{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T16:52:22Z","timestamp":1793206342848,"version":"4.5.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CSR-2308530"],"award-info":[{"award-number":["CSR-2308530"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["ARO-W911NF-24-1-0240"],"award-info":[{"award-number":["ARO-W911NF-24-1-0240"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tcad.2025.3531255","type":"journal-article","created":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T13:36:47Z","timestamp":1737121007000},"page":"2842-2855","source":"Crossref","is-referenced-by-count":12,"title":["Atleus: Accelerating Transformers on the Edge Enabled by 3D Heterogeneous Manycore Architectures"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0422-3365","authenticated-orcid":false,"given":"Pratyush","family":"Dhingra","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3848-5301","authenticated-orcid":false,"given":"Janardhan Rao","family":"Doppa","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5930-8531","authenticated-orcid":false,"given":"Partha Pratim","family":"Pande","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A survey of transformers","author":"Lin","year":"2021","journal-title":"arXiv:2106.04554"},{"key":"ref2","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022","journal-title":"arXiv:2204.02311"},{"key":"ref3","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv:2005.14165"},{"key":"ref4","article-title":"Finetuned language models are zero-shot learners","author":"Wei","year":"2022","journal-title":"arXiv:2109.01652"},{"key":"ref5","article-title":"QLoRA: Efficient finetuning of quantized LLMs","author":"Dettmers","year":"2023","journal-title":"arXiv:2305.14314"},{"key":"ref6","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref7","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","author":"Liu","year":"2022","journal-title":"arXiv:2205.05638"},{"key":"ref8","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019","journal-title":"arXiv:1902.00751"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2998456"},{"key":"ref10","first-page":"1","article-title":"Architectures and circuits for analog-memory-based hardware accelerators for deep neural networks","volume-title":"Proc. IEEE ISCAS","author":"Tsai"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589114"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2023.3282046"},{"key":"ref13","first-page":"1","article-title":"Noise injection adaption: End-to-end ReRAM crossbar non-ideal effect adaption for neural network mapping","volume-title":"Proc. 56th ACM\/IEEE DAC","author":"He"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3131114"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2022.3227871"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/DAC.2018.8465850"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2018.11.012"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.12"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415640"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3273992"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3121264"},{"key":"ref24","first-page":"175","article-title":"FTRANS: Energy-efficient acceleration of transformers using FPGA","volume-title":"Proc. ACM\/IEEE ISLPED","author":"Bingbing"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247913"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3649219"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191521"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.41"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2016.155"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2019.00095"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ectc51906.2022.00178"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2016.348"},{"key":"ref37","volume-title":"Simplify DDR PHY.","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"ref39","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023","journal-title":"arXiv:2307.08691"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MDT.2005.136"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.mee.2014.10.019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3608098"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3604802"},{"key":"ref44","article-title":"8-bit optimizers via block-wise quantization","author":"Dettmers","year":"2022","journal-title":"arXiv:2110.02861"},{"key":"ref45","article-title":"HuggingFace\u2019s Transformers: State-of-the-art natural language processing","author":"Wolf","year":"2020","journal-title":"arXiv:1910.03771"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3043731"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2013.6557149"},{"key":"ref49","volume-title":"Join the Hugging Face Community","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/2966986.2980095"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/DSD.2009.233"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3386263.3406931"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI.2016.133"},{"key":"ref54","article-title":"Negative feedback training: A novel concept to improve robustness of NVCIM DNN accelerators","author":"Qin","year":"2024","journal-title":"arXiv:2305.14561"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD51958.2021.9643444"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1038\/s44172-023-00074-3"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.3013194"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/43\/11085011\/10844861-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/11085011\/10844861.pdf?arnumber=10844861","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T18:43:16Z","timestamp":1763750596000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10844861\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":58,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2025.3531255","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}