{"id":"https://openalex.org/W4395106409","doi":"https://doi.org/10.1145/3620666.3651352","title":"SpecPIM: Accelerating Speculative Inference on PIM-Enabled System via Architecture-Dataflow Co-Exploration","display_name":"SpecPIM: Accelerating Speculative Inference on PIM-Enabled System via Architecture-Dataflow Co-Exploration","publication_year":2024,"publication_date":"2024-04-24","ids":{"openalex":"https://openalex.org/W4395106409","doi":"https://doi.org/10.1145/3620666.3651352"},"language":"en","primary_location":{"id":"doi:10.1145/3620666.3651352","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620666.3651352","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/A5089919148","display_name":"Cong Li","orcid":"https://orcid.org/0000-0001-7760-3254"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cong Li","raw_affiliation_strings":["School of Integrated Circuits, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7760-3254","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001078878","display_name":"Zhe Zhou","orcid":"https://orcid.org/0000-0001-7929-8054"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhe Zhou","raw_affiliation_strings":["School of Integrated Circuits, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7929-8054","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072186367","display_name":"Size Zheng","orcid":"https://orcid.org/0000-0002-9471-1780"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Size Zheng","raw_affiliation_strings":["School of Integrated Circuits, School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9471-1780","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003491032","display_name":"Jiaxi Zhang","orcid":"https://orcid.org/0000-0001-6599-6142"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxi Zhang","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6599-6142","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100604860","display_name":"Yun Liang","orcid":"https://orcid.org/0000-0002-9076-7998"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yun Liang","raw_affiliation_strings":["Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","School of Integrated Circuits, Peking University, Beijing, China","School of Integrated Circuits, Peking University, Beijing, China Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9076-7998","affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210165198"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089719475","display_name":"Guangyu Sun","orcid":"https://orcid.org/0000-0002-7315-6589"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210165198","display_name":"Beijing Advanced Sciences and Innovation Center","ror":"https://ror.org/05qm21180","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165198"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyu Sun","raw_affiliation_strings":["Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","School of Integrated Circuits, Peking University, Beijing, China","School of Integrated Circuits, Peking University, Beijing, China Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7315-6589","affiliations":[{"raw_affiliation_string":"Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","institution_ids":["https://openalex.org/I4210165198"]},{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"School of Integrated Circuits, Peking University, Beijing, China Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210165198"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.8524,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.99491094,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"950","last_page":"965"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9965999722480774,"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":0.9965999722480774,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9962000250816345,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9955000281333923,"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":0.8095858097076416},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.77813720703125},{"id":"https://openalex.org/keywords/inefficiency","display_name":"Inefficiency","score":0.5715372562408447},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5115166902542114},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.4432342052459717},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4186999201774597},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.41823670268058777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3529757261276245},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3489915132522583},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24378308653831482},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16436076164245605},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08343952894210815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8095858097076416},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.77813720703125},{"id":"https://openalex.org/C2778869765","wikidata":"https://www.wikidata.org/wiki/Q6028363","display_name":"Inefficiency","level":2,"score":0.5715372562408447},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5115166902542114},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.4432342052459717},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4186999201774597},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.41823670268058777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3529757261276245},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3489915132522583},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24378308653831482},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16436076164245605},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08343952894210815},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3620666.3651352","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620666.3651352","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":[],"awards":[{"id":"https://openalex.org/G4460768019","display_name":null,"funder_award_id":"62032001","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1975237352","https://openalex.org/W1981943579","https://openalex.org/W2045431893","https://openalex.org/W2513721464","https://openalex.org/W2545376626","https://openalex.org/W2562213348","https://openalex.org/W2605347906","https://openalex.org/W2783681199","https://openalex.org/W2884360532","https://openalex.org/W2884361556","https://openalex.org/W2896090304","https://openalex.org/W2904570726","https://openalex.org/W2935331687","https://openalex.org/W2940862705","https://openalex.org/W2963566954","https://openalex.org/W2979719709","https://openalex.org/W2982008795","https://openalex.org/W2982157693","https://openalex.org/W3017521908","https://openalex.org/W3030163527","https://openalex.org/W3042598257","https://openalex.org/W3043023836","https://openalex.org/W3157531038","https://openalex.org/W3158275024","https://openalex.org/W3160360002","https://openalex.org/W3189166979","https://openalex.org/W3190062760","https://openalex.org/W3190092209","https://openalex.org/W3191222816","https://openalex.org/W3204998121","https://openalex.org/W3205200804","https://openalex.org/W3207399097","https://openalex.org/W3210580311","https://openalex.org/W3212403328","https://openalex.org/W4220972538","https://openalex.org/W4226479682","https://openalex.org/W4280489237","https://openalex.org/W4281932226","https://openalex.org/W4288083528","https://openalex.org/W4297097348","https://openalex.org/W4308083513","https://openalex.org/W4310561894","https://openalex.org/W4318328413","https://openalex.org/W4321636575","https://openalex.org/W4360831749","https://openalex.org/W4360831828","https://openalex.org/W4385834084","https://openalex.org/W4386763946","https://openalex.org/W4387064011","https://openalex.org/W4387064057","https://openalex.org/W4389491877","https://openalex.org/W6739901393"],"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/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W4389471172"],"abstract_inverted_index":{"Generative":[0],"large":[1,41],"language":[2,31,42],"models'":[3],"(LLMs)":[4],"inference":[5,20,49],"suffers":[6],"from":[7],"inefficiency":[8],"because":[9],"of":[10,54,72,85],"the":[11,39,52,55,68,73,82],"token":[12],"dependency":[13],"brought":[14],"by":[15],"autoregressive":[16],"decoding.":[17],"Recently,":[18],"speculative":[19,48,77,86],"has":[21],"been":[22],"proposed":[23],"to":[24,33,44,67],"alleviate":[25],"this":[26],"problem,":[27],"which":[28],"introduces":[29],"small":[30],"models":[32,74],"generate":[34],"draft":[35],"tokens":[36],"and":[37],"adopts":[38],"original":[40],"model":[43],"conduct":[45],"verification.":[46],"Although":[47],"can":[50],"enhance":[51],"efficiency":[53],"decoding":[56],"procedure,":[57],"we":[58],"find":[59],"that":[60],"it":[61],"presents":[62],"variable":[63],"resource":[64],"demands":[65],"due":[66],"distinct":[69],"computation":[70],"patterns":[71],"used":[75],"in":[76,90],"inference.":[78],"This":[79],"variability":[80],"impedes":[81],"full":[83],"realization":[84],"inference's":[87],"acceleration":[88],"potential":[89],"current":[91],"systems.":[92]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":15}],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}
