{"id":"https://openalex.org/W4394998968","doi":"https://doi.org/10.1145/3620665.3640422","title":"AttAcc! Unleashing the Power of PIM for Batched Transformer-based Generative Model Inference","display_name":"AttAcc! Unleashing the Power of PIM for Batched Transformer-based Generative Model Inference","publication_year":2024,"publication_date":"2024-04-22","ids":{"openalex":"https://openalex.org/W4394998968","doi":"https://doi.org/10.1145/3620665.3640422"},"language":"en","primary_location":{"id":"doi:10.1145/3620665.3640422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620665.3640422","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 2","raw_type":"proceedings-article"},"type":"article","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/A5100618952","display_name":"Jaehyun Park","orcid":"https://orcid.org/0000-0001-5623-6985"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jaehyun Park","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032839104","display_name":"Jaewan Choi","orcid":"https://orcid.org/0000-0003-2447-4369"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewan Choi","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002219153","display_name":"Kwanhee Kyung","orcid":"https://orcid.org/0000-0003-4243-2111"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kwanhee Kyung","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085297039","display_name":"Michael Jaemin Kim","orcid":"https://orcid.org/0000-0001-9987-9809"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Michael Jaemin Kim","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089034192","display_name":"Yongsuk Kwon","orcid":"https://orcid.org/0000-0002-1956-4629"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongsuk Kwon","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037648751","display_name":"Nam Sung Kim","orcid":"https://orcid.org/0000-0002-0442-5634"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam Sung Kim","raw_affiliation_strings":["University of Illinois Urbana-Champaign, Urbana-Champaign, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana-Champaign, United States of America","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078262826","display_name":"Jung Ho Ahn","orcid":"https://orcid.org/0000-0003-1733-1394"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung Ho Ahn","raw_affiliation_strings":["Seoul National University, Seoul, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100618952"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":19.844,"has_fulltext":false,"cited_by_count":81,"citation_normalized_percentile":{"value":0.99682582,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"103","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.977400004863739,"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":0.977400004863739,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9764999747276306,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9718999862670898,"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":0.8227327466011047},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.6721906661987305},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6572796106338501},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5824319124221802},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5166454911231995},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4819078743457794},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.43623924255371094},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4267216622829437},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4238632023334503},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40347206592559814},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.34187984466552734},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.327784925699234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20953869819641113},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1204039454460144}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8227327466011047},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6721906661987305},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6572796106338501},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5824319124221802},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5166454911231995},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4819078743457794},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.43623924255371094},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4267216622829437},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4238632023334503},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40347206592559814},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34187984466552734},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.327784925699234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20953869819641113},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1204039454460144},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3620665.3640422","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3620665.3640422","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 2","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8794816260","display_name":null,"funder_award_id":"PRISM","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"}],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W1984222112","https://openalex.org/W2034861439","https://openalex.org/W2041811089","https://openalex.org/W2045431893","https://openalex.org/W2129991978","https://openalex.org/W2170901118","https://openalex.org/W2332254524","https://openalex.org/W2346205343","https://openalex.org/W2584298940","https://openalex.org/W2605347906","https://openalex.org/W2622148586","https://openalex.org/W2752340955","https://openalex.org/W2761132374","https://openalex.org/W2765234579","https://openalex.org/W2766489088","https://openalex.org/W2789777840","https://openalex.org/W2896090304","https://openalex.org/W2898984660","https://openalex.org/W2949989598","https://openalex.org/W2976137532","https://openalex.org/W2979719709","https://openalex.org/W2979874885","https://openalex.org/W2980688670","https://openalex.org/W2982008795","https://openalex.org/W3014934202","https://openalex.org/W3017024317","https://openalex.org/W3042598257","https://openalex.org/W3083970030","https://openalex.org/W3100710793","https://openalex.org/W3100985894","https://openalex.org/W3155004489","https://openalex.org/W3157531038","https://openalex.org/W3159727696","https://openalex.org/W3174762441","https://openalex.org/W3189166979","https://openalex.org/W3189877953","https://openalex.org/W3190062760","https://openalex.org/W3206328251","https://openalex.org/W3206453033","https://openalex.org/W3207399097","https://openalex.org/W4220702013","https://openalex.org/W4221001402","https://openalex.org/W4239722617","https://openalex.org/W4249322926","https://openalex.org/W4280496502","https://openalex.org/W4285113882","https://openalex.org/W4292261931","https://openalex.org/W4292779060","https://openalex.org/W4308083513","https://openalex.org/W4313546932","https://openalex.org/W4366341968","https://openalex.org/W4377865306","https://openalex.org/W4380874786","https://openalex.org/W4380881077","https://openalex.org/W4385245566","https://openalex.org/W4385834084"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4317547544","https://openalex.org/W4313395829","https://openalex.org/W2077105843","https://openalex.org/W2770465587","https://openalex.org/W2086716781","https://openalex.org/W2022510519"],"abstract_inverted_index":{"The":[0],"Transformer-based":[1],"generative":[2,15],"model":[3],"(TbGM),":[4],"comprising":[5],"summarization":[6],"(Sum)":[7],"and":[8,31,42,111,117,132,163,175],"generation":[9],"(Gen)":[10],"stages,":[11,37],"has":[12],"demonstrated":[13],"unprecedented":[14],"performance":[16,162],"across":[17],"a":[18,85,106,168],"wide":[19],"range":[20],"of":[21,29,39,92,101,126,137,166],"applications.":[22],"However,":[23],"it":[24],"also":[25],"demands":[26],"immense":[27],"amounts":[28],"compute":[30,135],"memory":[32,124,159],"resources.":[33],"Especially,":[34],"the":[35,40,47,55,67,93,98,122,129,133,138,142,153,157],"Gen":[36],"consisting":[38],"attention":[41,68,94,130],"fully-connected":[43],"(FC)":[44],"layers,":[45],"dominate":[46],"overall":[48],"execution":[49,91],"time.":[50],"Meanwhile,":[51],"we":[52,81,104,146],"reveal":[53],"that":[54,113,148],"conventional":[56,139,154],"system":[57,109,140,151,155],"with":[58,71,156],"GPUs":[59],"used":[60],"for":[61,89,97,128,141],"TbGM":[62,102,170],"inference":[63],"cannot":[64],"efficiently":[65],"execute":[66],"layer,":[69],"even":[70],"batching,":[72],"due":[73],"to":[74,173],"various":[75],"constraints.":[76],"To":[77],"address":[78],"this":[79],"inefficiency,":[80],"first":[82],"propose":[83,105],"AttAcc,":[84],"processing-in-memory":[86],"(PIM)":[87],"architecture":[88,110],"efficient":[90],"layer.":[95,144],"Subsequently,":[96],"end-to-end":[99],"acceleration":[100],"inference,":[103],"novel":[107],"heterogeneous":[108],"optimizations":[112],"strategically":[114],"use":[115],"xPU":[116],"PIM":[118],"together.":[119],"It":[120],"leverages":[121],"high":[123],"bandwidth":[125],"AttAcc":[127],"layer":[131],"powerful":[134],"capability":[136],"FC":[143],"Lastly,":[145],"demonstrate":[147],"our":[149],"GPU-PIM":[150],"outperforms":[152],"same":[158],"capacity,":[160],"improving":[161],"energy":[164],"efficiency":[165],"running":[167],"175B":[169],"by":[171],"up":[172],"2.81\u00d7":[174],"2.67\u00d7,":[176],"respectively.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":16},{"year":2025,"cited_by_count":64},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}