{"id":"https://openalex.org/W7133301734","doi":"https://doi.org/10.1109/isscc49663.2026.11409211","title":"31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding","display_name":"31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding","publication_year":2026,"publication_date":"2026-02-15","ids":{"openalex":"https://openalex.org/W7133301734","doi":"https://doi.org/10.1109/isscc49663.2026.11409211"},"language":"en","primary_location":{"id":"doi:10.1109/isscc49663.2026.11409211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isscc49663.2026.11409211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Solid-State Circuits Conference (ISSCC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2605.09375","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043072381","display_name":"Pingcheng Dong","orcid":"https://orcid.org/0000-0003-3975-286X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pingcheng Dong","raw_affiliation_strings":["Hong Kong University of Science and Technology,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056333723","display_name":"Yonghao Tan","orcid":"https://orcid.org/0000-0001-5372-5863"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yonghao Tan","raw_affiliation_strings":["Hong Kong University of Science and Technology,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086868241","display_name":"Xuejiao Liu","orcid":"https://orcid.org/0009-0007-6788-1593"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuejiao Liu","raw_affiliation_strings":["AI Chip Center for Emerging Smart System,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Chip Center for Emerging Smart System,Hong Kong,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127990977","display_name":"Peng Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Luo","raw_affiliation_strings":["AI Chip Center for Emerging Smart System,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Chip Center for Emerging Smart System,Hong Kong,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128010266","display_name":"Yu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["AI Chip Center for Emerging Smart System,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Chip Center for Emerging Smart System,Hong Kong,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037171233","display_name":"Di Pang","orcid":"https://orcid.org/0000-0002-0398-0791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Pang","raw_affiliation_strings":["AI Chip Center for Emerging Smart System,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Chip Center for Emerging Smart System,Hong Kong,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675945","display_name":"Songchen Ma","orcid":"https://orcid.org/0000-0002-7913-046X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Songchen Ma","raw_affiliation_strings":["Hong Kong University of Science and Technology,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002384034","display_name":"Xijie Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xijie Huang","raw_affiliation_strings":["Hong Kong University of Science and Technology,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016722419","display_name":"Shih-Yang Liu","orcid":"https://orcid.org/0000-0003-1997-0843"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shih-Yang Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040621049","display_name":"D. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dong Zhang","raw_affiliation_strings":["Hong Kong University of Science and Technology,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047573789","display_name":"Zhichao Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I39774598","display_name":"Hefei University","ror":"https://ror.org/01f5rdf64","country_code":"CN","type":"education","lineage":["https://openalex.org/I39774598"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichao Lu","raw_affiliation_strings":["Hefei Reliance Memory,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hefei Reliance Memory,Hefei,China","institution_ids":["https://openalex.org/I39774598"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052554057","display_name":"Luhong Liang","orcid":"https://orcid.org/0009-0001-4190-006X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luhong Liang","raw_affiliation_strings":["AI Chip Center for Emerging Smart System,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Chip Center for Emerging Smart System,Hong Kong,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102279835","display_name":"Chi-Ying Tsui","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chi-Ying Tsui","raw_affiliation_strings":["Hong Kong University of Science and Technology,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038947607","display_name":"Fengbin Tu","orcid":"https://orcid.org/0000-0003-2228-8829"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fengbin Tu","raw_affiliation_strings":["Hong Kong University of Science and Technology,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127979588","display_name":"Liang Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Zhao","raw_affiliation_strings":["Zhejiang University,Hangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124931301","display_name":"Kwang-Ting Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kwang-Ting Cheng","raw_affiliation_strings":["Hong Kong University of Science and Technology,Hong Kong,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology,Hong Kong,China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"532","last_page":"534"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.1988999992609024,"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":0.1988999992609024,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.06549999862909317,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.06040000170469284,"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/speedup","display_name":"Speedup","score":0.7427999973297119},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5338000059127808},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.49549999833106995},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.4927000105381012},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.44200000166893005},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.3424000144004822},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3346000015735626}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7427999973297119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6383000016212463},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5338000059127808},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.49549999833106995},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.412200003862381},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.40149998664855957},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C74050887","wikidata":"https://www.wikidata.org/wiki/Q848368","display_name":"Rotation (mathematics)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2957000136375427},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2653000056743622}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/isscc49663.2026.11409211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isscc49663.2026.11409211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE International Solid-State Circuits Conference (ISSCC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.09375","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.09375","pdf_url":"https://arxiv.org/pdf/2605.09375","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-170908","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-170908","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2605.09375","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.09375","pdf_url":"https://arxiv.org/pdf/2605.09375","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W4246587277","https://openalex.org/W4404781137","https://openalex.org/W4404782943","https://openalex.org/W4408183246","https://openalex.org/W4412963705","https://openalex.org/W4412966175"],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"a":[3,17,25],"55nm":[4],"speculative":[5,43,64],"decoding-based":[6],"LLM":[7],"accelerator":[8],"with":[9,30,46],"bumpingbased":[10],"face-to-face":[11],"ReRAM-on-logic":[12],"stacking":[13],"technology.":[14],"It":[15],"features":[16],"local":[18],"rotation":[19],"unit":[20],"for":[21,49],"outlier-free":[22],"low-bit":[23],"quantization,":[24],"stacking-aware":[26],"PNM":[27],"architecture":[28],"co-designed":[29],"blockwise":[31],"vector":[32],"quantization":[33],"to":[34],"reduce":[35],"weight":[36],"EMA":[37],"overheads,":[38],"and":[39,52,59],"an":[40],"adaptive":[41],"parallel":[42],"decoding":[44],"scheme":[45],"out-of-order":[47],"scheduler":[48],"high":[50],"resource":[51],"bandwidth":[53],"utilization.":[54],"Our":[55],"chip":[56],"achieves":[57],"14.08-to-135.69token/s":[58],"4.46-to-7.17\u00d7":[60],"speedup":[61],"over":[62],"vanilla":[63],"decoding.":[65]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-04T00:00:00"}
