{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:10:39Z","timestamp":1781885439024,"version":"3.54.5"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T00:00:00Z","timestamp":1761436800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,26]]},"DOI":"10.1109\/iccad66269.2025.11240722","type":"proceedings-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:39:34Z","timestamp":1763663974000},"page":"1-9","source":"Crossref","is-referenced-by-count":6,"title":["LEAP: LLM Inference on Scalable PIM-NoC Architecture with Balanced Dataflow and Fine-Grained Parallelism"],"prefix":"10.1109","author":[{"given":"Yimin","family":"Wang","sequence":"first","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue Jiet","family":"Chong","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanyao","family":"Fong","sequence":"additional","affiliation":[{"name":"National University of Singapore,Department of Electrical and Computer Engineering,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41565-020-0655-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-023-01053-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3649219"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213542"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2024.3427421"},{"key":"ref6","first-page":"1","article-title":"ReTransformer: ReRAM-based processing-in-memory architecture for transformer acceleration","volume-title":"Proceedings of the 39th International Conference on Computer-Aided Design","author":"Yang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3344524"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref10","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref11","article-title":"Introducing Llama 3.1: Our most capable models to date","year":"2024"},{"key":"ref12","article-title":"Llama 3.2: Revolutionizing edge AI and vision with open, customizable models","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2789723"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3043731"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2019.2958568"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46783.2024.10631368"},{"key":"ref17","first-page":"16344","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"WaferLLM: A wafer-scale LLM inference system","author":"He","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MSE.2007.44"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.33"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401746"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2023.3328864"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378514"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247873"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323612"}],"event":{"name":"2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","location":"Munich, Germany","start":{"date-parts":[[2025,10,26]]},"end":{"date-parts":[[2025,10,30]]}},"container-title":["2025 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11240608\/11240621\/11240722.pdf?arnumber=11240722","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T05:43:29Z","timestamp":1763703809000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240722\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/iccad66269.2025.11240722","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]}}}