{"id":"https://openalex.org/W4282962596","doi":"https://doi.org/10.1145/3524059.3532372","title":"Handling heavy-tailed input of transformer inference on GPUs","display_name":"Handling heavy-tailed input of transformer inference on GPUs","publication_year":2022,"publication_date":"2022-06-16","ids":{"openalex":"https://openalex.org/W4282962596","doi":"https://doi.org/10.1145/3524059.3532372"},"language":"en","primary_location":{"id":"doi:10.1145/3524059.3532372","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524059.3532372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th ACM International Conference on Supercomputing","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/A5024085713","display_name":"Jiangsu Du","orcid":"https://orcid.org/0000-0003-4707-9492"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangsu Du","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048148542","display_name":"Jiazhi Jiang","orcid":"https://orcid.org/0000-0002-1417-3012"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazhi Jiang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658705","display_name":"Yang You","orcid":"https://orcid.org/0000-0003-2816-4384"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang You","raw_affiliation_strings":["National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041534890","display_name":"Dan Huang","orcid":"https://orcid.org/0000-0001-5582-1031"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Huang","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["Sun Yat-sen University, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987999796867371,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9925000071525574,"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":0.784259557723999},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7445030808448792},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6393108367919922},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6361083388328552},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5287111401557922},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4622478485107422},{"id":"https://openalex.org/keywords/batch-processing","display_name":"Batch processing","score":0.4538026452064514},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.33291012048721313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3283834457397461},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20314103364944458},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18779420852661133},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10677990317344666},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10180389881134033},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08564522862434387},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.07222959399223328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.784259557723999},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7445030808448792},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6393108367919922},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6361083388328552},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5287111401557922},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4622478485107422},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.4538026452064514},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.33291012048721313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3283834457397461},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20314103364944458},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18779420852661133},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10677990317344666},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10180389881134033},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08564522862434387},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.07222959399223328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3524059.3532372","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524059.3532372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th ACM International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W2251939518","https://openalex.org/W2592549418","https://openalex.org/W2607892599","https://openalex.org/W2626696598","https://openalex.org/W2747329762","https://openalex.org/W2799054028","https://openalex.org/W2804032941","https://openalex.org/W2896457183","https://openalex.org/W2912918068","https://openalex.org/W2914209329","https://openalex.org/W2963748441","https://openalex.org/W3021293129","https://openalex.org/W3130716829","https://openalex.org/W3174167939","https://openalex.org/W3210432446","https://openalex.org/W4212774754","https://openalex.org/W6680890276","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2021850411","https://openalex.org/W4312263439","https://openalex.org/W2117014006","https://openalex.org/W4233815414","https://openalex.org/W2372170743","https://openalex.org/W1558545464","https://openalex.org/W2074301136","https://openalex.org/W1984303163","https://openalex.org/W1509211761","https://openalex.org/W2358725432"],"abstract_inverted_index":{"Transformer-based":[0],"models":[1,39],"achieve":[2],"superior":[3],"accuracy":[4],"in":[5,19,58],"the":[6,32,47,62,74],"field":[7],"of":[8,51,69],"natural":[9],"language":[10],"processing":[11,27,34,64],"(NLP)":[12],"and":[13,40,57,72],"start":[14],"to":[15],"be":[16],"widely":[17],"deployed":[18],"production.":[20],"As":[21],"a":[22,59],"popular":[23],"deployment":[24],"device,":[25],"graphic":[26],"units":[28],"(GPUs)":[29],"basically":[30],"adopt":[31],"batch":[33,63],"technique":[35],"for":[36],"inferring":[37],"transformer-based":[38],"achieving":[41],"high":[42],"hardware":[43],"performance.":[44],"However,":[45],"as":[46],"input":[48],"sequence":[49],"lengths":[50],"NLP":[52],"tasks":[53],"are":[54],"generally":[55],"variable":[56],"heavy-tailed":[60],"distribution,":[61],"will":[65],"bring":[66],"large":[67],"amounts":[68],"redundant":[70],"computation":[71],"hurt":[73],"practical":[75],"efficiency.":[76]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
