{"id":"https://openalex.org/W7166320557","doi":"https://doi.org/10.1145/3801487.3805612","title":"POSTER: Hardware Acceleration for Graph Neural Networks","display_name":"POSTER: Hardware Acceleration for Graph Neural Networks","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7166320557","doi":"https://doi.org/10.1145/3801487.3805612"},"language":"en","primary_location":{"id":"doi:10.1145/3801487.3805612","doi":"https://doi.org/10.1145/3801487.3805612","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3805612","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3801487.3805612?download=true","source":{"id":"https://openalex.org/S7407085882","display_name":"ACM International Conference on Computing Frontiers (CF)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3801487.3805612?download=true","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025404075","display_name":"Cory Davis","orcid":"https://orcid.org/0000-0003-2059-091X","observed_orcids":["https://orcid.org/0000-0003-2059-091X"]},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cory Davis","raw_affiliation_strings":["The University of Texas at San Antonio, San Antonio, USA"],"raw_orcid":"https://orcid.org/0000-0003-2059-091X","affiliations":[{"raw_affiliation_string":"The University of Texas at San Antonio, San Antonio, USA","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139507127","display_name":"Patrick Stockton","orcid":"https://orcid.org/0000-0002-5269-1910","observed_orcids":["https://orcid.org/0000-0002-5269-1910"]},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Stockton","raw_affiliation_strings":["The University of Texas at San Antonio, San Antonio, USA"],"raw_orcid":"https://orcid.org/0000-0002-5269-1910","affiliations":[{"raw_affiliation_string":"The University of Texas at San Antonio, San Antonio, USA","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010151984","display_name":"Eugene B John","orcid":"https://orcid.org/0000-0001-9494-4894","observed_orcids":["https://orcid.org/0000-0001-9494-4894"]},"institutions":[{"id":"https://openalex.org/I45438204","display_name":"The University of Texas at San Antonio","ror":"https://ror.org/01kd65564","country_code":"US","type":"education","lineage":["https://openalex.org/I45438204"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eugene B. John","raw_affiliation_strings":["The University of Texas at San Antonio, San Antonio, USA"],"raw_orcid":"https://orcid.org/0000-0001-9494-4894","affiliations":[{"raw_affiliation_string":"The University of Texas at San Antonio, San Antonio, USA","institution_ids":["https://openalex.org/I45438204"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111062876","display_name":"Jeeho Ryoo","orcid":"https://orcid.org/0009-0003-0401-3685","observed_orcids":["https://orcid.org/0009-0003-0401-3685"]},"institutions":[{"id":"https://openalex.org/I32907511","display_name":"Fairleigh Dickinson University","ror":"https://ror.org/04wkzvc75","country_code":"US","type":"education","lineage":["https://openalex.org/I32907511"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeeho Ryoo","raw_affiliation_strings":["Fairleigh Dickinson University, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0009-0003-0401-3685","affiliations":[{"raw_affiliation_string":"Fairleigh Dickinson University, Vancouver, Canada","institution_ids":["https://openalex.org/I32907511"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041246067","display_name":"Ebod Shojaei","orcid":"https://orcid.org/0009-0005-3367-1913","observed_orcids":["https://orcid.org/0009-0005-3367-1913"]},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ebod Shojaei","raw_affiliation_strings":["University of British Columbia, Vancouver, Canada"],"raw_orcid":"https://orcid.org/0009-0005-3367-1913","affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39926263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"347","last_page":"348"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4713999927043915,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.4713999927043915,"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":0.3208000063896179,"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":0.026200000196695328,"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/graph-neural-networks","display_name":"graph neural networks","score":0.9070000052452087},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"hardware acceleration","score":0.9789999723434448},{"id":"https://openalex.org/keywords/gpu-acceleration","display_name":"GPU acceleration","score":0.6800000071525574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6620000004768372},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40049999952316284},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32760000228881836},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2685999870300293},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2578999996185303},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2574000060558319},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3801487.3805612","doi":"https://doi.org/10.1145/3801487.3805612","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3805612","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3801487.3805612?download=true","source":{"id":"https://openalex.org/S7407085882","display_name":"ACM International Conference on Computing Frontiers (CF)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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:10.1145/3801487.3805612","doi":"https://doi.org/10.1145/3801487.3805612","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3801487.3805612","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3801487.3805612?download=true","source":{"id":"https://openalex.org/S7407085882","display_name":"ACM International Conference on Computing Frontiers (CF)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4458961679","display_name":"SHF: Medium: Collaborative Research: Predictive Modeling for Next-generation Heterogeneous System Design","funder_award_id":"1763848","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166320557.pdf","grobid_xml":"https://content.openalex.org/works/W7166320557.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2907492528","https://openalex.org/W3045200674","https://openalex.org/W3102510044","https://openalex.org/W3158399077","https://openalex.org/W4393407315"],"related_works":["https://openalex.org/W3202027370","https://openalex.org/W6969071711","https://openalex.org/W7197388214","https://openalex.org/W7134183236","https://openalex.org/W7028677362","https://openalex.org/W2402675130","https://openalex.org/W3200228538","https://openalex.org/W6936047806","https://openalex.org/W3091862797","https://openalex.org/W6992594957"],"abstract_inverted_index":{"Graph":[0],"Neural":[1],"Networks":[2],"deliver":[3],"state-of-the-art":[4],"performance":[5],"across":[6],"graph-structured":[7],"domains":[8],"but":[9],"remain":[10],"difficult":[11],"to":[12,50,59,83,118],"accelerate":[13],"on":[14,91,102,106,111,121],"modern":[15],"GPUs.":[16],"Their":[17],"sparse":[18],"neighborhood":[19],"aggregation":[20,125],"produces":[21],"non-coalesced,":[22],"bandwidth-intensive":[23],"memory":[24],"access":[25],"that":[26],"causes":[27],"pipeline":[28],"stalls":[29],"and":[30,108],"leaves":[31],"GPU":[32,52],"arithmetic":[33],"units":[34,48],"underutilized.":[35],"We":[36],"propose":[37],"Near-Cache":[38],"Compute":[39],"(NCC),":[40],"a":[41,67],"microarchitectural":[42],"extension":[43],"placing":[44],"lightweight":[45],"FP32":[46,57],"FMA":[47],"adjacent":[49],"each":[51],"L2":[53,62],"cache":[54],"bank,":[55],"enabling":[56],"operations":[58],"execute":[60],"at":[61],"latency":[63],"rather":[64],"than":[65],"incurring":[66],"DRAM":[68],"round-trip.":[69],"A":[70],"three-phase":[71],"SASS":[72],"compiler":[73],"pass":[74],"maps":[75],"eligible":[76],"LDG":[77],"\u2192":[78,80],"ALU":[79],"STG":[81],"patterns":[82],"NCC":[84,97],"ISA":[85],"extensions":[86],"without":[87],"application-level":[88],"changes.":[89],"Evaluated":[90],"Accel-Sim":[92],"against":[93],"an":[94],"A100":[95],"baseline,":[96],"achieves":[98],"1.44":[99],"\u00d7":[100,105,110,120],"speedup":[101],"LightGCN,":[103],"1.08":[104],"ExpressGNN,":[107],"1.06":[109],"GIN,":[112],"with":[113],"kernel-level":[114],"gains":[115],"of":[116],"up":[117],"9.5":[119],"the":[122],"most":[123],"memory-bound":[124],"kernels.":[126]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-06-28T00:00:00"}
