{"id":"https://openalex.org/W7165143105","doi":"https://doi.org/10.1145/3787109.3815208","title":"HoloLUT: An Efficient LUT-Based Engine via Holistic Data Processing for Low-bit LLM Inference","display_name":"HoloLUT: An Efficient LUT-Based Engine via Holistic Data Processing for Low-bit LLM Inference","publication_year":2026,"publication_date":"2026-06-18","ids":{"openalex":"https://openalex.org/W7165143105","doi":"https://doi.org/10.1145/3787109.3815208"},"language":null,"primary_location":{"id":"doi:10.1145/3787109.3815208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815208","pdf_url":null,"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 Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3787109.3815208","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015500761","display_name":"Hui Wang","orcid":"https://orcid.org/0009-0002-8690-3608"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Wang","raw_affiliation_strings":["Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0002-8690-3608","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107945960","display_name":"W. Ma","orcid":"https://orcid.org/0009-0008-2365-5284"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weize Ma","raw_affiliation_strings":["Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0008-2365-5284","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059107361","display_name":"Jinming Lu","orcid":"https://orcid.org/0000-0002-7134-6514"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinming Lu","raw_affiliation_strings":["Nanjing University, Suzhou, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0007-0192-3703","affiliations":[{"raw_affiliation_string":"Nanjing University, Suzhou, Jiangsu, China","institution_ids":["https://openalex.org/I3923682","https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100583800","display_name":"Jun Lin","orcid":"https://orcid.org/0009-0005-3505-4847"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lin","raw_affiliation_strings":["Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0005-3505-4847","affiliations":[{"raw_affiliation_string":"Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94512059,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"109","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.24379999935626984,"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":0.24379999935626984,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.17069999873638153,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.11620000004768372,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6373000144958496},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.5748999714851379},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5698999762535095},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5611000061035156},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5055999755859375},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4821000099182129},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.4226999878883362},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.39739999175071716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343000173568726},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6373000144958496},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.5748999714851379},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5698999762535095},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5611000061035156},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4821000099182129},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4226999878883362},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.42149999737739563},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.39739999175071716},{"id":"https://openalex.org/C67820243","wikidata":"https://www.wikidata.org/wiki/Q179164","display_name":"Unitary state","level":2,"score":0.3968000113964081},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.38760000467300415},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3831000030040741},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.3422999978065491},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.32499998807907104},{"id":"https://openalex.org/C46362747","wikidata":"https://www.wikidata.org/wiki/Q173431","display_name":"CMOS","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29910001158714294},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C87868495","wikidata":"https://www.wikidata.org/wiki/Q750843","display_name":"Information processing","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25380000472068787},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3787109.3815208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815208","pdf_url":null,"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 Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3787109.3815208","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3787109.3815208","pdf_url":null,"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 Great Lakes Symposium on VLSI 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.864126980304718,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2725159389","https://openalex.org/W2895531329","https://openalex.org/W3006586535","https://openalex.org/W4308083739","https://openalex.org/W4393407021","https://openalex.org/W4402670692","https://openalex.org/W4409248488","https://openalex.org/W4411486388","https://openalex.org/W4412945475"],"related_works":[],"abstract_inverted_index":{"Weight-only":[0],"quantization":[1],"enhances":[2],"the":[3,24,37,77],"efficiency":[4],"of":[5,26],"large":[6],"language":[7],"models":[8],"(LLMs)":[9],"by":[10],"storing":[11],"weights":[12,85],"in":[13,119,131,150],"low-bit":[14,42,148],"integers":[15],"while":[16],"retaining":[17],"activations":[18],"at":[19],"a":[20,50,71,95,101],"higher":[21],"precision.":[22],"However,":[23],"absence":[25],"efficient":[27],"mixed-precision":[28],"computation":[29],"support":[30],"on":[31],"general-purpose":[32],"hardware":[33,116],"tends":[34],"to":[35,107,138],"hinder":[36],"potential":[38,145],"computational":[39],"gains":[40],"from":[41],"LLMs.":[43],"While":[44],"lookup":[45],"table":[46],"(LUT)-based":[47],"methods":[48],"offer":[49],"promising":[51],"alternative,":[52],"conventional":[53],"bit-serial":[54],"architectures":[55],"introduce":[56],"shift-and-accumulate":[57,92],"bottlenecks,":[58],"limiting":[59],"throughput":[60],"and":[61,109,127,133],"energy":[62],"efficiency.":[63],"To":[64],"overcome":[65],"these":[66],"limitations,":[67],"we":[68],"propose":[69],"HoloLUT,":[70],"novel":[72],"LUT-based":[73,140],"engine":[74],"that":[75],"incorporates":[76],"Unitary":[78],"Data":[79],"Operation":[80],"paradigm.":[81],"This":[82],"paradigm":[83],"processes":[84],"holistically":[86],"rather":[87],"than":[88],"bit-serially,":[89],"thereby":[90],"eliminating":[91],"operations.":[93],"Furthermore,":[94],"precision-adaptive":[96],"mapping":[97],"strategy":[98],"combined":[99],"with":[100,114],"unified":[102],"LUT":[103],"generator":[104],"allows":[105],"HoloLUT":[106,123],"flexibly":[108],"efficiently":[110],"handle":[111],"various":[112],"precisions":[113],"negligible":[115],"overhead.":[117],"Implemented":[118],"28nm":[120],"CMOS":[121],"technology,":[122],"achieves":[124],"1.86":[125],"\u00d7":[126,129],"2.18":[128],"improvements":[130],"area":[132],"power":[134],"efficiency,":[135],"respectively,":[136],"compared":[137],"state-of-the-art":[139],"accelerators,":[141],"demonstrating":[142],"its":[143],"strong":[144],"for":[146],"deploying":[147],"LLMs":[149],"resource-constrained":[151],"scenarios.":[152]},"counts_by_year":[],"updated_date":"2026-06-19T15:51:49.773706","created_date":"2026-06-19T00:00:00"}