{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:31:41Z","timestamp":1760711501240,"version":"3.44.0"},"reference-count":43,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11132978","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["BBAL: A Bidirectional Block Floating Point-Based Quantisation Accelerator for Large Language Models"],"prefix":"10.1109","author":[{"given":"Xiaomeng","family":"Han","sequence":"first","affiliation":[{"name":"Southeast University,National Center of Technology Innovation for EDA, School of Integrated Circuits"}]},{"given":"Yuan","family":"Cheng","sequence":"additional","affiliation":[{"name":"Houmo AI"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Southeast University,National Center of Technology Innovation for EDA, School of Integrated Circuits"}]},{"given":"Junyang","family":"Lu","sequence":"additional","affiliation":[{"name":"Southeast University,National Center of Technology Innovation for EDA, School of Integrated Circuits"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Southeast University,National Center of Technology Innovation for EDA, School of Integrated Circuits"}]},{"given":"X.x.","family":"Zhang","sequence":"additional","affiliation":[{"name":"Jilin Normal University"}]},{"given":"Ning","family":"Xu","sequence":"additional","affiliation":[{"name":"Southeast University,National Center of Technology Innovation for EDA, School of Integrated Circuits"}]},{"given":"Dawei","family":"Yang","sequence":"additional","affiliation":[{"name":"Houmo AI"}]},{"given":"Zhe","family":"Jiang","sequence":"additional","affiliation":[{"name":"Southeast University,National Center of Technology Innovation for EDA, School of Integrated Circuits"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language models are few-shot learners","volume":"1","author":"Mann","year":"2020","journal-title":"arXiv preprint arXiv:2005.14165"},{"key":"ref2","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01401"},{"key":"ref4","article-title":"New trends in machine translation using large language models: Case examples with chatgpt","author":"Lyu","year":"2023","journal-title":"arXiv preprint arXiv:2305.01181"},{"key":"ref5","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2302.13971"},{"key":"ref6","article-title":"A survey on efficient inference for large language models","author":"Zhou","year":"2024","journal-title":"arXiv preprint arXiv:2404.14294"},{"key":"ref7","article-title":"Hardware acceleration of llms: A comprehensive survey and comparison","author":"Koilia","year":"2024","journal-title":"arXiv preprint arXiv:2409.03384"},{"key":"ref8","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han","year":"2015","journal-title":"arXiv preprint arXiv:1510.00149"},{"key":"ref9","article-title":"Billm: Pushing the limit of post-training quantization for llms","author":"Huang","year":"2024","journal-title":"arXiv preprint arXiv:2402.04291"},{"key":"ref10","first-page":"30318","article-title":"Gpt3. int8 (): 8-bit matrix multiplication for transformers at scale","volume":"35","author":"Dettmers","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref11","article-title":"Rptq: Reorder-based post-training quantization for large language models","author":"Yuan","year":"2023","journal-title":"arXiv preprint arXiv:2304.01089"},{"key":"ref12","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ARITH.2019.00022"},{"key":"ref14","article-title":"Fp.8 formats for deep learning","author":"Micikevicius","year":"2022","journal-title":"arXiv preprint arXiv:2209.05433"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.617"},{"key":"ref16","first-page":"25 490","article-title":"Be like water: Adaptive floating point for machine learning","volume-title":"International Conference on Machine Learning","author":"Yeh"},{"article-title":"A block minifloat representation for training deep neural networks","volume-title":"International Conference on Learning Representations","author":"Fox","key":"ref17"},{"article-title":"Bie: Bi-exponent block floating-point for large language models quantization","volume-title":"Fortyfirst International Conference on Machine Learning","author":"Zou","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10222859"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3116302"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11334"},{"issue":"2017","key":"ref22","article-title":"Attention is all you need. advances in neural information processing systems","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586134"},{"key":"ref24","article-title":"Opt: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv:2205.01068"},{"key":"ref25","article-title":"Llm-fp.4: 4-bit floating-point quantized transformers","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv:2310.16836"},{"key":"ref26","article-title":"Illm: Efficient integer-only inference for fully-quantized low-bit large language models","author":"Hu","year":"2024","journal-title":"arXiv preprint arXiv:2405.17849"},{"key":"ref27","first-page":"38 087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning","author":"Xiao"},{"key":"ref28","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv preprint arXiv:2210.17323"},{"key":"ref29","first-page":"28 092","article-title":"Post-training quantization for vision transformer","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/78.492531"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-94691-7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2023.3277247"},{"key":"ref34","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv:2307.09288"},{"article-title":"Meta llama 3: Advancing generative ai responsibly","year":"2024","author":"Meta","key":"ref35"},{"key":"ref36","article-title":"Pointer sentinel mixture models","author":"Merity","year":"2016","journal-title":"arXiv preprint arXiv:1609.07843"},{"key":"ref37","article-title":"Omniquant: Omnidirectionally calibrated quantization for large language models","author":"Shao","year":"2023","journal-title":"arXiv preprint arXiv:2308.13137"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3656221"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228584"},{"journal-title":"Logic synthesis using Synopsys\u00c2\u00ae","year":"1997","author":"Kurup","key":"ref41"},{"key":"ref42","first-page":"28","article-title":"Cacti 6.0: A tool to model large caches","volume":"27","author":"Muralimanohar","year":"2009","journal-title":"HP laboratories"},{"article-title":"Dnnweaver: From high-level deep network models to fpga acceleration","volume-title":"Workshop on Cognitive Architectures","author":"Sharma","key":"ref43"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","start":{"date-parts":[[2025,6,22]]},"location":"San Francisco, CA, USA","end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11132978.pdf?arnumber=11132978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:29:55Z","timestamp":1758000595000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11132978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11132978","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}