{"id":"https://openalex.org/W4200197440","doi":"https://doi.org/10.1109/iccad51958.2021.9643582","title":"GraphLily: Accelerating Graph Linear Algebra on HBM-Equipped FPGAs","display_name":"GraphLily: Accelerating Graph Linear Algebra on HBM-Equipped FPGAs","publication_year":2021,"publication_date":"2021-11-01","ids":{"openalex":"https://openalex.org/W4200197440","doi":"https://doi.org/10.1109/iccad51958.2021.9643582"},"language":"en","primary_location":{"id":"doi:10.1109/iccad51958.2021.9643582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad51958.2021.9643582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101586926","display_name":"Yuwei Hu","orcid":"https://orcid.org/0000-0002-2698-6811"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuwei Hu","raw_affiliation_strings":["School of Electrical and Computer Engineering, Cornell University,Ithaca,NY","School of Electrical and Computer Engineering, Cornell University, Ithaca, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University,Ithaca,NY","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039033697","display_name":"Yixiao Du","orcid":"https://orcid.org/0000-0002-6106-1283"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yixiao Du","raw_affiliation_strings":["School of Electrical and Computer Engineering, Cornell University,Ithaca,NY","School of Electrical and Computer Engineering, Cornell University, Ithaca, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University,Ithaca,NY","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053419294","display_name":"Ecenur Ustun","orcid":"https://orcid.org/0000-0001-6546-1367"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ecenur Ustun","raw_affiliation_strings":["School of Electrical and Computer Engineering, Cornell University,Ithaca,NY","School of Electrical and Computer Engineering, Cornell University, Ithaca, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University,Ithaca,NY","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037210004","display_name":"Zhiru Zhang","orcid":"https://orcid.org/0000-0002-0778-0308"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiru Zhang","raw_affiliation_strings":["School of Electrical and Computer Engineering, Cornell University,Ithaca,NY","School of Electrical and Computer Engineering, Cornell University, Ithaca, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University,Ithaca,NY","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9998000264167786,"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":0.9998000264167786,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9975000023841858,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9958000183105469,"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":0.8445672988891602},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7132336497306824},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5482585430145264},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4956399202346802},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.49018675088882446},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.47634461522102356},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4674438238143921},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46504393219947815},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43796128034591675},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3211541175842285},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17201682925224304}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8445672988891602},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7132336497306824},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5482585430145264},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4956399202346802},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.49018675088882446},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.47634461522102356},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4674438238143921},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46504393219947815},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43796128034591675},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3211541175842285},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17201682925224304},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad51958.2021.9643582","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad51958.2021.9643582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9200000166893005,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W78077100","https://openalex.org/W1543897857","https://openalex.org/W1910302617","https://openalex.org/W1969102784","https://openalex.org/W2053076698","https://openalex.org/W2080098453","https://openalex.org/W2106111377","https://openalex.org/W2116433835","https://openalex.org/W2139954584","https://openalex.org/W2146449469","https://openalex.org/W2150022482","https://openalex.org/W2157534438","https://openalex.org/W2157855196","https://openalex.org/W2171910722","https://openalex.org/W2276486856","https://openalex.org/W2284169075","https://openalex.org/W2287057303","https://openalex.org/W2461193710","https://openalex.org/W2583135230","https://openalex.org/W2798956872","https://openalex.org/W2898231337","https://openalex.org/W2903237845","https://openalex.org/W2907186209","https://openalex.org/W2914631005","https://openalex.org/W2962865652","https://openalex.org/W2973152414","https://openalex.org/W2987887101","https://openalex.org/W2997329429","https://openalex.org/W3034855459","https://openalex.org/W3092394454","https://openalex.org/W3098650335","https://openalex.org/W3100078588","https://openalex.org/W3103066605","https://openalex.org/W3103168911","https://openalex.org/W3132871189","https://openalex.org/W3133395503","https://openalex.org/W4232836277","https://openalex.org/W4235101327","https://openalex.org/W4245683599","https://openalex.org/W4253426709","https://openalex.org/W4255889623","https://openalex.org/W4256629673","https://openalex.org/W4294761111","https://openalex.org/W4316084067","https://openalex.org/W6603201521","https://openalex.org/W6756678368","https://openalex.org/W6766385987","https://openalex.org/W6774187331","https://openalex.org/W6776488958"],"related_works":["https://openalex.org/W1997955449","https://openalex.org/W79781788","https://openalex.org/W2144511445","https://openalex.org/W2386685757","https://openalex.org/W1997573906","https://openalex.org/W2529540995","https://openalex.org/W1501847821","https://openalex.org/W1981718088","https://openalex.org/W2105812312","https://openalex.org/W1993704253"],"abstract_inverted_index":{"Graph":[0],"processing":[1,61,212],"is":[2],"typically":[3],"memory":[4,11,22,34],"bound":[5],"due":[6],"to":[7,10,41,58,120,127,133,163,179,192,197,221],"low":[8],"compute":[9],"access":[12,17],"ratio":[13],"and":[14,105,130,216,224,237],"irregular":[15],"data":[16,141],"pattern.":[18],"The":[19,110,156],"emerging":[20],"high-bandwidth":[21],"(HBM)":[23],"delivers":[24],"exceptional":[25],"bandwidth":[26],"by":[27,73,149,234],"providing":[28],"multiple":[29,134],"channels":[30],"that":[31,122,207],"can":[32,187],"service":[33],"requests":[35],"concurrently,":[36],"thus":[37],"bringing":[38],"the":[39,44,75,94,137,146,160,167,198,231],"potential":[40],"significantly":[42],"boost":[43],"performance":[45],"of":[46,70,145],"graph":[47,54,60,71,81,211,244],"processing.":[48],"This":[49],"paper":[50],"proposes":[51],"GraphLily,":[52],"a":[53,67,114,151,171,177],"linear":[55,85],"algebra":[56,86],"overlay,":[57],"accelerate":[59],"on":[62,214,246],"HBM-equipped":[63],"FPGAs.":[64],"GraphLily":[65,88,174,218,248],"supports":[66],"rich":[68],"set":[69],"algorithms":[72,82],"adopting":[74],"GraphBLAS":[76,190],"programming":[77],"interface,":[78],"which":[79],"formulates":[80],"as":[83],"sparse":[84,115],"operations.":[87],"provides":[89],"efficient,":[90],"memory-optimized":[91],"accelerators":[92,245],"for":[93,202],"two":[95],"widely-used":[96],"kernels":[97],"in":[98,143],"GraphBLAS,":[99],"namely,":[100],"sparse-matrix":[101,106],"dense-vector":[102],"multiplication":[103,108],"(SpMV)":[104],"sparse-vector":[107],"(SpMSpV).":[109],"SpMV":[111,138,161],"accelerator":[112,139,158,162],"uses":[113],"matrix":[116],"storage":[117],"format":[118],"tailored":[119],"HBM":[121],"enables":[123],"streaming,":[124],"vectorized":[125],"accesses":[126,132,144],"each":[128],"channel":[129],"concurrent":[131],"channels.":[135],"Besides,":[136],"exploits":[140],"reuse":[142],"dense":[147],"vector":[148,169],"introducing":[150],"scalable":[152],"on-chip":[153],"buffer":[154],"design.":[155],"SpMSpV":[157],"complements":[159],"handle":[164],"cases":[165],"where":[166],"input":[168],"has":[170],"high":[172],"sparsity.":[173],"further":[175],"builds":[176],"middleware":[178],"provide":[180],"runtime":[181],"support.":[182],"With":[183],"this":[184],"middleware,":[185],"we":[186],"port":[188],"existing":[189],"programs":[191],"FPGAs":[193],"with":[194,209,241],"slight":[195],"modifications":[196],"original":[199],"code":[200],"intended":[201],"CPU/GPU":[203],"execution.":[204],"Evaluation":[205],"shows":[206],"compared":[208,240],"state-of-the-art":[210],"frameworks":[213],"CPUs":[215],"GPUs,":[217],"achieves":[219,249],"up":[220],"2.5":[222],"x":[223,226,236,251,253],"1.1":[225],"higher":[227,254],"throughput,":[228],"while":[229],"reducing":[230],"energy":[232],"consumption":[233],"8.1":[235],"2.4":[238],"x;":[239],"prior":[242],"single-purpose":[243],"FPGAs,":[247],"1.2":[250],"-1.9":[252],"throughput.":[255]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":24},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":11}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}