{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:44:34Z","timestamp":1767987874132,"version":"3.49.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.23919\/date64628.2025.10993005","type":"proceedings-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:36:35Z","timestamp":1747848995000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["HAAN: A Holistic Approach for Accelerating Normalization Operations in Large Language Models"],"prefix":"10.23919","author":[{"given":"Tianfan","family":"Peng","sequence":"first","affiliation":[{"name":"Tandon School of Engineering, New York University,New York,USA"}]},{"given":"Tianhua","family":"Xia","sequence":"additional","affiliation":[{"name":"Tandon School of Engineering, New York University,New York,USA"}]},{"given":"Jiajun","family":"Qin","sequence":"additional","affiliation":[{"name":"Tandon School of Engineering, New York University,New York,USA"}]},{"given":"Sai Qian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tandon School of Engineering, New York University,New York,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439477"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00051"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref4","author":"Ba","year":"2016","journal-title":"Layer normalization"},{"key":"ref5","article-title":"Root mean square layer normalization","volume":"32","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","article-title":"Understanding and improving layer normalization","volume":"32","author":"Xu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323725"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530505"},{"key":"ref9","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9180870"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/APCCAS.2018.8605654"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2022.3175534"},{"key":"ref14","author":"Xia","year":"2023","journal-title":"Softmax acceleration with adaptive numeric format for both training and inference"},{"key":"ref15","author":"Tseng","year":"2024","journal-title":"Quip#: Even better llm quantization with hadamard incoherence and lattice codebooks"},{"key":"ref16","author":"Ashkboos","year":"2024","journal-title":"Quarot: Outlier-free 4-bit inference in rotated llms"},{"key":"ref17","article-title":"Optimal brain compression: A framework for accurate post-training quantization and pruning","volume-title":"Advances in Neural Information Processing Systems","author":"Frantar","year":"2022"},{"key":"ref18","author":"Frantar","year":"2023","journal-title":"Gptq: Accurate post-training quantization for generative pretrained transformers"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref20","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref21","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-55560-2_5"},{"key":"ref23","author":"Zhang","year":"2022","journal-title":"Opt: Open pretrained transformer language models"},{"key":"ref24","author":"Brown","year":"2020","journal-title":"Language models are few-shot learners"},{"key":"ref25","author":"Shoeybi","year":"2019","journal-title":"Megatron-lm: Training multi-billion parameter language models using model parallelism"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Asia59966.2023.10326397"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC49529.2020.9524802"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9474043"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123359"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref31","article-title":"Fast inverse square root","volume":"32","author":"Lomont","year":"2003","journal-title":"Tech-315 nical Report"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3474381"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1472"},{"key":"ref35","author":"Clark","year":"2018","journal-title":"Think you have solved question answering? try arc, the ai2 reasoning challenge"},{"key":"ref36","volume-title":"A framework for few-shot language model evaluation","author":"Gao","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE-Asia59966.2023.10326397"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/PACET56979.2022.9976354"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3312775"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1109\/SOCC49529.2020.9524802","volume-title":"Hardware accelerator for multi-head attention and position-wise feed-forward in the transformer","author":"Lu","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3656177"}],"event":{"name":"2025 Design, Automation & Test in Europe Conference (DATE)","location":"Lyon, France","start":{"date-parts":[[2025,3,31]]},"end":{"date-parts":[[2025,4,2]]}},"container-title":["2025 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10992638\/10992588\/10993005.pdf?arnumber=10993005","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T05:32:18Z","timestamp":1747891938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10993005\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":41,"URL":"https:\/\/doi.org\/10.23919\/date64628.2025.10993005","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]}}}