{"id":"https://openalex.org/W4211029478","doi":"https://doi.org/10.1145/3490422.3502326","title":"DecGNN: A Framework for Mapping Decoupled GNN Models onto CPU-FPGA Heterogeneous Platform","display_name":"DecGNN: A Framework for Mapping Decoupled GNN Models onto CPU-FPGA Heterogeneous Platform","publication_year":2022,"publication_date":"2022-02-11","ids":{"openalex":"https://openalex.org/W4211029478","doi":"https://doi.org/10.1145/3490422.3502326"},"language":"en","primary_location":{"id":"doi:10.1145/3490422.3502326","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490422.3502326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"},"type":"conference-abstract","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/A5101916609","display_name":"Bingyi Zhang","orcid":"https://orcid.org/0000-0002-8115-0814"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bingyi Zhang","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014103790","display_name":"Hanqing Zeng","orcid":"https://orcid.org/0000-0002-2578-2147"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hanqing Zeng","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033166029","display_name":"Viktor K. Prasanna","orcid":"https://orcid.org/0000-0002-1609-8589"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Viktor K. Prasanna","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"154","last_page":"154"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9886000156402588,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8176090717315674},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7835801839828491},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.7574313282966614},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6779841184616089},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6593528985977173},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5393047332763672},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5011162757873535},{"id":"https://openalex.org/keywords/design-space-exploration","display_name":"Design space exploration","score":0.4603756070137024},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.45645543932914734},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.4388009309768677},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.43248608708381653},{"id":"https://openalex.org/keywords/hardware-architecture","display_name":"Hardware architecture","score":0.4321347773075104},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4168497323989868},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.39003604650497437},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36450624465942383},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.150604248046875},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10221788287162781},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.10164335370063782},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09897956252098083},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.08608585596084595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8176090717315674},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7835801839828491},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.7574313282966614},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6779841184616089},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6593528985977173},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5393047332763672},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5011162757873535},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.4603756070137024},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.45645543932914734},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.4388009309768677},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.43248608708381653},{"id":"https://openalex.org/C65232700","wikidata":"https://www.wikidata.org/wiki/Q5656403","display_name":"Hardware architecture","level":3,"score":0.4321347773075104},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4168497323989868},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.39003604650497437},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36450624465942383},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.150604248046875},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10221788287162781},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.10164335370063782},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09897956252098083},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.08608585596084595},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3490422.3502326","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3490422.3502326","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2022 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","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":0,"referenced_works":[],"related_works":["https://openalex.org/W2419277311","https://openalex.org/W2143593481","https://openalex.org/W2007449167","https://openalex.org/W156843270","https://openalex.org/W2095778784","https://openalex.org/W2063532530","https://openalex.org/W2946338335","https://openalex.org/W3035130950","https://openalex.org/W2898008564","https://openalex.org/W3188788977"],"abstract_inverted_index":{"A":[0],"well-known":[1],"issue":[2],"in":[3,12,26],"mini-batch":[4],"GNN":[5,53,108,167],"inference":[6,168],"is":[7],"neighborhood":[8,149],"explosion.":[9],"This":[10],"results":[11],"two":[13,175,180],"challenges":[14],"for":[15,75],"its":[16],"hardware":[17,37,46,76,113,161,192],"acceleration:":[18],"(1)":[19,93],"high":[20,27,112,191],"computation":[21,101,165],"and":[22,29,100,148,195],"communication":[23],"costs":[24],"resulting":[25,188],"latency,":[28],"(2)":[30,115],"low":[31,36],"computation-to-communication":[32,69],"ratio":[33],"leading":[34],"to":[35,97,110,118,135],"utilization.":[38],"To":[39,78],"address":[40],"these":[41],"challenges,":[42],"we":[43,87,103,123,152],"propose":[44,88],"a":[45,125],"mapping":[47],"framework":[48,173],"following":[49,90],"the":[50,89,98,105,120,132,137,146,154,187,201],"recently":[51],"proposed":[52],"design":[54],"principle":[55],"of":[56,107,128,166],"model":[57,147],"depth-receptive":[58],"field":[59],"decoupling.":[60],"We":[61,170],"show":[62,185],"that":[63,186],"Decoupled":[64,81],"GNNs":[65,82],"enjoy":[66],"significantly":[67],"higher":[68],"ratio,":[70],"therefore,":[71],"are":[72],"more":[73],"suitable":[74],"acceleration.":[77],"efficiently":[79],"map":[80],"onto":[83],"CPU-FPGA":[84],"heterogeneous":[85],"platforms,":[86,178],"model-architecture":[91],"co-optimizations:":[92],"Model":[94],"instantiation:":[95],"according":[96],"bandwidth":[99],"resources,":[102],"determine":[104,153],"number":[106,127],"layers":[109],"achieve":[111,190],"utilization;":[114],"Neighbor":[116],"selection:":[117],"meet":[119],"application":[121],"constraint,":[122],"select":[124],"small":[126],"important":[129],"neighbors":[130],"surrounding":[131],"target":[133],"vertices":[134],"improve":[136],"throughput":[138],"without":[139],"sacrificing":[140],"accuracy;":[141],"(3)":[142],"Hardware":[143],"mapping:":[144],"given":[145],"defined":[150],"above,":[151],"accelerator":[155],"parameters":[156],"based":[157],"on":[158,174,203],"our":[159,172],"novel":[160],"templates,":[162],"enabling":[163],"fast":[164],"workloads.":[169],"evaluate":[171],"state-of-the-art":[176,204],"FPGA":[177],"using":[179],"models":[181],"(GCN,":[182],"GraphSAGE).":[183],"Experiments":[184],"designs":[189],"utilization":[193],"88%-94%":[194],"significant":[196],"speedup":[197],"(1.1x-2.5x)":[198],"compared":[199],"with":[200],"implementations":[202],"CPU-GPU":[205],"platform.":[206]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}