{"id":"https://openalex.org/W4318541554","doi":"https://doi.org/10.1145/3575693.3575698","title":"STI: Turbocharge NLP Inference at the Edge via Elastic Pipelining","display_name":"STI: Turbocharge NLP Inference at the Edge via Elastic Pipelining","publication_year":2023,"publication_date":"2023-01-27","ids":{"openalex":"https://openalex.org/W4318541554","doi":"https://doi.org/10.1145/3575693.3575698"},"language":"en","primary_location":{"id":"doi:10.1145/3575693.3575698","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3575693.3575698","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3575693.3575698","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 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","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/10.1145/3575693.3575698","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102749086","display_name":"Liwei Guo","orcid":"https://orcid.org/0000-0001-8516-8045"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liwei Guo","raw_affiliation_strings":["University of Virginia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026240192","display_name":"Wonkyo Choe","orcid":"https://orcid.org/0000-0002-7799-9946"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wonkyo Choe","raw_affiliation_strings":["University of Virginia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia, USA","institution_ids":["https://openalex.org/I51556381"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025585492","display_name":"Felix Xiaozhu Lin","orcid":"https://orcid.org/0000-0002-1615-6419"},"institutions":[{"id":"https://openalex.org/I51556381","display_name":"University of Virginia","ror":"https://ror.org/0153tk833","country_code":"US","type":"education","lineage":["https://openalex.org/I51556381"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Xiaozhu Lin","raw_affiliation_strings":["University of Virginia, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Virginia, USA","institution_ids":["https://openalex.org/I51556381"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51556381"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"791","last_page":"803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9923999905586243,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9923999905586243,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9919000267982483,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9889000058174133,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8482257127761841},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7924242615699768},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.7552273273468018},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5212367177009583},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.5166121125221252},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4138835668563843},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4062402844429016},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1734892725944519},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16550761461257935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8482257127761841},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7924242615699768},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.7552273273468018},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5212367177009583},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5166121125221252},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4138835668563843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4062402844429016},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1734892725944519},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16550761461257935},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3575693.3575698","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3575693.3575698","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3575693.3575698","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 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3575693.3575698","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3575693.3575698","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3575693.3575698","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 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1852190989","display_name":"Collaborative Research: CNS Core: Medium: Understanding and Strengthening Memory Security for Non-Volatile Memory","funder_award_id":"2106893","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2484545922","display_name":"CAREER: A Trustworthy and Verifiable Software Backplane for the Cloud Edge","funder_award_id":"2128725","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8345018822","display_name":"SPX: Write Once, Run on Anything: Verified, Tuned Accelerator Kernels from High Level Specifications","funder_award_id":"1919197","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4318541554.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W1987520741","https://openalex.org/W1988888548","https://openalex.org/W1995145055","https://openalex.org/W2020631075","https://openalex.org/W2064675550","https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2897268228","https://openalex.org/W2921309956","https://openalex.org/W2923014074","https://openalex.org/W2924431334","https://openalex.org/W2946794439","https://openalex.org/W2960863015","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W2963341956","https://openalex.org/W2969388332","https://openalex.org/W2972324944","https://openalex.org/W2982041622","https://openalex.org/W2982479999","https://openalex.org/W2997958863","https://openalex.org/W3000666106","https://openalex.org/W3034457371","https://openalex.org/W3034666739","https://openalex.org/W3035251378","https://openalex.org/W3100985894","https://openalex.org/W3102021588","https://openalex.org/W3144271226","https://openalex.org/W3155243801","https://openalex.org/W3155853474","https://openalex.org/W3162665866","https://openalex.org/W3163516730","https://openalex.org/W3173374050","https://openalex.org/W3177265267","https://openalex.org/W3193626058","https://openalex.org/W3198374546","https://openalex.org/W3207622241","https://openalex.org/W4220890574","https://openalex.org/W4239187549","https://openalex.org/W4280572358","https://openalex.org/W4283030313"],"related_works":["https://openalex.org/W3034529322","https://openalex.org/W2029404707","https://openalex.org/W2046435967","https://openalex.org/W2055243143","https://openalex.org/W2113597336","https://openalex.org/W2115913271","https://openalex.org/W3008625068","https://openalex.org/W3128807919","https://openalex.org/W3176411177","https://openalex.org/W3035501883"],"abstract_inverted_index":{"Natural":[0],"Language":[1],"Processing":[2],"(NLP)":[3],"inference":[4,14],"is":[5,15],"seeing":[6],"increasing":[7],"adoption":[8],"by":[9,75,89],"mobile":[10,50,90],"applications,":[11],"where":[12],"on-device":[13],"desirable":[16],"for":[17],"crucially":[18],"preserving":[19],"user":[20],"data":[21],"privacy":[22],"and":[23,38,125,139],"avoiding":[24],"network":[25],"roundtrips.":[26],"Yet,":[27],"the":[28,44,58,94,98,114,134],"unprecedented":[29],"size":[30],"of":[31,48],"an":[32],"NLP":[33],"model":[34,60,99,123],"stresses":[35],"both":[36],"latency":[37],"memory,":[39],"creating":[40],"a":[41,49,54,83,109,119],"tension":[42],"between":[43,137],"two":[45],"key":[46],"resources":[47],"device.":[51],"To":[52],"meet":[53],"target":[55],"latency,":[56],"holding":[57],"whole":[59],"in":[61],"memory":[62,73,91],"launches":[63],"execution":[64,126],"as":[65,67,106,108],"soon":[66],"possible":[68],"but":[69],"increases":[70],"one":[71],"app\u2019s":[72],"footprints":[74],"several":[76],"times,":[77],"limiting":[78],"its":[79],"benefits":[80],"to":[81,118,133],"only":[82],"few":[84,110],"inferences":[85],"before":[86],"being":[87],"recycled":[88],"management.":[92],"On":[93],"other":[95],"hand,":[96],"loading":[97,124],"from":[100],"storage":[101],"on":[102],"demand":[103],"incurs":[104],"IO":[105,130,138],"long":[107],"seconds,":[111],"far":[112],"exceeding":[113],"delay":[115],"range":[116],"satisfying":[117],"user;":[120],"pipelining":[121],"layerwise":[122],"does":[127],"not":[128],"hide":[129],"either,":[131],"due":[132],"high":[135],"skewness":[136],"computation":[140],"delays.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}