{"id":"https://openalex.org/W7166321899","doi":"https://doi.org/10.1145/3801487.3801817","title":"Row-wise Inter-Phase Pipelining for Hardware-Efficient GCN Acceleration","display_name":"Row-wise Inter-Phase Pipelining for Hardware-Efficient GCN Acceleration","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7166321899","doi":"https://doi.org/10.1145/3801487.3801817"},"language":null,"primary_location":{"id":"doi:10.1145/3801487.3801817","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3801817","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3801487.3801817","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110370772","display_name":"Shi Chen","orcid":"https://orcid.org/0009-0005-0009-2624"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Chen","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0005-0009-2624","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061525547","display_name":"Junsheng Chang","orcid":"https://orcid.org/0009-0006-3061-980X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junsheng Chang","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0009-0006-3061-980X","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720832","display_name":"Yang Guo","orcid":"https://orcid.org/0000-0001-9050-0866"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Guo","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-9050-0866","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101790620","display_name":"Li Shen","orcid":"https://orcid.org/0000-0001-9043-2998"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Shen","raw_affiliation_strings":["National University of Defense Technology, Changsha, Hunan, China"],"raw_orcid":"https://orcid.org/0000-0001-9043-2998","affiliations":[{"raw_affiliation_string":"National University of Defense Technology, Changsha, Hunan, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.93132863,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"290","last_page":"298"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.30399999022483826,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.30399999022483826,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.29820001125335693,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.056699998676776886,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speedup","display_name":"Speedup","score":0.7275000214576721},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.698199987411499},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.6309000253677368},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6015999913215637},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.5230000019073486},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.4106000065803528},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.40299999713897705},{"id":"https://openalex.org/keywords/geometric-transformation","display_name":"Geometric transformation","score":0.3968999981880188},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.362199991941452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8043000102043152},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7275000214576721},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.698199987411499},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6618000268936157},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.6309000253677368},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6015999913215637},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.5230000019073486},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.4106000065803528},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.40299999713897705},{"id":"https://openalex.org/C56435381","wikidata":"https://www.wikidata.org/wiki/Q1196371","display_name":"Geometric transformation","level":3,"score":0.3968999981880188},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3736000061035156},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.335099995136261},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.2800999879837036},{"id":"https://openalex.org/C121838778","wikidata":"https://www.wikidata.org/wiki/Q7619924","display_name":"Storage efficiency","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C183778304","wikidata":"https://www.wikidata.org/wiki/Q165474","display_name":"Commutative property","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.25189998745918274},{"id":"https://openalex.org/C2781357197","wikidata":"https://www.wikidata.org/wiki/Q5757597","display_name":"High memory","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3801487.3801817","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3801817","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3801487.3801817","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3801817","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM International Conference on Computing Frontiers","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.9140912294387817,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2168113051","https://openalex.org/W2725159389","https://openalex.org/W2794952988","https://openalex.org/W2946332877","https://openalex.org/W2970929262","https://openalex.org/W2979310060","https://openalex.org/W2979750740","https://openalex.org/W2990045899","https://openalex.org/W3006586535","https://openalex.org/W3016542674","https://openalex.org/W3016832937","https://openalex.org/W3017228913","https://openalex.org/W3105753905","https://openalex.org/W3133253223","https://openalex.org/W3155922894","https://openalex.org/W3157609068","https://openalex.org/W3206743063","https://openalex.org/W4205993941","https://openalex.org/W4214755140","https://openalex.org/W4306317895","https://openalex.org/W4318541578","https://openalex.org/W4360831960","https://openalex.org/W4380881063","https://openalex.org/W4385800972","https://openalex.org/W4389491877","https://openalex.org/W4399205157","https://openalex.org/W4402571373","https://openalex.org/W4404455164"],"related_works":[],"abstract_inverted_index":{"Graph":[0],"Convolutional":[1],"Networks":[2],"(GCNs)":[3],"are":[4,115],"widely":[5],"deployed":[6],"for":[7,49],"learning":[8],"on":[9,29,82],"graph-structured":[10],"data.":[11],"Yet,":[12],"their":[13],"canonical":[14],"two-phase":[15],"execution,":[16],"consisting":[17],"of":[18,66,73,121,169],"feature":[19],"transformation":[20,45,88],"followed":[21],"by":[22,181,192],"neighborhood":[23],"aggregation,":[24,50],"suffers":[25],"from":[26],"severe":[27],"inefficiencies":[28],"existing":[30],"accelerators.":[31],"The":[32,135],"prevailing":[33],"phase-decoupled":[34],"model":[35],"explicitly":[36],"stores":[37],"dense":[38],"intermediate":[39],"results":[40],"to":[41,104,128],"off-chip":[42,119],"memory":[43],"after":[44],"and":[46,89,123,147,179,184,188],"reloads":[47],"them":[48],"incurring":[51],"substantial":[52],"inter-phase":[53],"data":[54],"movement.":[55],"Additionally,":[56],"irregular":[57],"access":[58,127],"patterns":[59],"cause":[60],"intra-phase":[61],"redundancy":[62],"through":[63,140],"repeated":[64],"fetches":[65],"sparse":[67],"inputs.":[68],"To":[69],"overcome":[70],"both":[71],"forms":[72],"redundancy,":[74],"we":[75],"propose":[76],"IPRS-GCN,":[77],"a":[78,95,165],"streaming":[79,126],"accelerator":[80],"built":[81],"Inter-Phase":[83],"Row-Streaming":[84],"(IPRS).":[85],"IPRS":[86],"fuses":[87],"aggregation":[90],"at":[91],"row":[92],"granularity":[93],"into":[94],"single":[96],"pipeline,":[97],"forwarding":[98],"each":[99],"node\u2019s":[100],"transformed":[101],"features":[102],"directly":[103],"its":[105],"neighbors":[106],"via":[107],"the":[108],"Row":[109],"Queue":[110],"as":[111,113],"soon":[112],"they":[114],"computed.":[116],"This":[117],"eliminates":[118],"storage":[120],"intermediates":[122],"enforces":[124],"single-pass":[125],"inputs":[129],"while":[130],"keeping":[131],"weights":[132],"resident":[133],"on-chip.":[134],"architecture":[136],"realizes":[137],"this":[138],"dataflow":[139],"lightweight":[141],"mechanisms":[142],"including":[143],"conflict-aware":[144],"non-zero":[145],"packing":[146],"degree-adaptive":[148],"buffering,":[149],"achieving":[150],"near-ideal":[151],"compute":[152],"utilization":[153],"with":[154],"minimal":[155],"on-chip":[156],"footprint.":[157],"Evaluated":[158],"across":[159],"five":[160],"real-world":[161],"datasets,":[162],"IPRS-GCN":[163],"achieves":[164],"geometric":[166],"mean":[167],"speedup":[168],"107.74":[170],"\u00d7":[171,183],"over":[172],"an":[173],"NVIDIA":[174],"V100":[175],"GPU,":[176],"outperforms":[177],"HyGCN":[178],"AWB-GCN":[180],"7.74":[182],"2.12":[185],"\u00d7,":[186],"respectively,":[187],"improves":[189],"energy":[190],"efficiency":[191],"1.37":[193],"\u00d7.":[194]},"counts_by_year":[],"updated_date":"2026-06-28T06:20:29.262167","created_date":"2026-06-28T00:00:00"}