{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:00:42Z","timestamp":1780639242095,"version":"3.54.1"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"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","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016311","name":"Arm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,20]]},"DOI":"10.23919\/date69613.2026.11539636","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:53:10Z","timestamp":1780602790000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Focus Session: Hardware\/Software Co-Design to Accelerate Generative AI Workloads on Heterogeneous Architectures"],"prefix":"10.23919","author":[{"given":"Pratyush","family":"Dhingra","sequence":"first","affiliation":[{"name":"Washington State University,Pullman,WA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vibhanshu","family":"Sharma","sequence":"additional","affiliation":[{"name":"Washington State University,Pullman,WA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Janardhan Rao","family":"Doppa","sequence":"additional","affiliation":[{"name":"Washington State University,Pullman,WA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Partha Pratim","family":"Pande","sequence":"additional","affiliation":[{"name":"Washington State University,Pullman,WA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2022.10.001"},{"key":"ref2","article-title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2018.11.012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080246"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3544974"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3760402"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1109\/ISCAS46773.2023.10181650","article-title":"Architectures and Circuits for Analog-memory-based Hardware Accelerators for Deep Neural Networks","volume-title":"ISCAS","author":"Tsai"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218505"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2021.3092533"},{"key":"ref10","article-title":"FARe: Fault-aware GNN training on ReRAM-based PIM accelerators","volume-title":"DATE","author":"Dhingra"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2023.3282046"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC51906.2022.00178"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3665314.3670814"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247913"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3649219"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001139"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415640"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2023.3273992"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3121264"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2025.3531255"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2016.155"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2019.00095"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2016.348"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3608098"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MDT.2005.136"},{"key":"ref28","article-title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","author":"Lisa Li","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.41"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref31","article-title":"LoRA: Low-Rank Adaptation of Large Language Models","volume-title":"ICLR","author":"Hu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196128"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415665"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317870"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3131114"},{"key":"ref37","article-title":"HR3 AM: A Heat Resilient Design for RRAM-based Neuromorphic Computing","volume-title":"ISLPED","author":"Liu"},{"key":"ref38","article-title":"ThRIve: Thermally Robust CNN Inference via Low-Rank Adaptation in Heterogeneous PIM Architectures","volume":"31","author":"Sharma","year":"2025","journal-title":"ACM TODAES"},{"key":"ref39","article-title":"Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting","author":"Li","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3545611"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM50854.2024.10873537"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IMW61990.2025.11026974"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JXCDC.2021.3057856"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ISVLSI59464.2023.10238622"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2020.2968079"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IMW.2017.7939066"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2018.8614710"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46783.2024.10631339"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM50854.2024.10873472"},{"key":"ref50","article-title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","author":"Zhong","year":"2024"}],"event":{"name":"2026 Design, Automation & Test in Europe Conference (DATE)","location":"Verona, Italy","start":{"date-parts":[[2026,4,20]]},"end":{"date-parts":[[2026,4,22]]}},"container-title":["2026 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539636.pdf?arnumber=11539636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:08:34Z","timestamp":1780636114000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":50,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539636","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}