{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:01Z","timestamp":1750309501628,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T00:00:00Z","timestamp":1737331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,1,20]]},"DOI":"10.1145\/3658617.3697641","type":"proceedings-article","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T14:32:21Z","timestamp":1741098741000},"page":"554-559","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MPICC: Multiple-Precision Inter-Combined MAC Unit with Stochastic Rounding for Ultra-Low-Precision Training"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4519-5237","authenticated-orcid":false,"given":"Leran","family":"Huang","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School\/Key Laboratory of Advanced Sensor and Integrated System, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4892-2309","authenticated-orcid":false,"given":"Yongpan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University\/Department of Electronic Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6881-5348","authenticated-orcid":false,"given":"Xinyuan","family":"Lin","sequence":"additional","affiliation":[{"name":"Tsinghua University\/Department of Electronic Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2683-9835","authenticated-orcid":false,"given":"Chenhan","family":"Wei","sequence":"additional","affiliation":[{"name":"Tsinghua University\/Department of Electronic Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4793-0972","authenticated-orcid":false,"given":"Wenyu","family":"Sun","sequence":"additional","affiliation":[{"name":"Tsinghua University\/Department of Electronic Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9722-5036","authenticated-orcid":false,"given":"Zengwei","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University\/Department of Electronic Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2618-0084","authenticated-orcid":false,"given":"Boran","family":"Cao","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School\/Key Laboratory of Advanced Sensor and Integrated System, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9031-1323","authenticated-orcid":false,"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University\/Department of Electronic Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2167-8709","authenticated-orcid":false,"given":"Xiaoxia","family":"Fu","sequence":"additional","affiliation":[{"name":"Tsinghua University\/Department of Electronic Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9416-1575","authenticated-orcid":false,"given":"Wentao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University\/Department of Electronic Engineering, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2170-2602","authenticated-orcid":false,"given":"Sheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School\/Key Laboratory of Advanced Sensor and Integrated System, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,3,4]]},"reference":[{"volume-title":"The Eleventh International Conference on Learning Representations.","author":"Brian","key":"e_1_3_2_1_1_1","unstructured":"Brian Chmiel et al. 2023. Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_2_1","unstructured":"Bita Darvish Rouhani et al. 2023. Microscaling Data Formats for Deep Learning. arXiv:2310.10537"},{"volume-title":"ANT: Exploiting Adaptive Numerical Data Type for Lowbit Deep Neural Network Quantization. In 2022 55th IEEE\/ACM International Symposium on Microarchitecture (MICRO). 1414--1433","author":"Cong","key":"e_1_3_2_1_3_1","unstructured":"Cong Guo et al. 2022. ANT: Exploiting Adaptive Numerical Data Type for Lowbit Deep Neural Network Quantization. In 2022 55th IEEE\/ACM International Symposium on Microarchitecture (MICRO). 1414--1433."},{"volume-title":"Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Network. In 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA). 764--775","author":"Hardik","key":"e_1_3_2_1_4_1","unstructured":"Hardik Sharma et al. 2018. Bit Fusion: Bit-Level Dynamically Composable Architecture for Accelerating Deep Neural Network. In 2018 ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA). 764--775."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2016.2525042"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the Great Lakes Symposium on VLSI","author":"Jing","year":"2023","unstructured":"Jing Zhang et al. 2023. Low-Cost Multiple-Precision Multiplication Unit Design For Deep Learning. In Proceedings of the Great Lakes Symposium on VLSI 2023. 9--14."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Luca Bertaccini et al. 2024. MiniFloats on RISC-V Cores: ISA Extensions with Mixed-Precision Short Dot Products. IEEE Transactions on Emerging Topics in Computing (2024) 1--16.","DOI":"10.1109\/TETC.2024.3365354"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Matteo Croci et al. 2022. Stochastic rounding: implementation error analysis and applications. Royal Society Open Science 9 (2022).","DOI":"10.1098\/rsos.211631"},{"key":"e_1_3_2_1_9_1","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Naigang","unstructured":"Naigang Wang et al. 2018. Training Deep Neural Networks with 8-bit Floating Point Numbers. In Advances in Neural Information Processing Systems, Vol. 31."},{"volume-title":"Automation Test in Europe Conference Exhibition (DATE). 1--6.","author":"Ben Sami","key":"e_1_3_2_1_10_1","unstructured":"Sami Ben Ali et al. 2024. A Stochastic Rounding-Enabled Low-Precision Floating-Point MAC for DNN Training. In 2024 Design, Automation Test in Europe Conference Exhibition (DATE). 1--6."},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 32nd International Conference on International Conference on Machine Learning","volume":"37","author":"Suyog","unstructured":"Suyog Gupta et al. 2015. Deep learning with limited numerical precision. In Proceedings of the 32nd International Conference on International Conference on Machine Learning, Vol. 37. 1737--1746."},{"volume-title":"Performance Precision. In 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). 522--531","author":"Stefano","key":"e_1_3_2_1_12_1","unstructured":"Stefano Markidis et al. 2018. NVIDIA Tensor Core Programmability, Performance Precision. In 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). 522--531."},{"key":"e_1_3_2_1_13_1","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Xiao","year":"1807","unstructured":"Xiao Sun et al. 2020. Ultra-Low Precision 4-bit Training of Deep Neural Networks. In Advances in Neural Information Processing Systems, Vol. 33. Curran Associates, Inc., 1796--1807."},{"key":"e_1_3_2_1_14_1","volume-title":"2024 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"67","author":"Yang","unstructured":"Yang Wang et al. 2024. 34.1 A 28nm 83.23TFLOPS\/W POSIT-Based Compute-in-Memory Macro for High-Accuracy AI Applications. In 2024 IEEE International Solid-State Circuits Conference (ISSCC), Vol. 67. 566--568."},{"volume-title":"In Proceedings of the 36th ACM International Conference on Supercomputing (ICS'22)","author":"Zixuan","key":"e_1_3_2_1_15_1","unstructured":"Zixuan Ma et al. 2022. Efficiently emulating high-bitwidth computation with low-bitwidth hardware. In In Proceedings of the 36th ACM International Conference on Supercomputing (ICS'22). 12 pages."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2020.3044752"}],"event":{"name":"ASPDAC '25: 30th Asia and South Pacific Design Automation Conference","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEICE","IPSJ","IEEE CAS","IEEE CEDA"],"location":"Tokyo Japan","acronym":"ASPDAC '25"},"container-title":["Proceedings of the 30th Asia and South Pacific Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658617.3697641","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658617.3697641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658617.3697641"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,20]]},"references-count":16,"alternative-id":["10.1145\/3658617.3697641","10.1145\/3658617"],"URL":"https:\/\/doi.org\/10.1145\/3658617.3697641","relation":{},"subject":[],"published":{"date-parts":[[2025,1,20]]},"assertion":[{"value":"2025-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}