{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:50:54Z","timestamp":1765547454128,"version":"build-2065373602"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":["2112562","2328805"],"award-info":[{"award-number":["2112562","2328805"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-23-2-0224"],"award-info":[{"award-number":["W911NF-23-2-0224"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Des. Test"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/mdat.2025.3600328","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:16:53Z","timestamp":1755627413000},"page":"54-62","source":"Crossref","is-referenced-by-count":1,"title":["Circuits to Systems: Codesigning Efficient AI Hardware"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1486-8412","authenticated-orcid":false,"given":"Yiran","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4479-5525","authenticated-orcid":false,"given":"Cong","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3054-0617","authenticated-orcid":false,"given":"Yintao","family":"He","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]},{"given":"Mingyuan","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9146-370X","authenticated-orcid":false,"given":"Tergel","family":"Molom-Ochir","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]},{"given":"Nicky","family":"Ramos","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]},{"given":"Haoxuan","family":"Shan","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8815-7948","authenticated-orcid":false,"given":"Chiyue","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3228-6544","authenticated-orcid":false,"given":"Hai","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/2.30"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"ref3","article-title":"Gain cell-based analog content addressable memory for dynamic associative tasks in AI","author":"Manea","year":"2024","journal-title":"arXiv:2410.09755"},{"key":"ref4","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"volume-title":"CUDA C++ Programming Guide","year":"2023","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref7","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"Han","year":"2015","journal-title":"arXiv:1510.00149"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00095"},{"key":"ref9","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Brown"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5573\/JSTS.2022.22.1.30"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41563-019-0291-x"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2009.2032192"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898010"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/felec.2022.847069"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/aelm.202101198"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.112130359"},{"key":"ref17","first-page":"256","article-title":"Systolic arrays (for VLSI)","volume-title":"Sparse Matrix Proceedings 1978","volume":"1","author":"Kung","year":"1979"},{"volume-title":"NVIDIA A100 Tensor Core GPU Architecture","year":"2025","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00069"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1002\/smsc.202400133"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1103\/physrevapplied.11.054065"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1039\/d2mh01087a"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"ref24","first-page":"31094","article-title":"FlexGen: High-throughput generative inference of large language models with a single GPU","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sheng"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3676641.3716009"},{"issue":"2","key":"ref26","first-page":"3","article-title":"LoRa: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","volume":"1","author":"Hu"},{"volume-title":"Mastering LLM Techniques: Inference Optimization","year":"2023","key":"ref27"},{"key":"ref28","article-title":"BitNet: Scaling 1-bit transformers for large language models","author":"Wang","year":"2023","journal-title":"arXiv:2310.11453"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"}],"container-title":["IEEE Design & Test"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6221038\/11219247\/11130367-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221038\/11219247\/11130367.pdf?arnumber=11130367","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T17:39:15Z","timestamp":1761759555000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11130367\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":29,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/mdat.2025.3600328","relation":{},"ISSN":["2168-2356","2168-2364"],"issn-type":[{"type":"print","value":"2168-2356"},{"type":"electronic","value":"2168-2364"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}