{"id":"https://openalex.org/W7106164093","doi":"https://doi.org/10.1109/iccad66269.2025.11240722","title":"LEAP: LLM Inference on Scalable PIM-NoC Architecture with Balanced Dataflow and Fine-Grained Parallelism","display_name":"LEAP: LLM Inference on Scalable PIM-NoC Architecture with Balanced Dataflow and Fine-Grained Parallelism","publication_year":2025,"publication_date":"2025-10-26","ids":{"openalex":"https://openalex.org/W7106164093","doi":"https://doi.org/10.1109/iccad66269.2025.11240722"},"language":null,"primary_location":{"id":"doi:10.1109/iccad66269.2025.11240722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","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":null,"display_name":"Yimin Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yimin Wang","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yue Jiet Chong","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yue Jiet Chong","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":null,"display_name":"Xuanyao Fong","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xuanyao Fong","raw_affiliation_strings":["National University of Singapore,Department of Electrical and Computer Engineering,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":3.5291,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.93765094,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.1589999943971634,"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":0.1589999943971634,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.1518000066280365,"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/T14347","display_name":"Big Data and Digital Economy","score":0.10369999706745148,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/dataflow","display_name":"Dataflow","score":0.8468000292778015},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.6080999970436096},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5830000042915344},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5564000010490417},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.5367000102996826},{"id":"https://openalex.org/keywords/von-neumann-architecture","display_name":"Von Neumann architecture","score":0.5315999984741211},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4650000035762787},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.39559999108314514},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.38769999146461487}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8468000292778015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8309000134468079},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.6080999970436096},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5830000042915344},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5638999938964844},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5564000010490417},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.5367000102996826},{"id":"https://openalex.org/C80469333","wikidata":"https://www.wikidata.org/wiki/Q189088","display_name":"Von Neumann architecture","level":2,"score":0.5315999984741211},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4650000035762787},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46219998598098755},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.40119999647140503},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.39559999108314514},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C176727019","wikidata":"https://www.wikidata.org/wiki/Q1172415","display_name":"Dataflow architecture","level":3,"score":0.3797999918460846},{"id":"https://openalex.org/C2776221188","wikidata":"https://www.wikidata.org/wiki/Q21072556","display_name":"Design space exploration","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37450000643730164},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.35249999165534973},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.3488999903202057},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.3384000062942505},{"id":"https://openalex.org/C489000","wikidata":"https://www.wikidata.org/wiki/Q747385","display_name":"Data flow diagram","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C200106649","wikidata":"https://www.wikidata.org/wiki/Q223683","display_name":"Transpose","level":3,"score":0.2750000059604645},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2776928060","wikidata":"https://www.wikidata.org/wiki/Q1753563","display_name":"SystemC","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C88468194","wikidata":"https://www.wikidata.org/wiki/Q1172416","display_name":"Data-flow analysis","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccad66269.2025.11240722","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccad66269.2025.11240722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/ACM International Conference On Computer Aided Design (ICCAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8804330825805664,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2105102111","https://openalex.org/W2120000030","https://openalex.org/W2289252105","https://openalex.org/W2782046614","https://openalex.org/W2945146780","https://openalex.org/W2980200167","https://openalex.org/W2997869757","https://openalex.org/W3013080934","https://openalex.org/W3112740243","https://openalex.org/W3158617745","https://openalex.org/W4288083528","https://openalex.org/W4312847929","https://openalex.org/W4386763463","https://openalex.org/W4388052862","https://openalex.org/W4388626384","https://openalex.org/W4389166813","https://openalex.org/W4390241252","https://openalex.org/W4392240059","https://openalex.org/W4400579220","https://openalex.org/W4401880123"],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"model":[2],"(LLM)":[3],"inference":[4],"has":[5],"been":[6],"a":[7,35],"prevalent":[8],"demand":[9],"in":[10,22,54,95],"daily":[11],"life":[12],"and":[13,19,30,45,73,85,97,107,113],"industries.":[14],"The":[15,51,99],"large":[16],"tensor":[17],"sizes":[18],"computing":[20],"complexities":[21],"LLMs":[23,55],"have":[24],"brought":[25],"challenges":[26],"to":[27,58,67,120],"memory,":[28],"computing,":[29],"databus.":[31],"This":[32],"paper":[33],"proposes":[34],"computation/memory/communication":[36],"co-designed":[37],"non-von":[38],"Neumann":[39],"accelerator":[40],"by":[41,77],"aggregating":[42],"processing-in-memory":[43],"(PIM)":[44],"computational":[46],"network-on-chip":[47],"(NoC),":[48],"termed":[49],"LEAP.":[50],"matrix":[52],"multiplications":[53],"are":[56,75],"assigned":[57],"PIM":[59,96],"or":[60],"NoC":[61],"based":[62],"on":[63,103],"the":[64,92,121],"data":[65,69],"dynamicity":[66],"maximize":[68],"locality.":[70],"Model":[71],"partition":[72],"mapping":[74],"optimized":[76],"heuristic":[78],"design":[79],"space":[80],"exploration.":[81],"Dedicated":[82],"fine-grained":[83],"parallelism":[84],"tiling":[86],"techniques":[87],"enable":[88],"high-throughput":[89],"dataflow":[90],"across":[91],"distributed":[93],"resources":[94],"NoC.":[98],"architecture":[100],"is":[101],"evaluated":[102],"Llama":[104],"1B/8B/13B":[105],"models":[106],"shows":[108],"~2.55\u00d7":[109],"throughput":[110],"(tokens/sec)":[111],"improvement":[112],"~71.94\u00d7":[114],"energy":[115],"efficiency":[116],"(tokens/Joule)":[117],"boost":[118],"compared":[119],"A100":[122],"GPU.":[123]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-11-20T00:00:00"}