{"id":"https://openalex.org/W4395106465","doi":"https://doi.org/10.1145/3620666.3651333","title":"Boost Linear Algebra Computation Performance via Efficient VNNI Utilization","display_name":"Boost Linear Algebra Computation Performance via Efficient VNNI Utilization","publication_year":2024,"publication_date":"2024-04-24","ids":{"openalex":"https://openalex.org/W4395106465","doi":"https://doi.org/10.1145/3620666.3651333"},"language":"en","primary_location":{"id":"doi:10.1145/3620666.3651333","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620666.3651333","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"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/A5100397092","display_name":"Hao Zhou","orcid":"https://orcid.org/0009-0009-3536-7623"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Zhou","raw_affiliation_strings":["Enflame-Tech Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-3536-7623","affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035098350","display_name":"Qian-Ru Han","orcid":"https://orcid.org/0009-0003-7829-2963"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiukun Han","raw_affiliation_strings":["Enflame-Tech Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0003-7829-2963","affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101555572","display_name":"Heng Shi","orcid":"https://orcid.org/0000-0002-1779-9221"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heng Shi","raw_affiliation_strings":["Enflame-Tech Inc., Shanghai, China","SJTU, Shanghai, China","Enflame-Tech Inc., Shanghai, China SJTU, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1779-9221","affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]},{"raw_affiliation_string":"SJTU, Shanghai, China","institution_ids":[]},{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China SJTU, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291785","display_name":"Yalin Zhang","orcid":"https://orcid.org/0009-0001-0533-1111"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yalin Zhang","raw_affiliation_strings":["Enflame-Tech Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0001-0533-1111","affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023243107","display_name":"Jianguo Yao","orcid":"https://orcid.org/0000-0002-1142-4496"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianguo Yao","raw_affiliation_strings":["Enflame-Tech Inc., Shanghai, China","SJTU, Shanghai, China","Enflame-Tech Inc., Shanghai, China SJTU, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1142-4496","affiliations":[{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China","institution_ids":[]},{"raw_affiliation_string":"SJTU, Shanghai, China","institution_ids":[]},{"raw_affiliation_string":"Enflame-Tech Inc., Shanghai, China SJTU, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4514,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46830171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"149","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987000226974487,"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":0.9987000226974487,"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/T10320","display_name":"Neural Networks and Applications","score":0.9955999851226807,"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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8067589998245239},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7364276051521301},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.6942969560623169},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6797324419021606},{"id":"https://openalex.org/keywords/linear-algebra","display_name":"Linear algebra","score":0.6593342423439026},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5590848326683044},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.492527574300766},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4428805112838745},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.43674707412719727},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38560375571250916},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34934911131858826},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2570943832397461},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24668201804161072},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21726617217063904},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08866903185844421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8067589998245239},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7364276051521301},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.6942969560623169},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6797324419021606},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.6593342423439026},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5590848326683044},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.492527574300766},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4428805112838745},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.43674707412719727},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38560375571250916},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34934911131858826},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2570943832397461},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24668201804161072},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21726617217063904},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08866903185844421},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3620666.3651333","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620666.3651333","pdf_url":null,"source":null,"license":null,"license_id":null,"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":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1975594295","https://openalex.org/W2099404643","https://openalex.org/W2108556169","https://openalex.org/W2111394443","https://openalex.org/W2135736783","https://openalex.org/W2160145830","https://openalex.org/W2252007067","https://openalex.org/W2288740281","https://openalex.org/W2294933397","https://openalex.org/W2330908417","https://openalex.org/W2333659671","https://openalex.org/W2488840986","https://openalex.org/W2765425776","https://openalex.org/W2792271488","https://openalex.org/W2798960592","https://openalex.org/W2896457183","https://openalex.org/W2896938601","https://openalex.org/W3008658471","https://openalex.org/W3008964021","https://openalex.org/W3094502228","https://openalex.org/W3121932930","https://openalex.org/W3122286897","https://openalex.org/W3123639931","https://openalex.org/W3125750521","https://openalex.org/W3152824079","https://openalex.org/W3205717712","https://openalex.org/W4220850685","https://openalex.org/W4226443139","https://openalex.org/W4244894488","https://openalex.org/W4245767887","https://openalex.org/W4246166885","https://openalex.org/W4255465399","https://openalex.org/W4281932226","https://openalex.org/W4285503968"],"related_works":["https://openalex.org/W2121300814","https://openalex.org/W2037547261","https://openalex.org/W2534771569","https://openalex.org/W4231091074","https://openalex.org/W1886613375","https://openalex.org/W4236081792","https://openalex.org/W4250583430","https://openalex.org/W4234406076","https://openalex.org/W2010731026","https://openalex.org/W2019451907"],"abstract_inverted_index":{"Intel's":[0],"Vector":[1],"Neural":[2],"Network":[3],"Instruction":[4],"(VNNI)":[5],"provides":[6],"higher":[7],"efficiency":[8],"on":[9],"calculating":[10],"dense":[11],"linear":[12],"algebra":[13],"(DLA)":[14],"computations":[15],"than":[16],"conventional":[17],"SIMD":[18],"instructions.":[19],"However,":[20],"existing":[21],"auto-vectorizers":[22],"frequently":[23],"deliver":[24],"suboptimal":[25],"utilization":[26],"of":[27],"VNNI":[28],"by":[29,64],"either":[30],"failing":[31],"to":[32],"recognize":[33],"VNNI's":[34],"unique":[35],"computation":[36],"pattern":[37,69],"at":[38],"the":[39,65],"innermost":[40],"loops/basic":[41],"blocks,":[42],"or":[43],"producing":[44],"inferior":[45],"code":[46,60],"through":[47],"constrained":[48],"and":[49,71],"rudimentary":[50],"peephole":[51],"optimizations/pattern":[52],"matching":[53],"techniques.":[54],"Auto-tuning":[55],"frameworks":[56],"might":[57],"generate":[58],"proficient":[59],"but":[61],"are":[62],"hampered":[63],"necessity":[66],"for":[67],"sophisticated":[68],"templates":[70],"extensive":[72],"search":[73],"processes.":[74]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}