{"id":"https://openalex.org/W7163541648","doi":"https://doi.org/10.23919/date69613.2026.11539383","title":"Endor: Exploit Nearly-Decode-Only Opportunities of LLM Reasoning on Near-Memory Architecture","display_name":"Endor: Exploit Nearly-Decode-Only Opportunities of LLM Reasoning on Near-Memory Architecture","publication_year":2026,"publication_date":"2026-04-20","ids":{"openalex":"https://openalex.org/W7163541648","doi":"https://doi.org/10.23919/date69613.2026.11539383"},"language":null,"primary_location":{"id":"doi:10.23919/date69613.2026.11539383","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date69613.2026.11539383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Design, Automation &amp;amp; Test in Europe Conference (DATE)","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/A5058464361","display_name":"J S Liu","orcid":null},"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":"Jun Liu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137844992","display_name":"Tianlang Zhao","orcid":null},"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":"Tianlang Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736545","display_name":"Shiyi Liu","orcid":"https://orcid.org/0000-0002-2157-8667"},"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":"Shiyi Liu","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124980642","display_name":"Jiancai Ye","orcid":null},"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":"Jiancai Ye","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137917807","display_name":"Lin Li","orcid":null},"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":"Lin Li","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052456451","display_name":"Z-F Yu","orcid":null},"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":"Zhen Yu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083382573","display_name":"Li Ding","orcid":"https://orcid.org/0000-0001-8169-8225"},"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":"Li Ding","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137842138","display_name":"Hao Zhou","orcid":null},"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":"Hao Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137875882","display_name":"Zhenhua Zhu","orcid":null},"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":"Zhenhua Zhu","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086217226","display_name":"Xuefei Ning","orcid":"https://orcid.org/0000-0003-2209-8312"},"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":"Xuefei Ning","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385336","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-2093-1788"},"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":"Yuan Xie","raw_affiliation_strings":["Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137843696","display_name":"Yu Wang","orcid":null},"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":"Yu Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072245580","display_name":"Guohao Dai","orcid":"https://orcid.org/0000-0001-7346-2685"},"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":"Guohao Dai","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":13,"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":0.9148758,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11424","display_name":"Security and Verification in Computing","score":0.14650000631809235,"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"}},"topics":[{"id":"https://openalex.org/T11424","display_name":"Security and Verification in Computing","score":0.14650000631809235,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.13490000367164612,"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/T10142","display_name":"Formal Methods in Verification","score":0.12710000574588776,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/exploit","display_name":"Exploit","score":0.7732999920845032},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4440000057220459},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3160000145435333},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.295199990272522},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2883000075817108},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.27649998664855957}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7732999920845032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6593999862670898},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3483999967575073},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2662000060081482},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/date69613.2026.11539383","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date69613.2026.11539383","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 Design, Automation &amp;amp; Test in Europe Conference (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327803","display_name":"Shanghai Rising-Star Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2034861439","https://openalex.org/W2962800603","https://openalex.org/W3042598257","https://openalex.org/W3130554079","https://openalex.org/W3158275024","https://openalex.org/W3207399097","https://openalex.org/W4281685651","https://openalex.org/W4281731825","https://openalex.org/W4308083513","https://openalex.org/W4360831749","https://openalex.org/W4386763970","https://openalex.org/W4387321091","https://openalex.org/W4388757726","https://openalex.org/W4393578753","https://openalex.org/W4401211878","https://openalex.org/W4407425079","https://openalex.org/W4409248462","https://openalex.org/W4409248659","https://openalex.org/W4409248815","https://openalex.org/W4411485931","https://openalex.org/W4415797351","https://openalex.org/W7133224126"],"related_works":[],"abstract_inverted_index":{"Reasoning":[0],"with":[1],"Large":[2],"Language":[3],"Models":[4],"(LLMs)":[5],"has":[6],"become":[7],"a":[8,133,174,186,201,205,211],"pivotal":[9],"research":[10],"topic":[11],"because":[12],"their":[13],"logical":[14],"abilities":[15],"significantly":[16],"surpass":[17],"those":[18],"of":[19,28,44,52,57,124,140,150,164,248],"standard":[20],"LLMs.":[21],"LLM":[22,45,141,151,260],"reasoning":[23,46,142,152],"typically":[24],"forms":[25],"multiple":[26,263],"chains":[27],"thought,":[29],"action-by-action,":[30],"and":[31,66,185,210,220,250,258,265],"selects":[32],"the":[33,37,41,60,72,112,138,147,155,159,165,169,195,239,254],"best":[34],"one":[35],"as":[36],"final":[38],"answer.":[39],"However,":[40],"inference":[42,139],"overhead":[43],"is":[47],"more":[48],"than":[49,55],"an":[50,179,244],"order":[51],"magnitude":[53],"higher":[54],"that":[56,146,231],"LLM.":[58],"Despite":[59],"emerging":[61],"shift":[62],"towards":[63],"memory-optimized":[64],"algorithms":[65,78,234],"near-memory":[67,106,202],"hardware,":[68],"we":[69,130,172,198],"still":[70],"face":[71],"following":[73],"challenges:":[74],"(1)":[75],"Existing":[76],"memory-centric":[77],"(e.g.,":[79,105],"KV":[80],"cache":[81,182,207],"technique)":[82],"have":[83],"low":[84,122],"computational":[85],"utilization":[86,123],"(<":[87],"4%":[88],"on":[89,262],"NVIDIA":[90,255],"A100":[91,256],"GPU)":[92],"due":[93,115],"to":[94,109,116,121,136,158,190,223,253],"intensive":[95],"memory":[96,125,225],"access":[97],"for":[98],"inter-action":[99,181],"data.":[100],"(2)":[101],"Emerging":[102],"hardware":[103,196,236],"architectures":[104],"processing)":[107],"fail":[108],"fully":[110,216],"utilize":[111],"inherent":[113],"parallelism":[114,222],"dependencies":[117],"among":[118],"models,":[119],"leading":[120],"bandwidth.To":[126],"tackle":[127],"these":[128],"challenges,":[129],"propose":[131,173,199],"Endor,":[132],"hardware-algorithm":[134],"co-design":[135],"accelerate":[137],"efficiently.":[143],"We":[144],"identify":[145],"auto-regressive":[148],"decoding":[149],"changes":[153],"from":[154],"token":[156],"level":[157,161],"action":[160],"in":[162],"terms":[163],"computing":[166],"paradigm.":[167],"At":[168,194],"algorithm":[170],"level,":[171,197],"\"nearly-decode-only\"":[175],"method":[176,184],"which":[177],"encompasses":[178],"efficient":[180],"reuse":[183],"prediction-based":[187],"pipeline":[188],"optimization":[189],"reduce":[191],"computation":[192],"overhead.":[193],"Endor-NMP,":[200],"accelerator":[203],"featuring":[204],"score-aware":[206],"management":[208],"architecture":[209],"heterogeneous":[212],"mapping":[213],"dataflow.":[214],"Endor":[215,242],"exploits":[217],"both":[218],"interaction":[219],"intra-action":[221],"improve":[224],"bandwidth":[226],"utilization.":[227],"Experimental":[228],"results":[229],"demonstrate":[230],"neither":[232],"existing":[233],"nor":[235],"can":[237],"achieve":[238],"expected":[240],"acceleration.":[241],"achieves":[243],"end-to-end":[245],"average":[246],"speedup":[247],"2.97\u00d7":[249],"2.52\u00d7":[251],"compared":[252],"GPU":[257],"advanced":[259],"accelerators":[261],"models":[264],"datasets.":[266]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-06-05T00:00:00"}
