{"id":"https://openalex.org/W7092191477","doi":"https://doi.org/10.1145/3725843.3756037","title":"MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness","display_name":"MCBP: A Memory-Compute Efficient LLM Inference Accelerator Leveraging Bit-Slice-enabled Sparsity and Repetitiveness","publication_year":2025,"publication_date":"2025-10-17","ids":{"openalex":"https://openalex.org/W7092191477","doi":"https://doi.org/10.1145/3725843.3756037"},"language":null,"primary_location":{"id":"doi:10.1145/3725843.3756037","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756037","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756037","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 58th IEEE/ACM International Symposium on Microarchitecture","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/10.1145/3725843.3756037","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huizheng Wang","orcid":"https://orcid.org/0000-0002-9763-8208"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huizheng Wang","raw_affiliation_strings":["School of Integrated Circuits, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9763-8208","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zichuan Wang","orcid":"https://orcid.org/0009-0001-7114-0647"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zichuan Wang","raw_affiliation_strings":["School of Integrated Circuits, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-7114-0647","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiheng Yue","orcid":"https://orcid.org/0000-0003-4084-3478"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Yue","raw_affiliation_strings":["School of Integrated Circuits, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4084-3478","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yousheng Long","orcid":"https://orcid.org/0009-0008-0326-2029"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yousheng Long","raw_affiliation_strings":["School of Integrated Circuits, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-0326-2029","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Taiquan Wei","orcid":"https://orcid.org/0009-0005-3501-3148"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Taiquan Wei","raw_affiliation_strings":["School of Integrated Circuits, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-3501-3148","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jianxun Yang","orcid":"https://orcid.org/0000-0001-9905-0961"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxun Yang","raw_affiliation_strings":["School of Integrated Circuits, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9905-0961","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Wang","orcid":"https://orcid.org/0000-0002-8293-8881"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Wang","raw_affiliation_strings":["School of Integrated Circuits, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8293-8881","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chao Li","orcid":"https://orcid.org/0000-0001-6218-4659"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Li","raw_affiliation_strings":["Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-6218-4659","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shaojun Wei","orcid":"https://orcid.org/0000-0001-5117-7920"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Wei","raw_affiliation_strings":["School of Integrated Circuits, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5117-7920","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Hu","orcid":"https://orcid.org/0000-0001-6942-4395"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Hu","raw_affiliation_strings":["School of Integrated Circuits, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6942-4395","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":null,"display_name":"Shouyi Yin","orcid":"https://orcid.org/0000-0002-8438-8588"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shouyi Yin","raw_affiliation_strings":["School of Integrated Circuits, Tsinghua University, Beijing, China and Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8438-8588","affiliations":[{"raw_affiliation_string":"School of Integrated Circuits, Tsinghua University, Beijing, China and Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.1536,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.99076621,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1592","last_page":"1608"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.26440000534057617,"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":0.26440000534057617,"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":0.23579999804496765,"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/T11424","display_name":"Security and Verification in Computing","score":0.047600001096725464,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.41589999198913574},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2994000017642975},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2919999957084656},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.26510000228881836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6204000115394592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2994000017642975},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28610000014305115},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26080000400543213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2459000051021576},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2401999980211258}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3725843.3756037","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756037","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756037","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 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3725843.3756037","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3725843.3756037","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3725843.3756037","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 58th IEEE/ACM International Symposium on Microarchitecture","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1187591493","display_name":null,"funder_award_id":"2022ZD0115200","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G1750178727","display_name":"Collaborative Research: PPoSS: LARGE: Research into the Use and iNtegration of Data Movement Accelerators (RUN-DMX)","funder_award_id":"2316177","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G338081660","display_name":null,"funder_award_id":"62125403","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7234679820","display_name":null,"funder_award_id":"92164301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329777","display_name":"Beijing National Research Center For Information Science And Technology","ror":null},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7092191477.pdf","grobid_xml":"https://content.openalex.org/works/W7092191477.grobid-xml"},"referenced_works_count":80,"referenced_works":["https://openalex.org/W2034861439","https://openalex.org/W2072730350","https://openalex.org/W2089534194","https://openalex.org/W2115330819","https://openalex.org/W2260498192","https://openalex.org/W2285660444","https://openalex.org/W2431931973","https://openalex.org/W2541839172","https://openalex.org/W2565960208","https://openalex.org/W2593564159","https://openalex.org/W2761132374","https://openalex.org/W2767737961","https://openalex.org/W2794141774","https://openalex.org/W2913573286","https://openalex.org/W2923014074","https://openalex.org/W2931118404","https://openalex.org/W2949870694","https://openalex.org/W2963122961","https://openalex.org/W2963367920","https://openalex.org/W2963594949","https://openalex.org/W2979439447","https://openalex.org/W2979826702","https://openalex.org/W3016542674","https://openalex.org/W3047848469","https://openalex.org/W3102587717","https://openalex.org/W3105802176","https://openalex.org/W3157114665","https://openalex.org/W3159727696","https://openalex.org/W3159782774","https://openalex.org/W3177265267","https://openalex.org/W3185702163","https://openalex.org/W3187481008","https://openalex.org/W3189877953","https://openalex.org/W3194676777","https://openalex.org/W3205192296","https://openalex.org/W3206290655","https://openalex.org/W3206453033","https://openalex.org/W3207265322","https://openalex.org/W3207622241","https://openalex.org/W3210059290","https://openalex.org/W4214686755","https://openalex.org/W4224267386","https://openalex.org/W4236868170","https://openalex.org/W4240168186","https://openalex.org/W4247198796","https://openalex.org/W4280557024","https://openalex.org/W4281708367","https://openalex.org/W4281800613","https://openalex.org/W4285236966","https://openalex.org/W4291653336","https://openalex.org/W4293025165","https://openalex.org/W4308083513","https://openalex.org/W4308083526","https://openalex.org/W4308083827","https://openalex.org/W4308083928","https://openalex.org/W4312569226","https://openalex.org/W4313467238","https://openalex.org/W4360606782","https://openalex.org/W4360831795","https://openalex.org/W4360831844","https://openalex.org/W4360831992","https://openalex.org/W4375928954","https://openalex.org/W4377864779","https://openalex.org/W4380875572","https://openalex.org/W4380881077","https://openalex.org/W4386764135","https://openalex.org/W4386765251","https://openalex.org/W4391136507","https://openalex.org/W4393406875","https://openalex.org/W4393406920","https://openalex.org/W4394745423","https://openalex.org/W4396833177","https://openalex.org/W4399487278","https://openalex.org/W4401211704","https://openalex.org/W4401211806","https://openalex.org/W4401211845","https://openalex.org/W4404134025","https://openalex.org/W4404954358","https://openalex.org/W4404955790","https://openalex.org/W4408183246"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"face":[4],"significant":[5],"inference":[6],"latency":[7],"due":[8],"to":[9,37,51,74],"inefficiencies":[10],"in":[11,21],"GEMM":[12,90],"operations,":[13],"weight":[14],"access,":[15,19],"and":[16,54,72],"KV":[17],"cache":[18],"especially":[20],"real-time":[22],"scenarios.This":[23],"highlights":[24],"the":[25],"need":[26],"for":[27],"a":[28,60],"versatile":[29],"compute-memory":[30,62],"efficient":[31,63],"accelerator.Unfortunately,":[32],"existing":[33],"Transformer":[34],"accelerators":[35],"struggle":[36],"address":[38],"both":[39],"aspects":[40],"simultaneously,":[41],"as":[42],"they":[43],"focus":[44],"on":[45],"value-level":[46],"processing,":[47],"missing":[48],"fine-grained":[49],"opportunities":[50],"optimize":[52],"computation":[53,84],"memory":[55],"collaboratively.This":[56],"paper":[57],"introduces":[58],"MCBP,":[59],"bitgrained":[61],"algorithm-hardware":[64],"co-design":[65],"that":[66],"leverages":[67],"bit-slice":[68],"(BS)":[69],"enabled":[70],"repetitiveness":[71],"sparsity":[73],"accelerate":[75],"LLM":[76],"inference.MCBP":[77],"features":[78],"three":[79],"key":[80],"innovations:":[81],"1)":[82],"BS-repetitiveness-enabled":[83],"reduction":[85],"(BRCR),":[86],"which":[87],"eliminates":[88],"redundant":[89],"computations":[91],"via":[92],"leveraging":[93],"redundancy":[94],"hidden":[95],"among":[96],"BS":[97],"vectors;":[98],"2)":[99],"BS-sparsity-enabled":[100],"two-state":[101]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2025-10-17T00:00:00"}