{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T06:46:32Z","timestamp":1785912392185,"version":"3.56.0"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62504139,62325405,U24B6015"],"award-info":[{"award-number":["62504139,62325405,U24B6015"]}]},{"name":"Beijing Natural Science Foundation","award":["L257010"],"award-info":[{"award-number":["L257010"]}]},{"name":"National Key R&D Program of China","award":["2023YFB4502200"],"award-info":[{"award-number":["2023YFB4502200"]}]},{"name":"Beijing National Research Center for Information Science, Technology","award":["BNR2024TD03001"],"award-info":[{"award-number":["BNR2024TD03001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/isca66397.2026.00104","type":"proceedings-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T19:17:12Z","timestamp":1785871032000},"page":"1383-1399","source":"Crossref","is-referenced-by-count":0,"title":["Bringing Near Data Processing Into the Low-Bit Floating-Point Era"],"prefix":"10.1109","author":[{"given":"Tongxin","family":"Xie","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehao","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihao","family":"Jia","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuechen","family":"Xi","sequence":"additional","affiliation":[{"name":"Nankai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Microelectronics, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mo","family":"Guang","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiale","family":"Yan","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaiwen","family":"Long","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingcheng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huazhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Pretraining large language models with nvfp4","author":"Abecassis","year":"2025","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00070"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00080"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3180"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/access.2018.2877890"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Quartet: Native fp4 training can be optimal for large language models","author":"Castro","year":"2025","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/PACT58117.2023.00017"},{"key":"ref9","article-title":"Sana-video: Efficient video generation with block linear diffusion transformer","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Fp4 all the way: Fully quantized training of 1lms","author":"Chmiel","year":"2025","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3132402.3132406"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527388"},{"key":"ref14","first-page":"10271","article-title":"Pushing the limits of narrow precision inferencing at cloud scale with microsoft floating point","volume":"33","author":"Rouhani","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056040"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.22"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref20","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2015","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3658617.3697641"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00029"},{"key":"ref26","first-page":"46","article-title":"Jit-q: Just-intime quantization with processing-in-memory for efficient ml training","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Ibrahim","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3410842"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS54282.2022.9869896"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00070"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2025.3532682"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358284"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3725843.3756118"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731711"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731008"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640376"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651352"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2020.2973991"},{"key":"ref39","first-page":"3","article-title":"Llm-mq: Mixed-precision quantization for efficient 1lm deployment","volume-title":"The Efficient Natural Language and Speech Processing Workshop with NeurIPS","volume":"9","author":"Li","year":"2023"},{"key":"ref40","first-page":"87","article-title":"Awq: Activation-aware weight quantization for on-device llm compression and acceleration","volume-title":"Proceedings of machine learning and systems","volume":"6","author":"Lin","year":"2024"},{"key":"ref41","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731041"},{"key":"ref43","volume-title":"Memory-centric computing","author":"Mutlu","year":"2023"},{"key":"ref44","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"OpenAI","volume-title":"Gpt-4 technical report","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"ref47","article-title":"Microscaling data formats for deep learning","author":"Rouhani","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651324"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731096"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607077"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00027"},{"key":"ref52","volume-title":"Cutlass","author":"Thakkar","year":"2023"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582026"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00052"},{"key":"ref55","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","volume-title":"Block scaled matrix multiplication - triton documentation","author":"Developers","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref60","article-title":"Optimizing large language model training using fp4 quantization","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref61","volume-title":"Memory is all you need: An overview of compute-in-memory architectures for accelerating large language model inference","author":"Wolters","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s44335-024-00004-2"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00054"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00055"},{"key":"ref65","article-title":"Sageattention: Accurate 8-bit attention for plug-and-play inference acceleration","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Sageattention 3: Microscaling fp4 attention for inference and an exploration of 8-bit training","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"}],"event":{"name":"2026 ACM\/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA)","location":"Raleigh, NC, USA","start":{"date-parts":[[2026,6,27]]},"end":{"date-parts":[[2026,7,1]]}},"container-title":["2026 ACM\/IEEE 53rd Annual International Symposium on Computer Architecture (ISCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11617393\/11617394\/11617747.pdf?arnumber=11617747","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T05:59:54Z","timestamp":1785909594000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11617747\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/isca66397.2026.00104","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]}}}