.7145788073539734},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.6193366050720215},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6073900461196899},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5422263145446777},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43078190088272095},{"id":"https://openalex.org/C13251829","wikidata":"https://www.wikidata.org/wiki/Q3085841","display_name":"Dense graph","level":5,"score":0.42683202028274536},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4183501899242401},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34528249502182007},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32204920053482056},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2871280908584595},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28122782707214355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25412559509277344},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19584104418754578},{"id":"https://openalex.org/C203776342","wikidata":"https://www.wikidata.org/wiki/Q1378376","display_name":"Line graph","level":3,"score":0.0},{"id":"https://openalex.org/C102192266","wikidata":"https://www.wikidata.org/wiki/Q4545823","display_name":"1-planar graph","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2970217631","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1908.10834v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null}],"best_oa_location":{"id":"mag:2970217631","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1908.10834v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4943999946117401}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1501856433","https://openalex.org/W2048266589","https://openalex.org/W2285660444","https://openalex.org/W2289252105","https://openalex.org/W2468907370","https://openalex.org/W2606780347","https://openalex.org/W2613119772","https://openalex.org/W2803533564","https://openalex.org/W2809418595"],"related_works":["https://openalex.org/W3105753905","https://openalex.org/W3157903467","https://openalex.org/W4205993941","https://openalex.org/W4226439885","https://openalex.org/W4312726386","https://openalex.org/W3046757167","https://openalex.org/W3199624392","https://openalex.org/W4379116054","https://openalex.org/W3201267481","https://openalex.org/W4380366711"],"abstract_inverted_index":{"Deep":[0],"learning":[1,57],"systems":[2],"have":[3],"been":[4],"successfully":[5],"applied":[6],"to":[7,34,39,91,142],"Euclidean":[8],"data":[9,44],"such":[10],"as":[11],"images,":[12],"video,":[13],"and":[14,21,73,80,117,178,188],"audio.":[15],"In":[16,83,120],"many":[17,50],"applications,":[18],"however,":[19],"information":[20],"their":[22],"relationships":[23],"are":[24,69,110],"better":[25],"expressed":[26],"with":[27,54,160],"graphs.":[28],"Graph":[29],"Convolutional":[30],"Networks":[31],"(GCNs)":[32],"appear":[33],"be":[35],"a":[36,135,189],"promising":[37],"approach":[38],"efficiently":[40],"learn":[41],"from":[42],"graph":[43,127],"structures,":[45],"having":[46],"shown":[47],"advantages":[48],"in":[49,102],"critical":[51],"applications.":[52],"As":[53],"other":[55],"deep":[56],"modalities,":[58],"hardware":[59],"acceleration":[60],"is":[61,65,153],"critical.":[62],"The":[63],"challenge":[64],"that":[66,166],"real-world":[67,104],"graphs":[68],"often":[70],"extremely":[71],"large":[72,136],"unbalanced;":[74],"this":[75,84],"poses":[76],"significant":[77],"performance":[78,181],"demands":[79],"design":[81],"challenges.":[82],"paper,":[85],"we":[86],"propose":[87],"Autotuning-Workload-Balancing":[88],"GCN":[89,93,191],"(AWB-GCN)":[90],"accelerate":[92],"inference.":[94],"To":[95],"address":[96],"the":[97,125,131,149],"issue":[98],"of":[99,138],"workload":[100,132],"imbalance":[101],"processing":[103,139],"graphs,":[105],"three":[106],"hardware-based":[107],"autotuning":[108],"techniques":[109],"proposed:":[111],"dynamic":[112],"distribution":[113,133],"smoothing,":[114],"remote":[115],"switching,":[116],"row":[118],"remapping.":[119],"particular,":[121],"AWB-GCN":[122,168],"continuously":[123],"monitors":[124],"sparse":[126],"pattern,":[128],"dynamically":[129],"adjusts":[130],"among":[134],"number":[137],"elements":[140],"(up":[141],"4K":[143],"PEs),":[144],"and,":[145],"after":[146],"converging,":[147],"reuses":[148],"ideal":[150],"configuration.":[151],"Evaluation":[152],"performed":[154],"using":[155],"an":[156],"Intel":[157],"D5005":[158],"FPGA":[159],"five":[161],"commonly-used":[162],"datasets.":[163],"Results":[164],"show":[165],"4K-PE":[167],"can":[169],"significantly":[170],"elevate":[171],"PE":[172],"utilization":[173],"by":[174],"7.7x":[175],"on":[176],"average":[177],"demonstrate":[179],"considerable":[180],"speedups":[182],"over":[183],"CPUs":[184],"(3255x),":[185],"GPUs":[186],"(80.3x),":[187],"prior":[190],"accelerator":[192],"(5.1x).":[193]},"counts_by_year":[{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2019-09-05T00:00:00"}