{"id":"https://openalex.org/W3130716829","doi":"https://doi.org/10.1145/3437801.3441578","title":"TurboTransformers","display_name":"TurboTransformers","publication_year":2021,"publication_date":"2021-02-17","ids":{"openalex":"https://openalex.org/W3130716829","doi":"https://doi.org/10.1145/3437801.3441578","mag":"3130716829"},"language":"en","primary_location":{"id":"doi:10.1145/3437801.3441578","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437801.3441578","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437801.3441578","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3437801.3441578","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069911612","display_name":"Jiarui Fang","orcid":"https://orcid.org/0000-0002-6724-2763"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarui Fang","raw_affiliation_strings":["Tencent Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458535","display_name":"Yang Yu","orcid":"https://orcid.org/0000-0003-1972-6496"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yu","raw_affiliation_strings":["Tencent Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024922240","display_name":"Chengduo Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengduo Zhao","raw_affiliation_strings":["Tencent Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066557235","display_name":"Jie Zhou","orcid":"https://orcid.org/0000-0002-3836-4163"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhou","raw_affiliation_strings":["Tencent Inc, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Inc, Beijing, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":7.1634,"has_fulltext":true,"cited_by_count":115,"citation_normalized_percentile":{"value":0.9766604,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"389","last_page":"402"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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/T10320","display_name":"Neural Networks and Applications","score":0.9966999888420105,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.994700014591217,"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":0.7939745187759399},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7206043004989624},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6403428912162781},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6373991966247559},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5022332668304443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4888855516910553},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.4160040616989136},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.38524749875068665},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2184491753578186},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09290000796318054},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08078178763389587}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939745187759399},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7206043004989624},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6403428912162781},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6373991966247559},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5022332668304443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4888855516910553},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.4160040616989136},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.38524749875068665},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2184491753578186},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09290000796318054},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08078178763389587},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3437801.3441578","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437801.3441578","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437801.3441578","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3437801.3441578","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3437801.3441578","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3437801.3441578","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332564","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3130716829.pdf","grobid_xml":"https://content.openalex.org/works/W3130716829.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2064675550","https://openalex.org/W2097117768","https://openalex.org/W2152175008","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2791673912","https://openalex.org/W2798291715","https://openalex.org/W2804032941","https://openalex.org/W2949251082","https://openalex.org/W2950813464","https://openalex.org/W2963403868","https://openalex.org/W2970971581","https://openalex.org/W2982157693","https://openalex.org/W3005664618","https://openalex.org/W3014367186","https://openalex.org/W3101543398","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W4385280324","https://openalex.org/W2912153778","https://openalex.org/W4387163678","https://openalex.org/W4288108708","https://openalex.org/W2973430807","https://openalex.org/W2984436043","https://openalex.org/W2912831041","https://openalex.org/W2890685186","https://openalex.org/W2904359912","https://openalex.org/W2796130100"],"abstract_inverted_index":{"The":[0,91],"transformer":[1,67],"is":[2],"the":[3,9,19,75],"most":[4],"critical":[5],"algorithm":[6],"innovation":[7],"of":[8,32,48,80,88,93],"Nature":[10],"Language":[11],"Processing":[12],"(NLP)":[13],"field":[14],"in":[15,35,53,86],"recent":[16],"years.":[17],"Unlike":[18],"Recurrent":[20],"Neural":[21],"Network":[22],"(RNN)":[23],"models,":[24],"transformers":[25],"are":[26,59],"able":[27],"to":[28,39,73,100],"process":[29],"on":[30,42],"dimensions":[31,95],"sequence":[33],"lengths":[34],"parallel,":[36],"therefore":[37],"leads":[38],"better":[40],"accuracy":[41],"long":[43],"sequences.":[44],"However,":[45],"efficient":[46,101],"deployments":[47],"them":[49],"for":[50],"online":[51],"services":[52],"data":[54],"centers":[55],"equipped":[56],"with":[57],"GPUs":[58],"not":[60],"easy.":[61],"First,":[62],"more":[63,71],"computation":[64],"introduced":[65],"by":[66],"structures":[68],"makes":[69],"it":[70],"challenging":[72],"meet":[74],"latency":[76],"and":[77,104],"throughput":[78],"constraints":[79],"serving.":[81],"Second,":[82],"NLP":[83],"tasks":[84],"take":[85],"sentences":[87],"variable":[89],"length.":[90],"variability":[92],"input":[94],"brings":[96],"a":[97],"severe":[98],"problem":[99],"memory":[102],"management":[103],"serving":[105],"optimization.":[106]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":16},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-09-01T08:31:24.195828","created_date":"2021-03-01T00:00:00"}