{"id":"https://openalex.org/W4360831840","doi":"https://doi.org/10.1109/hpca56546.2023.10071058","title":"VEGETA: Vertically-Integrated Extensions for Sparse/Dense GEMM Tile Acceleration on CPUs","display_name":"VEGETA: Vertically-Integrated Extensions for Sparse/Dense GEMM Tile Acceleration on CPUs","publication_year":2023,"publication_date":"2023-02-01","ids":{"openalex":"https://openalex.org/W4360831840","doi":"https://doi.org/10.1109/hpca56546.2023.10071058"},"language":"en","primary_location":{"id":"doi:10.1109/hpca56546.2023.10071058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10071058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","raw_type":"proceedings-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/A5069792279","display_name":"Geonhwa Jeong","orcid":"https://orcid.org/0000-0001-6659-3927"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Geonhwa Jeong","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001744939","display_name":"Sana Damani","orcid":"https://orcid.org/0000-0001-6976-9000"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sana Damani","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008320997","display_name":"Abhimanyu Rajeshkumar Bambhaniya","orcid":"https://orcid.org/0000-0003-0145-9713"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhimanyu Rajeshkumar Bambhaniya","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064436855","display_name":"Eric Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Qin","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024082060","display_name":"Christopher J. Hughes","orcid":"https://orcid.org/0009-0009-2888-0314"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher J. Hughes","raw_affiliation_strings":["Intel Labs"],"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036799188","display_name":"Sreenivas Subramoney","orcid":"https://orcid.org/0000-0001-5372-0173"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sreenivas Subramoney","raw_affiliation_strings":["Intel Labs"],"affiliations":[{"raw_affiliation_string":"Intel Labs","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000822269","display_name":"Hyesoon Kim","orcid":"https://orcid.org/0000-0002-6061-7825"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyesoon Kim","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034089074","display_name":"Tushar Krishna","orcid":"https://orcid.org/0000-0001-5738-6942"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tushar Krishna","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5069792279"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":8.0717,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.98465081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"259","last_page":"272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9958999752998352,"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/computer-science","display_name":"Computer science","score":0.7887252569198608},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6321297883987427},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.6228234171867371},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.533380389213562},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5085541009902954},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.48812136054039},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.48649829626083374},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4763743579387665},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.41941896080970764},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3588639497756958},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2885270118713379},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13307753205299377}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887252569198608},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6321297883987427},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.6228234171867371},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.533380389213562},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5085541009902954},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.48812136054039},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.48649829626083374},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4763743579387665},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.41941896080970764},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3588639497756958},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2885270118713379},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13307753205299377},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpca56546.2023.10071058","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpca56546.2023.10071058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"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":45,"referenced_works":["https://openalex.org/W2017369466","https://openalex.org/W2134633067","https://openalex.org/W2194775991","https://openalex.org/W2289252105","https://openalex.org/W2595551253","https://openalex.org/W2606722458","https://openalex.org/W2625457103","https://openalex.org/W2794952988","https://openalex.org/W2900228909","https://openalex.org/W2914209329","https://openalex.org/W2915480215","https://openalex.org/W2931743911","https://openalex.org/W2945146780","https://openalex.org/W2964080840","https://openalex.org/W2979310060","https://openalex.org/W2979545880","https://openalex.org/W2980186997","https://openalex.org/W3012143782","https://openalex.org/W3012178976","https://openalex.org/W3016542674","https://openalex.org/W3016735325","https://openalex.org/W3016832937","https://openalex.org/W3040024858","https://openalex.org/W3042343931","https://openalex.org/W3100023286","https://openalex.org/W3103168911","https://openalex.org/W3105753905","https://openalex.org/W3130236035","https://openalex.org/W3133446571","https://openalex.org/W3185702163","https://openalex.org/W3190761184","https://openalex.org/W3211907200","https://openalex.org/W3212852614","https://openalex.org/W4246166885","https://openalex.org/W4287208846","https://openalex.org/W4292779060","https://openalex.org/W4302296459","https://openalex.org/W6638632666","https://openalex.org/W6751349269","https://openalex.org/W6755207826","https://openalex.org/W6763737044","https://openalex.org/W6778883912","https://openalex.org/W6789946416","https://openalex.org/W6794457956","https://openalex.org/W6803607599"],"related_works":["https://openalex.org/W2293771254","https://openalex.org/W4221142455","https://openalex.org/W3121828480","https://openalex.org/W2039875226","https://openalex.org/W2914631005","https://openalex.org/W2032786851","https://openalex.org/W2952630098","https://openalex.org/W3132517792","https://openalex.org/W4318969866","https://openalex.org/W4285148873"],"abstract_inverted_index":{"Deep":[0],"Learning":[1],"(DL)":[2],"acceleration":[3],"support":[4,69,104,112],"in":[5,43,130],"CPUs":[6,30,66],"has":[7],"recently":[8],"gained":[9],"a":[10,92,132],"lot":[11],"of":[12,59,75,83,94,120],"traction,":[13],"with":[14,22,117],"several":[15],"companies":[16],"(Arm,":[17],"Intel,":[18],"IBM)":[19],"announcing":[20],"products":[21],"specialized":[23],"matrix":[24,78,101,128],"engines":[25,102],"accessible":[26],"via":[27],"GEMM":[28],"instructions.":[29],"are":[31],"pervasive":[32],"and":[33,56,80,86,96,139,148],"need":[34],"to":[35,52,67,72,103,123],"handle":[36],"diverse":[37,114],"requirements":[38],"across":[39],"DL":[40,48,115],"workloads":[41,49],"running":[42,143],"edge/HPC/cloud":[44],"platforms.":[45],"Therefore,":[46],"as":[47],"embrace":[50],"sparsity":[51,71,107],"reduce":[53],"the":[54,76,84,124],"computations":[55],"memory":[57],"size":[58],"models,":[60],"it":[61],"is":[62],"also":[63],"imperative":[64],"for":[65,70,108,113],"add":[68],"avoid":[73],"under-utilization":[74],"dense":[77,100,127],"engine":[79,129,134],"inefficient":[81],"usage":[82],"caches":[85],"registers.":[87],"This":[88],"work":[89],"presents":[90],"VEGETA,":[91],"set":[93],"ISA":[95],"microarchitecture":[97],"extensions":[98],"over":[99],"flexible":[105],"structured":[106],"CPUs,":[109,131],"enabling":[110],"programmable":[111],"models":[116],"varying":[118],"degrees":[119],"sparsity.":[121],"Compared":[122],"state-of-the-art":[125],"(SOTA)":[126],"VEGETA":[133],"provides":[135],"1.09\u00d7,":[136],"2.20\u00d7,":[137],"3.74\u00d7,":[138],"3.28\u00d7":[140],"speed-ups":[141],"when":[142],"4:4":[144],"(dense),":[145],"2:4,":[146],"1:4,":[147],"unstructured":[149],"(95%)":[150],"sparse":[151],"DNN":[152],"layers.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":8}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}