{"id":"https://openalex.org/W4404317065","doi":"https://doi.org/10.1109/tcad.2024.3496882","title":"Vesper: A Versatile Sparse Linear Algebra Accelerator With Configurable Compute Patterns","display_name":"Vesper: A Versatile Sparse Linear Algebra Accelerator With Configurable Compute Patterns","publication_year":2024,"publication_date":"2024-11-13","ids":{"openalex":"https://openalex.org/W4404317065","doi":"https://doi.org/10.1109/tcad.2024.3496882"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2024.3496882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3496882","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},"type":"article","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/A5061332970","display_name":"Hanchen Jin","orcid":"https://orcid.org/0000-0001-5485-3648"},"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":"Hanchen Jin","raw_affiliation_strings":["Graduate School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","Graduate School of Electrical and Computer Engineering, Cornell University, USA"],"raw_orcid":"https://orcid.org/0000-0001-5485-3648","affiliations":[{"raw_affiliation_string":"Graduate School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Graduate School of Electrical and Computer Engineering, Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029785504","display_name":"Zichao Yue","orcid":"https://orcid.org/0009-0003-8585-5947"},"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":"Zichao Yue","raw_affiliation_strings":["Graduate School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","Graduate School of Electrical and Computer Engineering, Cornell University, USA"],"raw_orcid":"https://orcid.org/0009-0003-8585-5947","affiliations":[{"raw_affiliation_string":"Graduate School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Graduate School of Electrical and Computer Engineering, Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062730166","display_name":"Zhongyuan Zhao","orcid":"https://orcid.org/0000-0002-6637-553X"},"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":"Zhongyuan Zhao","raw_affiliation_strings":["School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","School of Electrical and Computer Engineering, Cornell University, USA"],"raw_orcid":"https://orcid.org/0000-0002-6637-553X","affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, USA","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":["Graduate School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","Graduate School of Electrical and Computer Engineering, Cornell University, USA"],"raw_orcid":"https://orcid.org/0000-0002-6106-1283","affiliations":[{"raw_affiliation_string":"Graduate School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Graduate School of Electrical and Computer Engineering, Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103232740","display_name":"Chenhui Deng","orcid":"https://orcid.org/0009-0006-6482-5855"},"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":"Chenhui Deng","raw_affiliation_strings":["Graduate School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","Graduate School of Electrical and Computer Engineering, Cornell University, USA"],"raw_orcid":"https://orcid.org/0009-0006-6482-5855","affiliations":[{"raw_affiliation_string":"Graduate School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Graduate School of Electrical and Computer Engineering, Cornell University, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103070090","display_name":"Nitish Srivastava","orcid":"https://orcid.org/0000-0002-3442-5352"},"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":"Nitish Srivastava","raw_affiliation_strings":["Graduate School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","Graduate School of Electrical and Computer Engineering, Cornell University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Graduate School of Electrical and Computer Engineering, Cornell University, USA","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":["Graduate School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","School of Electrical and Computer Engineering, Cornell University, USA"],"raw_orcid":"https://orcid.org/0000-0002-0778-0308","affiliations":[{"raw_affiliation_string":"Graduate School of Electrical and Computer Engineering, Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"School of Electrical and Computer Engineering, Cornell University, USA","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":0.3268,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61649944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"44","issue":"5","first_page":"1731","last_page":"1744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.983299970626831,"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":0.983299970626831,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9692000150680542,"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/T10682","display_name":"Quantum Computing Algorithms and Architecture","score":0.9366999864578247,"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/linear-algebra","display_name":"Linear algebra","score":0.7359312176704407},{"id":"https://openalex.org/keywords/linear-particle-accelerator","display_name":"Linear particle accelerator","score":0.546364963054657},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4997413158416748},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.45274266600608826},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4490377604961395},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.40355032682418823},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.327253520488739},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.18011260032653809},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.15547898411750793},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.09219026565551758},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.06130576133728027}],"concepts":[{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.7359312176704407},{"id":"https://openalex.org/C180048950","wikidata":"https://www.wikidata.org/wiki/Q836828","display_name":"Linear particle accelerator","level":3,"score":0.546364963054657},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4997413158416748},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.45274266600608826},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4490377604961395},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.40355032682418823},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.327253520488739},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.18011260032653809},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.15547898411750793},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.09219026565551758},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.06130576133728027},{"id":"https://openalex.org/C168834538","wikidata":"https://www.wikidata.org/wiki/Q3705329","display_name":"Beam (structure)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2024.3496882","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3496882","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W1526797232","https://openalex.org/W1567268701","https://openalex.org/W1665157575","https://openalex.org/W1918839972","https://openalex.org/W1935978687","https://openalex.org/W2002555321","https://openalex.org/W2020306365","https://openalex.org/W2024818089","https://openalex.org/W2035080386","https://openalex.org/W2066636486","https://openalex.org/W2089437293","https://openalex.org/W2147657366","https://openalex.org/W2419507445","https://openalex.org/W2461193710","https://openalex.org/W2590246587","https://openalex.org/W2625457103","https://openalex.org/W2794952988","https://openalex.org/W2950656546","https://openalex.org/W2964306489","https://openalex.org/W2979310060","https://openalex.org/W2979747168","https://openalex.org/W3016735325","https://openalex.org/W3016832937","https://openalex.org/W3016904661","https://openalex.org/W3103168911","https://openalex.org/W3130421533","https://openalex.org/W3133347161","https://openalex.org/W3155922894","https://openalex.org/W3158233278","https://openalex.org/W3158275024","https://openalex.org/W3173889673","https://openalex.org/W3187908937","https://openalex.org/W3195003484","https://openalex.org/W3198975860","https://openalex.org/W4200197440","https://openalex.org/W4211147898","https://openalex.org/W4280557024","https://openalex.org/W4281621462","https://openalex.org/W4281658036","https://openalex.org/W4281685651","https://openalex.org/W4285504028","https://openalex.org/W4293024216","https://openalex.org/W4308083753","https://openalex.org/W4318540786","https://openalex.org/W4318541582","https://openalex.org/W4327930477","https://openalex.org/W4327930517","https://openalex.org/W4380875466","https://openalex.org/W4389500477","https://openalex.org/W6628929334","https://openalex.org/W6636599907"],"related_works":["https://openalex.org/W4285303061","https://openalex.org/W2525488343","https://openalex.org/W622366405","https://openalex.org/W2477677129","https://openalex.org/W2378563121","https://openalex.org/W2383666998","https://openalex.org/W2063186542","https://openalex.org/W2358786979","https://openalex.org/W2388645548","https://openalex.org/W616292901"],"abstract_inverted_index":{"Sparse":[0],"linear":[1],"algebra":[2],"(SLA)":[3],"operations":[4],"are":[5,31,76,229],"fundamental":[6],"building":[7],"blocks":[8],"for":[9,57,117,183,231],"many":[10],"important":[11,105],"applications,":[12],"such":[13,84],"as":[14,85],"data":[15],"analytics,":[16],"graph":[17],"processing,":[18],"machine":[19],"learning,":[20],"and":[21,41,71,97,134,187,259,270],"scientific":[22],"computing.":[23],"In":[24,236],"particular,":[25],"four":[26,104],"compute":[27,82,114,159,190],"kernels":[28,107,119,186,258],"in":[29],"SLA":[30,59,106,148,185,234,257],"widely":[32],"used,":[33],"including":[34],"sparse-matrix-dense-vector":[35],"multiplication,":[36,38,40],"sparse-matrix-dense-matrix":[37],"sparse-matrix-sparse-vector":[39],"sparse-matrix-sparse-matrix":[42],"multiplication.":[43],"Recently,":[44],"an":[45,139,147,249],"active":[46],"area":[47],"of":[48,123,129,146,196,204,263],"research":[49],"has":[50],"emerged":[51],"to":[52,79,111,142,268],"build":[53,166],"specialized":[54],"hardware":[55,154,180],"accelerators":[56,227],"these":[58],"kernels.":[60],"However,":[61],"existing":[62],"efforts":[63],"mostly":[64],"focus":[65],"on":[66,151,200,241],"accelerating":[67],"a":[68,80,95,152,157,167,201,215,232,242],"single":[69],"kernel":[70,149],"the":[72,113,130,144,175,179,188,194,225,276],"proposed":[73],"accelerator":[74,100,171],"architectures":[75],"often":[77],"limited":[78],"specific":[81,158,233],"pattern,":[83],"inner,":[86],"outer,":[87],"or":[88,217],"row-wise":[89],"product.":[90],"This":[91],"work":[92],"proposes":[93],"Vesper,":[94],"high-performance":[96],"versatile":[98],"sparse":[99],"that":[101,173,212,228,254],"supports":[102],"all":[103],"while":[108],"being":[109],"configurable":[110],"execute":[112],"patterns":[115],"suitable":[116],"different":[118,184],"under":[120],"various":[121],"degrees":[122,262],"sparsity.":[124],"To":[125],"enable":[126],"rapid":[127],"exploration":[128],"large":[131],"architectural":[132],"design":[133],"configuration":[135,155],"space,":[136],"we":[137,165,238],"devise":[138],"analytical":[140],"model":[141],"estimate":[143],"performance":[145,195],"running":[150],"given":[153],"using":[156,198],"pattern.":[160],"Guided":[161],"by":[162],"our":[163],"model,":[164],"flexible":[168],"yet":[169],"efficient":[170],"architecture":[172],"maximizes":[174],"resource":[176],"sharing":[177],"amongst":[178],"modules":[181],"used":[182],"associated":[189],"patterns.":[191],"We":[192],"evaluate":[193,239],"Vesper":[197,213,240,273],"gem5":[199],"diverse":[202],"set":[203],"matrices":[205],"from":[206],"SuiteSparse.":[207],"Our":[208],"experiment":[209],"results":[210],"show":[211],"achieves":[214],"comparable":[216],"higher":[218],"throughput":[219],"with":[220],"increased":[221],"bandwidth":[222],"efficiency":[223],"than":[224],"state-of-the-art":[226],"tailor-made":[230],"kernel.":[235],"addition,":[237],"real-world":[243],"application":[244],"called":[245],"label":[246],"propagation":[247],"(LP),":[248],"iterative":[250],"graph-based":[251],"learning":[252],"algorithm":[253,278],"involves":[255],"multiple":[256],"exhibits":[260],"varying":[261],"sparsity":[264],"across":[265],"iterations.":[266],"Compared":[267],"CPU-":[269],"GPU-based":[271],"executions,":[272],"speeds":[274],"up":[275],"LP":[277],"by$12.0\\times":[279],"$and$1.7\\times":[280],"$,":[281],"respectively.":[282]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}