{"id":"https://openalex.org/W4395106460","doi":"https://doi.org/10.1145/3620666.3651336","title":"FEASTA: A Flexible and Efficient Accelerator for Sparse Tensor Algebra in Machine Learning","display_name":"FEASTA: A Flexible and Efficient Accelerator for Sparse Tensor Algebra in Machine Learning","publication_year":2024,"publication_date":"2024-04-24","ids":{"openalex":"https://openalex.org/W4395106460","doi":"https://doi.org/10.1145/3620666.3651336"},"language":"en","primary_location":{"id":"doi:10.1145/3620666.3651336","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3620666.3651336","pdf_url":null,"source":null,"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 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3620666.3651336","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101518558","display_name":"Kai Zhong","orcid":"https://orcid.org/0000-0002-8448-9530"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kai Zhong","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103138440","display_name":"Zhenhua Zhu","orcid":"https://orcid.org/0009-0007-9259-7180"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Zhu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015946486","display_name":"Guohao Dai","orcid":"https://orcid.org/0000-0003-0849-3252"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohao Dai","raw_affiliation_strings":["Infinigence-AI, Beijing, China","Shanghai Jiao Tong University, Shanghai, China","Shanghai Jiao Tong University, Shanghai, China Infinigence-AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Infinigence-AI, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China Infinigence-AI, Beijing, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023007010","display_name":"Hongyi Wang","orcid":"https://orcid.org/0009-0008-7095-7963"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyi Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020244808","display_name":"Xinhao Yang","orcid":"https://orcid.org/0009-0001-9739-2930"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhao Yang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038968284","display_name":"Haoyu Zhang","orcid":"https://orcid.org/0009-0003-3889-8688"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyu Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102769280","display_name":"Jin Si","orcid":"https://orcid.org/0009-0006-6829-9637"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Si","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076000240","display_name":"Qiuli Mao","orcid":"https://orcid.org/0009-0004-8777-2579"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiuli Mao","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026831784","display_name":"Shulin Zeng","orcid":"https://orcid.org/0000-0002-1030-3748"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shulin Zeng","raw_affiliation_strings":["Infinigence-AI, Beijing, China","Tsinghua University, Beijing, China","Tsinghua University, Beijing, China Infinigence-AI, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Infinigence-AI, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua University, Beijing, China Infinigence-AI, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014087671","display_name":"Ke Hong","orcid":"https://orcid.org/0000-0002-5768-6037"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Hong","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049888384","display_name":"Genghan Zhang","orcid":"https://orcid.org/0000-0002-3866-8167"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Genghan Zhang","raw_affiliation_strings":["Stanford University, Stanford, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023755254","display_name":"Huazhong Yang","orcid":"https://orcid.org/0000-0003-2421-353X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huazhong Yang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":13,"corresponding_author_ids":["https://openalex.org/A5101518558"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":5.3835,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9666083,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"349","last_page":"366"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.972599983215332,"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":0.7167689800262451},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.6722493171691895},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5573173761367798},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5287361145019531},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5272278785705566},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4683961868286133},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4166707992553711},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34454792737960815},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11461147665977478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7167689800262451},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.6722493171691895},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5573173761367798},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5287361145019531},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5272278785705566},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4683961868286133},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4166707992553711},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34454792737960815},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11461147665977478},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3620666.3651336","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3620666.3651336","pdf_url":null,"source":null,"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 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3620666.3651336","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3620666.3651336","pdf_url":null,"source":null,"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 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.9100000262260437}],"awards":[{"id":"https://openalex.org/G1799421016","display_name":null,"funder_award_id":"61832007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2045798616","display_name":null,"funder_award_id":"62325405","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G663016133","display_name":null,"funder_award_id":"62204164","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6803541034","display_name":null,"funder_award_id":"U21B2031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6839492696","display_name":null,"funder_award_id":"U19B2019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8262591375","display_name":null,"funder_award_id":"62104128","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W1665214252","https://openalex.org/W2082051746","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2336215235","https://openalex.org/W2590246587","https://openalex.org/W2626696598","https://openalex.org/W2794952988","https://openalex.org/W2798482398","https://openalex.org/W2798724095","https://openalex.org/W2886821472","https://openalex.org/W2894703649","https://openalex.org/W2896457183","https://openalex.org/W2921480401","https://openalex.org/W2963125977","https://openalex.org/W2971933740","https://openalex.org/W2979310060","https://openalex.org/W2979747168","https://openalex.org/W2980186997","https://openalex.org/W2981972129","https://openalex.org/W2987129023","https://openalex.org/W3016542674","https://openalex.org/W3016735325","https://openalex.org/W3016832937","https://openalex.org/W3034877463","https://openalex.org/W3040024858","https://openalex.org/W3040646053","https://openalex.org/W3080980548","https://openalex.org/W3081279536","https://openalex.org/W3092618035","https://openalex.org/W3102446692","https://openalex.org/W3103168911","https://openalex.org/W3116564952","https://openalex.org/W3129093240","https://openalex.org/W3129482887","https://openalex.org/W3132695675","https://openalex.org/W3152893301","https://openalex.org/W3155919942","https://openalex.org/W3155922894","https://openalex.org/W3158233278","https://openalex.org/W3158831985","https://openalex.org/W3175498521","https://openalex.org/W3181186005","https://openalex.org/W3195003484","https://openalex.org/W3198975860","https://openalex.org/W3206453033","https://openalex.org/W3207878884","https://openalex.org/W3217045543","https://openalex.org/W4205983429","https://openalex.org/W4211060338","https://openalex.org/W4211095909","https://openalex.org/W4211147898","https://openalex.org/W4213311498","https://openalex.org/W4214718338","https://openalex.org/W4229005866","https://openalex.org/W4285503871","https://openalex.org/W4287363917","https://openalex.org/W4296473245","https://openalex.org/W4308083753","https://openalex.org/W4313484599","https://openalex.org/W4318540786","https://openalex.org/W4327930477","https://openalex.org/W6760001035","https://openalex.org/W6780277617","https://openalex.org/W6842757321"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W2171015181","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W4323831447","https://openalex.org/W1998888015","https://openalex.org/W4321636545","https://openalex.org/W2023476765"],"abstract_inverted_index":{"Recently,":[0],"sparse":[1,109,157,213,220],"tensor":[2],"algebra":[3],"(SpTA)":[4],"plays":[5],"an":[6,171],"increasingly":[7],"important":[8],"role":[9],"in":[10,65],"machine":[11],"learning.":[12],"However,":[13,44],"due":[14],"to":[15,114,200,218],"the":[16,21,32,98,104,108,116,127,131,145,164,168,184],"unstructured":[17],"sparsity":[18,88],"of":[19,31,120,152,175],"SpTA,":[20],"general-purpose":[22],"processors":[23],"(e.g.,":[24],"GPU":[25,201],"and":[26,49,61,74,125,156,161,177,186,208,223],"CPU)":[27],"are":[28,39],"inefficient":[29],"because":[30],"underutilized":[33],"hardware":[34],"resources.":[35],"Sparse":[36,78],"kernel":[37],"accelerators":[38],"optimized":[40],"for":[41,77,154],"specific":[42],"tasks.":[43],"their":[45],"dedicated":[46],"processing":[47],"units":[48,180],"data":[50,112],"paths":[51],"cannot":[52],"effectively":[53],"support":[54],"other":[55],"SpTA":[56,84,122,139],"tasks":[57,85],"with":[58,86],"different":[59,150],"dataflow":[60,99],"various":[62,87,203],"sparsity,":[63],"resulting":[64],"performance":[66,211],"degradation.":[67],"This":[68],"paper":[69],"proposes":[70],"FEASTA,":[71],"a":[72,137],"Flexible":[73],"Efficient":[75],"Accelerator":[76],"Tensor":[79],"Algebra.":[80],"To":[81],"process":[82],"general":[83,121,138],"efficiently,":[89],"we":[90,102],"design":[91],"FEASTA":[92,192,205,229],"meticulously":[93],"from":[94],"three":[95],"levels.":[96],"At":[97,130,167],"abstraction":[100],"level,":[101,136,170],"apply":[103],"Einstein":[105],"Summation":[106],"on":[107,144,212],"fiber":[110,128],"tree":[111],"structure":[113],"model":[115],"unified":[117],"execution":[118,146],"flow":[119],"as":[123],"joining":[124],"merging":[126],"tree.":[129],"instruction":[132,165],"set":[133],"architecture":[134,169,173],"(ISA)":[135],"ISA":[140],"is":[141,181],"proposed":[142],"based":[143],"flow.":[147],"It":[148],"includes":[149],"types":[151],"instructions":[153],"dense":[155],"data,":[158],"achieving":[159],"flexibility":[160],"efficiency":[162,197,233],"at":[163],"level.":[166],"instruction-driven":[172],"consisting":[174],"configurable":[176],"high-performance":[178],"function":[179],"designed,":[182],"supporting":[183],"flexible":[185],"efficient":[187],"ISA.":[188],"Evaluations":[189],"show":[190],"that":[191],"has":[193],"5.40\u00d7":[194],"geomean":[195],"energy":[196,232],"improvements":[198],"compared":[199,217],"among":[202],"workloads.":[204],"delivers":[206],"1.47\u00d7":[207],"3.19\u00d7":[209],"higher":[210],"matrix":[214,221],"multiplication":[215],"kernels":[216],"state-of-the-art":[219],"accelerator":[222],"CPU":[224],"extension.":[225],"Across":[226],"diverse":[227],"kernels,":[228],"achieves":[230],"1.69-12.70\u00d7":[231],"over":[234],"existing":[235],"architectures.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}