{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T13:06:44Z","timestamp":1763644004477,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031195679"},{"type":"electronic","value":"9783031195686"}],"license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-19568-6_3","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T09:01:55Z","timestamp":1696064515000},"page":"63-88","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Low- and Mixed-Precision Inference Accelerators"],"prefix":"10.1007","author":[{"given":"Maarten","family":"J. Molendijk","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Floran","family":"A. M. de Putter","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henk","family":"Corporaal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"key":"3_CR1","doi-asserted-by":"crossref","unstructured":"Andri, R., Karunaratne, G., Cavigelli, L., Benini, L.: ChewBaccaNN: A flexible 223 TOPS\/W BNN accelerator. arXiv (May), 23\u201326 (2020)","DOI":"10.1109\/ISCAS51556.2021.9401214"},{"key":"3_CR2","doi-asserted-by":"publisher","unstructured":"Bankman, D., Yang, L., Moons, B., Verhelst, M., Murmann, B.: An always-on 3.8 \u03bc J\/86% CIFAR-10 mixed-signal binary CNN processor with all memory on chip in 28-nm CMOS. IEEE J. Solid-State Circuits 54(1), 158\u2013172 (2019). https:\/\/doi.org\/10.1109\/JSSC.2018.2869150. https:\/\/ieeexplore.ieee.org\/document\/8480105\/","DOI":"10.1109\/JSSC.2018.2869150"},{"key":"3_CR3","unstructured":"Bengio, Y., L\u00e9onard, N., Courville, A.: Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation pp. 1\u201312 (2013). http:\/\/arxiv.org\/abs\/1308.3432"},{"key":"3_CR4","unstructured":"Blalock, D., Ortiz, J.J.G., Frankle, J., Guttag, J.: What is the State of Neural Network Pruning? (2020). http:\/\/arxiv.org\/abs\/2003.03033"},{"key":"3_CR5","first-page":"1","volume":"2020","author":"A Bulat","year":"2019","unstructured":"Bulat, A., Tzimiropoulos, G.: XNOR-Net++: Improved binary neural networks. In: 30th British Machine Vision Conference 2019, BMVC 2019 pp. 1\u201312 (2020)","journal-title":"BMVC"},{"key":"3_CR6","doi-asserted-by":"publisher","unstructured":"Conti, F., Schiavone, P.D., Benini, L.: XNOR neural engine: a hardware accelerator IP for 21.6-fJ\/op binary neural network inference. IEEE Trans. Comput.-Aided Design Integr. Circuits Syst. 37(11), 2940\u20132951 (2018). https:\/\/doi.org\/10.1109\/TCAD.2018.2857019","DOI":"10.1109\/TCAD.2018.2857019"},{"key":"3_CR7","volume-title":"Microprocessor Architectures: From VLIW to TTA","author":"H Corporaal","year":"1997","unstructured":"Corporaal, H.: Microprocessor Architectures: From VLIW to TTA. Wiley, Hoboken (1997)"},{"key":"3_CR8","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.neunet.2018.01.010","volume":"100","author":"L Deng","year":"2018","unstructured":"Deng, L., Jiao, P., Pei, J., Wu, Z., Li, G.: GXNOR-Net: training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework. Neural Netw. 100, 49\u201358 (2018). https:\/\/doi.org\/10.1016\/j.neunet.2018.01.010","journal-title":"Neural Netw."},{"key":"3_CR9","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1109\/FPL.2010.51","volume":"2010","author":"O Esko","year":"2010","unstructured":"Esko, O., J\u00e4\u00e4skel\u00e4inen, P., Huerta, P., De La Lama, C.S., Takala, J., Martinez, J.I.: Customized exposed datapath soft-core design flow with compiler support. In: Proceedings - 2010 International Conference on Field Programmable Logic and Applications, FPL 2010, pp. 217\u2013222 (2010). https:\/\/doi.org\/10.1109\/FPL.2010.51","journal-title":"FPL"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Gholami, A., Kim, S., Dong, Z., Yao, Z., Mahoney, M.W., Keutzer, K.: A Survey of Quantization Methods for Efficient Neural Network Inference (2021). http:\/\/arxiv.org\/abs\/2103.13630","DOI":"10.1201\/9781003162810-13"},{"key":"3_CR11","unstructured":"Gluska, S., Grobman, M.: Exploring Neural Networks Quantization via Layer-Wise Quantization Analysis (2020). http:\/\/arxiv.org\/abs\/2012.08420"},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Huang, S., Waeijen, L., Corporaal, H.: How flexible is your computing system? ACM Trans. Embedd. Comput. Syst. (2022). https:\/\/doi.org\/10.1145\/3524861. https:\/\/dl.acm.org\/doi\/10.1145\/3524861","DOI":"10.1145\/3524861"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"J\u00e4\u00e4skel\u00e4inen, P., Viitanen, T., Takala, J., Berg, H.: HW\/SW co-design toolset for customization of exposed datapath processors. In: Computing Platforms for Software-Defined Radio, pp. 147\u2013164. Springer International Publishing, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49679-5_8","DOI":"10.1007\/978-3-319-49679-5_8"},{"key":"3_CR14","doi-asserted-by":"publisher","unstructured":"Jacob, B., Kligys, S., Chen, B., Zhu, M., Tang, M., Howard, A., Adam, H., Kalenichenko, D.: Quantization and training of neural networks for efficient integer-arithmetic-only inference. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2704\u20132713 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00286","DOI":"10.1109\/CVPR.2018.00286"},{"key":"3_CR15","unstructured":"Kharya, P.: TensorFloat-32 in the A100 GPU Accelerates AI Training, HPC up to 20x (2020). https:\/\/blogs.nvidia.com\/blog\/2020\/05\/14\/tensorfloat-32-precision-format\/"},{"issue":"4","key":"3_CR16","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.1109\/JSSC.2020.3038616","volume":"56","author":"PC Knag","year":"2021","unstructured":"Knag, P.C., Chen, G.K., Sumbul, H.E., Kumar, R., Hsu, S.K., Agarwal, A., Kar, M., Kim, S., Anders, M.A., Kaul, H., Krishnamurthy, R.K.: A 617-TOPS\/W all-digital binary neural network accelerator in 10-nm FinFET CMOS. IEEE J. Solid-State Circuits 56(4), 1082\u20131092 (2021). https:\/\/doi.org\/10.1109\/JSSC.2020.3038616","journal-title":"IEEE J. Solid-State Circuits"},{"issue":"8","key":"3_CR17","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/TC.2021.3059962","volume":"70","author":"L Mei","year":"2021","unstructured":"Mei, L., Houshmand, P., Jain, V., Giraldo, S., Verhelst, M.: ZigZag: enlarging joint architecture-mapping design space exploration for DNN accelerators. IEEE Trans. Comput. 70(8), 1160\u20131174 (2021). https:\/\/doi.org\/10.1109\/TC.2021.3059962","journal-title":"IEEE Trans. Comput."},{"issue":"8","key":"3_CR18","doi-asserted-by":"publisher","first-page":"1962","DOI":"10.1109\/TVLSI.2019.2906678","volume":"27","author":"O Muller","year":"2019","unstructured":"Muller, O., Prost-Boucle, A., Bourge, A., Petrot, F.: Efficient decompression of binary encoded balanced ternary sequences. IEEE Trans. Very Large Scale Integr. Syst. 27(8), 1962\u20131966 (2019). https:\/\/doi.org\/10.1109\/TVLSI.2019.2906678","journal-title":"IEEE Trans. Very Large Scale Integr. Syst."},{"key":"3_CR19","unstructured":"Multanen, J.: Energy-Efficient Instruction Streams for Embedded Processors. Ph.D. Thesis, Tampere University (2021)"},{"key":"3_CR20","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1109\/ISPASS.2019.00042","volume":"2019","author":"A Parashar","year":"2019","unstructured":"Parashar, A., Raina, P., Shao, Y.S., Chen, Y.H., Ying, V.A., Mukkara, A., Venkatesan, R., Khailany, B., Keckler, S.W., Emer, J.: Timeloop: A systematic approach to DNN accelerator evaluation. In: Proceedings - 2019 IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS 2019, pp. 304\u2013315 (2019). https:\/\/doi.org\/10.1109\/ISPASS.2019.00042","journal-title":"ISPASS"},{"key":"3_CR21","first-page":"525","volume":"9908","author":"M Rastegari","year":"2016","unstructured":"Rastegari, M., Ordonez, V., Redmon, J., Farhadi, A.: XNOR-net: ImageNet classification using binary convolutional neural networks. In: Computer Vision\u2014ECCV 2016. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics), LNCS, vol. 9908, pp. 525\u2013542 (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_32","journal-title":"LNCS"},{"key":"3_CR22","unstructured":"Scherer, M., Rutishauser, G., Cavigelli, L., Benini, L.: CUTIE: Beyond PetaOp\/s\/W Ternary DNN Inference Acceleration with Better-than-Binary Energy Efficiency pp. 1\u201314 (2020). http:\/\/arxiv.org\/abs\/2011.01713"},{"key":"3_CR23","doi-asserted-by":"publisher","unstructured":"Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., Le, Q.V.: MnasNet: Platform-aware neural architecture search for mobile. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2019-June, pp. 2815\u20132823 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00293","DOI":"10.1109\/CVPR.2019.00293"},{"key":"3_CR24","volume-title":"PULPino: Datasheet","author":"A Traber","year":"2017","unstructured":"Traber, A., Gautschi, M.: PULPino: Datasheet. ETH Zurich, University of Bologna (2017)"},{"key":"3_CR25","doi-asserted-by":"publisher","unstructured":"Ueyoshi, K., Papistas, I.A., Houshmand, P., Sarda, G.M., Jain, V., Shi, M., Zheng, Q., Giraldo, S., Vrancx, P., Doevenspeck, J., Bhattacharjee, D., Cosemans, S., Mallik, A., Debacker, P., Verkest, D., Verhelst, M.: DIANA: An end-to-end energy-efficient digital and ANAlog hybrid neural network SoC. In: 2022 IEEE International Solid- State Circuits Conference (ISSCC), pp. 1\u20133. IEEE (2022). https:\/\/doi.org\/10.1109\/ISSCC42614.2022.9731716. https:\/\/ieeexplore.ieee.org\/document\/9731716\/","DOI":"10.1109\/ISSCC42614.2022.9731716"},{"key":"3_CR26","doi-asserted-by":"publisher","unstructured":"Valavi, H., Ramadge, P.J., Nestler, E., Verma, N.: A 64-Tile 2.4-Mb in-memory-computing CNN accelerator employing charge-domain compute. IEEE J. Solid-State Circuits 54(6), 1789\u20131799 (2019). https:\/\/doi.org\/10.1109\/JSSC.2019.2899730. https:\/\/ieeexplore.ieee.org\/document\/8660469\/","DOI":"10.1109\/JSSC.2019.2899730"},{"key":"3_CR27","unstructured":"Wang, S., Kanwar, P.: BFloat16: The secret to high performance on Cloud TPUs (2019). https:\/\/cloud.google.com\/blog\/products\/ai-machine-learning\/bfloat16-the-secret-to-high-performance-on-cloud-tpus"},{"key":"3_CR28","doi-asserted-by":"publisher","unstructured":"Wu, B., Dai, X., Zhang, P., Wang, Y., Sun, F., Wu, Y., Tian, Y., Vajda, P., Jia, Y., Keutzer, K.: FBNET: Hardware-aware efficient convnet design via differentiable neural architecture search. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2019-June, pp. 10726\u201310734 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01099","DOI":"10.1109\/CVPR.2019.01099"},{"key":"3_CR29","doi-asserted-by":"publisher","unstructured":"Wu, Y.N., Emer, J.S., Sze, V.: Accelergy: An architecture-level energy estimation methodology for accelerator designs. In: IEEE\/ACM International Conference on Computer-Aided Design, Digest of Technical Papers, ICCAD 2019-Nov (2019). https:\/\/doi.org\/10.1109\/ICCAD45719.2019.8942149","DOI":"10.1109\/ICCAD45719.2019.8942149"}],"container-title":["Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19568-6_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T09:07:38Z","timestamp":1696064858000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19568-6_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"ISBN":["9783031195679","9783031195686"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19568-6_3","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]},"assertion":[{"value":"1 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}