{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:18:08Z","timestamp":1787530688576,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"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":[[2024,10,27]]},"DOI":"10.1145\/3676536.3676840","type":"proceedings-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T13:21:20Z","timestamp":1744204880000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":19,"title":["Mixed-precision Neural Networks on RISC-V Cores: ISA extensions for Multi-Pumped Soft SIMD Operations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7184-3740","authenticated-orcid":false,"given":"Giorgos","family":"Armeniakos","sequence":"first","affiliation":[{"name":"National Technichal University of Athens, Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4508-6384","authenticated-orcid":false,"given":"Alexis","family":"Maras","sequence":"additional","affiliation":[{"name":"National Technichal University of Athens, Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3151-2730","authenticated-orcid":false,"given":"Sotirios","family":"Xydis","sequence":"additional","affiliation":[{"name":"National Technichal University of Athens, Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6930-6847","authenticated-orcid":false,"given":"Dimitrios","family":"Soudris","sequence":"additional","affiliation":[{"name":"National Technichal University of Athens, Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"1","volume-title":"In-datacenter performance analysis of a tensor processing unit,\" in Proceedings of the 44th annual international symposium on computer architecture","author":"Jouppi N. P.","year":"2017","unstructured":"N. P. Jouppi, C. Young, N. Patil, D. Patterson, G. Agrawal, R. Bajwa, S. Bates, S. Bhatia, N. Boden, A. Borchers, et al., \"In-datacenter performance analysis of a tensor processing unit,\" in Proceedings of the 44th annual international symposium on computer architecture, 2017, pp. 1--12."},{"key":"e_1_3_2_1_2_1","first-page":"33","volume-title":"Circuits and Systems (ICECS)","author":"Garofalo A.","year":"2019","unstructured":"A. Garofalo, M. Rusci, F. Conti, D. Rossi, and L. Benini, \"Pulp-nn: A computing library for quantized neural network inference at the edge on risc-v based parallel ultra low power clusters,\" in 2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS), 2019, pp. 33--36."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"E. Reggiani A. Pappalardo M. Doblas M. Moreto M. Olivieri O. S. Unsal and A. Cristal \"Mix-gemm: An efficient hw-sw architecture for mixed-precision quantized deep neural networks inference on edge devices \" in 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA) 2023 pp. 1085--1098.","DOI":"10.1109\/HPCA56546.2023.10071076"},{"key":"e_1_3_2_1_4_1","volume-title":"Hardware approximate techniques for deep neural network accelerators: A survey,\" ACM Comput. Surv","author":"Armeniakos G.","unstructured":"G. Armeniakos, G. Zervakis, D. Soudris, and J. Henkel, \"Hardware approximate techniques for deep neural network accelerators: A survey,\" ACM Comput. Surv., vol. 55, no. 4, nov 2022."},{"key":"e_1_3_2_1_5_1","first-page":"186","volume-title":"Automation & Test in Europe Conference & Exhibition (DATE)","author":"Garofalo A.","year":"2020","unstructured":"A. Garofalo, G. Tagliavini, F. Conti, D. Rossi, and L. Benini, \"Xpulpnn: Accelerating quantized neural networks on risc-v processors through isa extensions,\" in 2020 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2020, pp. 186--191."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_3_2_1_7_1","unstructured":"www.lowrisc.org \"Ibex risc-v core \" https:\/\/github.com\/lowRISC\/ibex."},{"key":"e_1_3_2_1_8_1","first-page":"1","volume-title":"d. Fine Licht, and T. Hoefler, \"Temporal vectorization: A compiler approach to automatic multi-pumping,\" in 2022 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","author":"Johnsen C.-J.","year":"2022","unstructured":"C.-J. Johnsen, T. D. Matteis, T. Ben-Nun, J. d. Fine Licht, and T. Hoefler, \"Temporal vectorization: A compiler approach to automatic multi-pumping,\" in 2022 IEEE\/ACM International Conference On Computer Aided Design (ICCAD), 2022, pp. 1--9."},{"key":"e_1_3_2_1_9_1","first-page":"206","volume-title":"Architectures and Processors (ASAP)","author":"Zhao R.","year":"2017","unstructured":"R. Zhao, T. Todman, W. Luk, and X. Niu, \"Deeppump: Multi-pumping deep neural networks,\" in 2017 IEEE 28th International Conference on Application-specific Systems, Architectures and Processors (ASAP), 2017, pp. 206--206."},{"key":"e_1_3_2_1_10_1","first-page":"512","volume-title":"IEEE","author":"Ottavi G.","year":"2020","unstructured":"G. Ottavi, A. Garofalo, G. Tagliavini, F. Conti, L. Benini, and D. Rossi, \"A mixed-precision risc-v processor for extreme-edge dnn inference,\" in 2020 IEEE Computer Society Annual Symposium on VLSI (ISVLSI). IEEE, 2020, pp. 512--517."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387902.3394038"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2018.2865489"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2020.2973355"},{"key":"e_1_3_2_1_14_1","article-title":"Optimizing cnn computation using risc-v custom instruction sets for edge platforms","author":"Wang S.","year":"2024","unstructured":"S. Wang, X. Wang, Z. Xu, B. Chen, C. Feng, Q. Wang, and T. T. Ye, \"Optimizing cnn computation using risc-v custom instruction sets for edge platforms,\" IEEE Transactions on Computers, 2024.","journal-title":"IEEE Transactions on Computers"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490422.3502364"},{"key":"e_1_3_2_1_16_1","volume-title":"Sysmol: A hardware-software co-design framework for ultra-low and fine-grained mixed-precision neural networks","author":"Zhou C.","year":"2023","unstructured":"C. Zhou, V. Richard, P. Savarese, Z. Hassman, M. Maire, M. DiBrino, and Y. Li, \"Sysmol: A hardware-software co-design framework for ultra-low and fine-grained mixed-precision neural networks,\" 2023."},{"key":"e_1_3_2_1_17_1","first-page":"1","article-title":"Hardware-aware dnn compression via diverse pruning and mixed-precision quantization","author":"Balaskas K.","year":"2024","unstructured":"K. Balaskas, A. Karatzas, C. Sad, K. Siozios, I. Anagnostopoulos, G. Zervakis, and J. Henkel, \"Hardware-aware dnn compression via diverse pruning and mixed-precision quantization,\" IEEE Transactions on Emerging Topics in Computing, pp. 1--14, 2024.","journal-title":"IEEE Transactions on Emerging Topics in Computing"},{"key":"e_1_3_2_1_18_1","volume-title":"Cmsis-nn: Efficient neural network kernels for arm cortex-m cpus,\" arXiv preprint arXiv:1801.06601","author":"Lai L.","year":"2018","unstructured":"L. Lai, N. Suda, and V. Chandra, \"Cmsis-nn: Efficient neural network kernels for arm cortex-m cpus,\" arXiv preprint arXiv:1801.06601, 2018."},{"key":"e_1_3_2_1_19_1","volume-title":"gemmlowp: A small self-contained low-precision gemm library,\" https:\/\/github.com\/google\/gemmlowp","author":"Jacob B.","year":"2022","unstructured":"B. Jacob and P. Warden, \"gemmlowp: A small self-contained low-precision gemm library,\" https:\/\/github.com\/google\/gemmlowp, 2022."},{"key":"e_1_3_2_1_20_1","unstructured":"STMicroelectronics \"X-CUBE-AI - Artificial Intelligence Expansion Package \" https:\/\/www.st.com\/en\/embedded-software\/x-cube-ai.html 2023."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3066883"},{"key":"e_1_3_2_1_22_1","first-page":"711","article-title":"Mcunet: Tiny deep learning on iot devices","volume":"33","author":"Lin J.","year":"2020","unstructured":"J. Lin, W.-M. Chen, Y. Lin, C. Gan, S. Han, et al., \"Mcunet: Tiny deep learning on iot devices,\" Advances in Neural Information Processing Systems, vol. 33, pp. 11 711--11 722, 2020.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2020.2983648"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2682138"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3566097.3567872"},{"key":"e_1_3_2_1_26_1","first-page":"73","volume-title":"Exploration of low numeric precision deep learning inference using intel\u00ae fpgas,\" in 2018 IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)","author":"Colangelo P.","year":"2018","unstructured":"P. Colangelo, N. Nasiri, E. Nurvitadhi, A. Mishra, M. Margala, and K. Nealis, \"Exploration of low numeric precision deep learning inference using intel\u00ae fpgas,\" in 2018 IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 2018, pp. 73--80."},{"key":"e_1_3_2_1_27_1","volume-title":"Approximate computing survey, part i: Terminology and software & hardware approximation techniques","author":"Leon V.","year":"2023","unstructured":"V. Leon, M. A. Hanif, G. Armeniakos, X. Jiao, M. Shafique, K. Pekmestzi, and D. Soudris, \"Approximate computing survey, part i: Terminology and software & hardware approximation techniques,\" 2023."},{"key":"e_1_3_2_1_28_1","volume-title":"spike, and the rocket core,\" Berkeley Architecture Group","author":"Keller B.","year":"2013","unstructured":"B. Keller, \"Risc-v, spike, and the rocket core,\" Berkeley Architecture Group, 2013."},{"key":"e_1_3_2_1_29_1","unstructured":"W. Snyder P. Wasson D. Galbi and et al \"Verilator \" https:\/\/github.com\/verilator\/verilator."},{"key":"e_1_3_2_1_30_1","volume-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications,\" arXiv preprint arXiv:1704.04861","author":"Howard A. G.","year":"2017","unstructured":"A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, \"Mobilenets: Efficient convolutional neural networks for mobile vision applications,\" arXiv preprint arXiv:1704.04861, 2017."},{"key":"e_1_3_2_1_31_1","volume-title":"Visual wake words dataset,\" arXiv preprint arXiv:1906.05721","author":"Chowdhery A.","year":"2019","unstructured":"A. Chowdhery, P. Warden, J. Shlens, A. Howard, and R. Rhodes, \"Visual wake words dataset,\" arXiv preprint arXiv:1906.05721, 2019."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mejo.2016.04.006"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1077603.1077647"}],"event":{"name":"ICCAD '24: 43rd IEEE\/ACM International Conference on Computer-Aided Design","location":"Newark Liberty International Airport Marriott New York NY USA","acronym":"ICCAD '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CAS","IEEE CEDA","IEEE EDS"]},"container-title":["Proceedings of the 43rd IEEE\/ACM International Conference on Computer-Aided Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676840","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676536.3676840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:45Z","timestamp":1750295925000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676840"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":33,"alternative-id":["10.1145\/3676536.3676840","10.1145\/3676536"],"URL":"https:\/\/doi.org\/10.1145\/3676536.3676840","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2025-04-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}