{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T10:54:42Z","timestamp":1781866482753,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-AC05-00OR22725"],"award-info":[{"award-number":["DE-AC05-00OR22725"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1145\/3797248.3816058","type":"proceedings-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T10:46:08Z","timestamp":1781865968000},"page":"113-119","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Energy-Efficient LLM Inferencing on Analog Devices via Algorithm-Hardware Co-Design"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0850-7714","authenticated-orcid":false,"given":"Guojing","family":"Cong","sequence":"first","affiliation":[{"name":"ORNL, Oak Ridge, Tennessee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4799-7739","authenticated-orcid":false,"given":"Ashish","family":"Gautam","sequence":"additional","affiliation":[{"name":"Oak Ridge National Lab, Oak Ridge, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6894-9851","authenticated-orcid":false,"given":"Shruti R.","family":"Kulkarni","sequence":"additional","affiliation":[{"name":"Computer Science and Mathematics Division, Oak Ridge National Lab, Oak Ridge, TN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9461-6866","authenticated-orcid":false,"given":"Seung-Hwan","family":"Lim","sequence":"additional","affiliation":[{"name":"Oak Ridge National Lab, Oak ridge, TN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"I.\u00a0Beltagy M.\u00a0E. Peters and A.\u00a0Cohan. Longformer: The long-document transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2004.05150 2020."},{"key":"e_1_3_3_2_3_2","unstructured":"M.\u00a0Zaheer et al. Big bird: Transformers for longer sequences. Advances in Neural Information Processing Systems 33:17283\u201317297 2020."},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"T.\u00a0Dao D.\u00a0Fu S.\u00a0Ermon A.\u00a0Rudra and C.\u00a0R\u00e9. Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems 35:16344\u201316359 2022.","DOI":"10.52202\/068431-1189"},{"key":"e_1_3_3_2_5_2","unstructured":"K.\u00a0Choromanski et al. Rethinking attention with performers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2009.14794 2020."},{"key":"e_1_3_3_2_6_2","unstructured":"S.\u00a0Wang B.\u00a0Z. Li M.\u00a0Khabsa H.\u00a0Fang and H.\u00a0Ma. Linformer: Self-attention with linear complexity. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2006.04768 2020."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"P.\u00a0Y. Chen et al. Neurosim: A circuit-level macro model for benchmarking neuro-inspired architectures in online learning. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 37(12):3067\u20133080 2018.","DOI":"10.1109\/TCAD.2018.2789723"},{"key":"e_1_3_3_2_8_2","unstructured":"L.\u00a0Xia et al. MNSIM: Simulation platform for memristor-based neuromorphic computing system. 2016 Design Automation & Test in Europe Conference & Exhibition (DATE) 37(5):1009\u20131022 2017."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"S.\u00a0R. Kulkarni B.\u00a0Rajendran and others. Neuromorphic hardware accelerator for SNN inference based on STT-RAM crossbar arrays. In 2019 26th IEEE International Conference on Electronics Circuits and Systems (ICECS) pages 1\u20134. IEEE 2019.","DOI":"10.1109\/ICECS46596.2019.8964886"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"A.\u00a0Shafiee et al. Isaac: A convolutional neural network accelerator with in-situ analog arithmetic in crossbars. ACM SIGARCH Computer Architecture News 44(3):14\u201326 2016.","DOI":"10.1145\/3007787.3001139"},{"key":"e_1_3_3_2_11_2","unstructured":"J.\u00a0Malekar P.\u00a0Chandarana and et al. PIM-LLM: A high-throughput hybrid PIM architecture for 1-bit LLMs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.01994 2025."},{"key":"e_1_3_3_2_12_2","unstructured":"C.\u00a0Wolters A.\u00a0Sebastian and et al. Memory is all you need: An overview of compute-in-memory architectures for accelerating large language model inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.08413 2024."},{"key":"e_1_3_3_2_13_2","unstructured":"R.-J. Zhu Y.\u00a0Zhang S. Abreu N.\u00a0Sebe and et al. Scalable matmul-free language modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.02528 2024."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"crossref","unstructured":"N.\u00a0Leroux P. Manea C. Sudarshan and et al. Analog in-memory computing attention mechanism for fast and energy-efficient large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.19315 2024.","DOI":"10.21203\/rs.3.rs-5461915\/v1"},{"key":"e_1_3_3_2_15_2","unstructured":"A.\u00a0Vaswani et al. Attention is all you need. Advances in Neural Information Processing Systems 30 2017."},{"key":"e_1_3_3_2_16_2","unstructured":"A.\u00a0Radford J.\u00a0Wu R.\u00a0Child D.\u00a0Luan D.\u00a0Amodei and I.\u00a0Sutskever. Language models are unsupervised multitask learners. OpenAI Blog 1(8):9 2019."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"A.\u00a0Or A.\u00a0Jain D.\u00a0Vega-Myhre J\u00a0 Cai and et al. \u201cTorchAO: PyTorch-Native Training-to-Serving Model Optimization.\u201d arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.16099 2025. doi: 10.48550\/arXiv.2507.16099.","DOI":"10.48550\/arXiv.2507.16099"},{"key":"e_1_3_3_2_18_2","unstructured":"M.\u00a0Elhoushi and J.\u00a0Johnson. \u201cany4: Learned 4-bit Numeric Representation for LLMs.\u201d In International Conference on Machine Learning 2025. https:\/\/openreview.net\/forum?id=tJmhOPkWCj."},{"key":"e_1_3_3_2_19_2","unstructured":"A.\u00a0Gokaslan V.\u00a0Cohen E.\u00a0Pavlick and S.\u00a0Tellex \u201cOpenWebText Corpus \u201d 2019. [Online]. Available: http:\/\/Skylion007.github.io\/OpenWebTextCorpus."},{"key":"e_1_3_3_2_20_2","unstructured":"A.\u00a0Karpathy \u201cchar-rnn \u201d 2015. [Online]. Available: https:\/\/github.com\/karpathy\/char-rnn."},{"key":"e_1_3_3_2_21_2","unstructured":"G.\u00a0Xiao J.\u00a0Lin M.\u00a0Seznec H.\u00a0Wu J.\u00a0Demouth and S.\u00a0Han \u201cSmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models \u201d in Proceedings of the 40th International Conference on Machine Learning Proceedings of Machine Learning Research vol.\u00a0202 pp.\u00a038087\u201338099 PMLR 2023."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"C.\u00a0Lammie W.\u00a0Xiang B.\u00a0Linares-Barranco M.R.\u00a0Azghadi \u201cMemTorch: An open-source simulation framework for memristive deep learning systems \u201d in Neurocomputing vol.\u00a0485 pp.\u00a0124\u2013133 2022.","DOI":"10.1016\/j.neucom.2022.02.043"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"C.\u00a0He W.\u00a0Li J.\u00a0Li Q.\u00a0Li Z.\u00a0Xie T.\u00a0Du \u201cDesign of Ferroelectric Field-Effect Transistor (FeFET)-Based Computing-in-Memory Architecture with Energy-Efficient and Low Latency for Edge AI Computing \u201d in Electronics vol.\u00a015 no.\u00a04 pp.\u00a0841 2026 MDPI.","DOI":"10.3390\/electronics15040841"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"SR.\u00a0Nandakumar SR.\u00a0Kulkarni AV.\u00a0Babu B.\u00a0Rajendran \u201cBuilding brain-inspired computing systems: Examining the role of nanoscale devices \u201d in IEEE Nanotechnology Magazine vol.\u00a012 no.\u00a03 pp.\u00a019\u201335 2018 IEEE.","DOI":"10.1109\/MNANO.2018.2845078"}],"event":{"name":"IGSC '26: International Green and Sustainable Computing Conference","location":"Canandaigua USA","acronym":"IGSC 2026","sponsor":["SIGDA ACM Special Interest Group on Design Automation"]},"container-title":["Proceedings of the 16th ACM International Green and Sustainable Computing Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3797248.3816058","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T10:48:52Z","timestamp":1781866132000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797248.3816058"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":23,"alternative-id":["10.1145\/3797248.3816058","10.1145\/3797248"],"URL":"https:\/\/doi.org\/10.1145\/3797248.3816058","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"2026-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}