{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T18:08:24Z","timestamp":1784830104152,"version":"3.55.0"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"7923","license":[{"start":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T00:00:00Z","timestamp":1660694400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T00:00:00Z","timestamp":1660694400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nature"],"published-print":{"date-parts":[[2022,8,18]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Realizing increasingly complex artificial intelligence (AI) functionalities directly on edge devices calls for unprecedented energy efficiency of edge hardware. Compute-in-memory (CIM) based on resistive random-access memory (RRAM)<jats:sup>1<\/jats:sup>promises to meet such demand by storing AI model weights in dense, analogue and non-volatile RRAM devices, and by performing AI computation directly within RRAM, thus eliminating power-hungry data movement between separate compute and memory<jats:sup>2\u20135<\/jats:sup>. Although recent studies have demonstrated in-memory matrix-vector multiplication on fully integrated RRAM-CIM hardware<jats:sup>6\u201317<\/jats:sup>, it remains a goal for a RRAM-CIM chip to simultaneously deliver high energy efficiency, versatility to support diverse models and software-comparable accuracy. Although efficiency, versatility and accuracy are all indispensable for broad adoption of the technology, the inter-related trade-offs among them cannot be addressed by isolated improvements on any single abstraction level of the design. Here, by co-optimizing across all hierarchies of the design from algorithms and architecture to circuits and devices, we present NeuRRAM\u2014a RRAM-based CIM chip that simultaneously delivers versatility in reconfiguring CIM cores for diverse model architectures, energy efficiency that is two-times better than previous state-of-the-art RRAM-CIM chips across various computational bit-precisions, and inference accuracy comparable to software models quantized to four-bit weights across various AI tasks, including accuracy of 99.0\u2009percent on MNIST<jats:sup>18<\/jats:sup>and 85.7\u2009percent on CIFAR-10<jats:sup>19<\/jats:sup>image classification, 84.7-percent accuracy on Google speech command recognition<jats:sup>20<\/jats:sup>, and a 70-percent reduction in image-reconstruction error on a Bayesian image-recovery task.<\/jats:p>","DOI":"10.1038\/s41586-022-04992-8","type":"journal-article","created":{"date-parts":[[2022,8,17]],"date-time":"2022-08-17T16:07:57Z","timestamp":1660752477000},"page":"504-512","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":883,"title":["A compute-in-memory chip based on resistive random-access memory"],"prefix":"10.1038","volume":"608","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3507-9014","authenticated-orcid":false,"given":"Weier","family":"Wan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3066-4898","authenticated-orcid":false,"given":"Rajkumar","family":"Kubendran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clemens","family":"Schaefer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sukru Burc","family":"Eryilmaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dabin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen","family":"Deiss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Priyanka","family":"Raina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Qian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2417-983X","authenticated-orcid":false,"given":"Bin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siddharth","family":"Joshi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huaqiang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"H.-S. Philip","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3166-5529","authenticated-orcid":false,"given":"Gert","family":"Cauwenberghs","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,8,17]]},"reference":[{"key":"4992_CR1","doi-asserted-by":"publisher","first-page":"1951","DOI":"10.1109\/JPROC.2012.2190369","volume":"100","author":"HSP Wong","year":"2012","unstructured":"Wong, H. S. P. et al. Metal-oxide RRAM. Proc. IEEE 100, 1951\u20131970 (2012).","journal-title":"Proc. IEEE"},{"key":"4992_CR2","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1038\/nature14441","volume":"521","author":"M Prezioso","year":"2015","unstructured":"Prezioso, M. et al. Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature 521, 61\u201364 (2015).","journal-title":"Nature"},{"key":"4992_CR3","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41586-018-0180-5","volume":"558","author":"S Ambrogio","year":"2018","unstructured":"Ambrogio, S. et al. Equivalent-accuracy accelerated neural-network training using analogue memory. Nature 558, 60\u201367 (2018).","journal-title":"Nature"},{"key":"4992_CR4","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1038\/s41928-018-0092-2","volume":"1","author":"D Ielmini","year":"2018","unstructured":"Ielmini, D. & Wong, H. S. P. In-memory computing with resistive switching devices. Nat. Electron. 1, 333\u2013343 (2018).","journal-title":"Nat. Electron."},{"key":"4992_CR5","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1038\/s41586-020-1942-4","volume":"577","author":"P Yao","year":"2020","unstructured":"Yao, P. et al. Fully hardware-implemented memristor convolutional neural network. Nature 577, 641\u2013646 (2020).","journal-title":"Nature"},{"key":"4992_CR6","doi-asserted-by":"crossref","unstructured":"Mochida, R. et al. A 4M synapses integrated analog ReRAM based 66.5 TOPS\/W neural-network processor with cell current controlled writing and flexible network architecture. In Symposium on VLSI Technology, Digest of Technical Papers 175\u2013176 (IEEE, 2018).","DOI":"10.1109\/VLSIT.2018.8510676"},{"key":"4992_CR7","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1038\/s41928-019-0288-0","volume":"2","author":"WH Chen","year":"2019","unstructured":"Chen, W. H. et al. CMOS-integrated memristive non-volatile computing-in-memory for AI edge processors. Nat. Electron. 2, 420\u2013428 (2019).","journal-title":"Nat. Electron."},{"key":"4992_CR8","doi-asserted-by":"crossref","unstructured":"Khaddam-Aljameh, R. et al. HERMES core-A 14nm CMOS and PCM-based in-memory compute core using an array of 300ps\/LSB linearized CCO-based ADCs and local digital processing. In IEEE Symposium on VLSI Circuits, Digest of Technical Papers JFS2-5 (IEEE, 2021).","DOI":"10.23919\/VLSICircuits52068.2021.9492362"},{"key":"4992_CR9","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1038\/s41928-021-00676-9","volume":"4","author":"JM Hung","year":"2021","unstructured":"Hung, J. M. et al. A four-megabit compute-in-memory macro with eight-bit precision based on CMOS and resistive random-access memory for AI edge devices. Nat. Electron. 4, 921\u2013930 (2021).","journal-title":"Nat. Electron."},{"key":"4992_CR10","doi-asserted-by":"crossref","unstructured":"Xue, C. X. et al. A 1Mb multibit ReRAM computing-in-memory macro with 14.6ns parallel MAC computing time for CNN based AI edge processors. In IEEE International Solid-State Circuits Conference (ISSCC), Digest of Technical Papers 388\u2013390 (IEEE, 2019).","DOI":"10.1109\/ISSCC.2019.8662395"},{"key":"4992_CR11","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1038\/s41928-019-0270-x","volume":"2","author":"F Cai","year":"2019","unstructured":"Cai, F. et al. A fully integrated reprogrammable memristor\u2013CMOS system for efficient multiply\u2013accumulate operations. Nat. Electron. 2, 290\u2013299 (2019).","journal-title":"Nat. Electron."},{"key":"4992_CR12","doi-asserted-by":"crossref","unstructured":"Ishii, M. et al. On-chip trainable 1.4M 6T2R PCM synaptic array with 1.6K stochastic LIF neurons for spiking RBM. In International Electron Devices Meeting (IEDM), Technical Digest 14.2.1\u201314.2.4 (IEEE, 2019).","DOI":"10.1109\/IEDM19573.2019.8993466"},{"key":"4992_CR13","doi-asserted-by":"crossref","unstructured":"Yan, B. et al. RRAM-based spiking nonvolatile computing-in-memory processing engine with precision-configurable in situ nonlinear activation. In Symposium on VLSI Technology, Digest of Technical Papers T86\u2013T87 (IEEE, 2019).","DOI":"10.23919\/VLSIT.2019.8776485"},{"key":"4992_CR14","doi-asserted-by":"crossref","unstructured":"Wan, W. et al. A 74 TMACS\/W CMOS-RRAM neurosynaptic core with dynamically reconfigurable dataflow and in-situ transposable weights for probabilistic graphical models. In IEEE International Solid-State Circuits Conference (ISSCC), Digest of Technical Papers 498\u2013500 (IEEE, 2020).","DOI":"10.1109\/ISSCC19947.2020.9062979"},{"key":"4992_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Q. et al. A fully integrated analog ReRAM based 78.4TOPS\/W compute-in-memory chip with fully parallel MAC computing. In IEEE International Solid-State Circuits Conference (ISSCC), Digest of Technical Papers 500\u2013502 (IEEE, 2020).","DOI":"10.1109\/ISSCC19947.2020.9062953"},{"key":"4992_CR16","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1038\/s41928-020-00505-5","volume":"4","author":"CX Xue","year":"2021","unstructured":"Xue, C. X. et al. A CMOS-integrated compute-in-memory macro based on resistive random-access memory for AI edge devices. Nat. Electron. 4, 81\u201390 (2021).","journal-title":"Nat. Electron."},{"key":"4992_CR17","doi-asserted-by":"publisher","first-page":"6629","DOI":"10.1109\/TED.2021.3115993","volume":"68","author":"P Narayanan","year":"2021","unstructured":"Narayanan, P. et al. Fully on-chip MAC at 14 nm enabled by accurate row-wise programming of PCM-based weights and parallel vector-transport in duration-format. IEEE Trans. Electron Devices 68, 6629\u20136636 (2021).","journal-title":"IEEE Trans. Electron Devices"},{"key":"4992_CR18","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278\u20132323 (1998).","journal-title":"Proc. IEEE"},{"key":"4992_CR19","unstructured":"Krizhevsky, A. & Hinton, G. Learning Multiple Layers of Features from Tiny Images (2009); https:\/\/www.cs.toronto.edu\/~kriz\/learning-features-2009-TR.pdf"},{"key":"4992_CR20","unstructured":"Warden, P. Speech commands: a dataset for limited-vocabulary speech recognition. Preprint at https:\/\/arxiv.org\/abs\/1804.03209 (2018)."},{"key":"4992_CR21","doi-asserted-by":"crossref","unstructured":"Joshi, V. et al. Accurate deep neural network inference using computational phase-change memory. Nat. Commun. 11, 2473 (2020).","DOI":"10.1038\/s41467-020-16108-9"},{"key":"4992_CR22","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms3072","volume":"4","author":"F Alibart","year":"2013","unstructured":"Alibart, F., Zamanidoost, E. & Strukov, D. B. Pattern classification by memristive crossbar circuits using ex situ and in situ training. Nat. Commun. 4, 2072 (2013).","journal-title":"Nat. Commun."},{"key":"4992_CR23","doi-asserted-by":"crossref","unstructured":"Eryilmaz, S. B. et al. Experimental demonstration of array-level learning with phase change synaptic devices. In International Electron Devices Meeting (IEDM), Technical Digest 25.5.1\u201325.5.4 (IEEE, 2013).","DOI":"10.1109\/IEDM.2013.6724691"},{"key":"4992_CR24","doi-asserted-by":"publisher","first-page":"3498","DOI":"10.1109\/TED.2015.2439635","volume":"62","author":"GW Burr","year":"2015","unstructured":"Burr, G. W. et al. Experimental demonstration and tolerancing of a large-scale neural network (165 000 synapses) using phase-change memory as the synaptic weight element. IEEE Trans. Electron Devices 62, 3498\u20133507 (2015).","journal-title":"IEEE Trans. Electron Devices"},{"key":"4992_CR25","doi-asserted-by":"publisher","first-page":"5004","DOI":"10.1109\/TED.2016.2616483","volume":"63","author":"SB Eryilmaz","year":"2016","unstructured":"Eryilmaz, S. B. et al. Training a probabilistic graphical model with resistive switching electronic synapses. IEEE Trans. Electron Devices 63, 5004\u20135011 (2016).","journal-title":"IEEE Trans. Electron Devices"},{"key":"4992_CR26","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1038\/nnano.2017.83","volume":"12","author":"PM Sheridan","year":"2017","unstructured":"Sheridan, P. M. et al. Sparse coding with memristor networks. Nat. Nanotechnol. 12, 784\u2013789 (2017).","journal-title":"Nat. Nanotechnol."},{"key":"4992_CR27","doi-asserted-by":"publisher","first-page":"15199","DOI":"10.1038\/ncomms15199","volume":"8","author":"P Yao","year":"2017","unstructured":"Yao, P. et al. Face classification using electronic synapses. Nat. Commun. 8, 15199 (2017).","journal-title":"Nat. Commun."},{"key":"4992_CR28","unstructured":"Banbury, C. et al. MLPerf tiny benchmark. In Conference on Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks (2021)."},{"key":"4992_CR29","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1109\/TVLSI.2021.3063543","volume":"29","author":"S Roy","year":"2021","unstructured":"Roy, S., Sridharan, S., Jain, S. & Raghunathan, A. TxSim: modeling training of deep neural networks on resistive crossbar systems. IEEE Trans. Very Large Scale Integr. Syst. 29, 730\u2013738 (2021).","journal-title":"IEEE Trans. Very Large Scale Integr. Syst."},{"key":"4992_CR30","doi-asserted-by":"crossref","unstructured":"Yang, T. J. & Sze, V. Design considerations for efficient deep neural networks on processing-in-memory accelerators. In International Electron Devices Meeting (IEDM), Technical Digest 22.1.1\u201322.1.4 (IEEE, 2019).","DOI":"10.1109\/IEDM19573.2019.8993662"},{"key":"4992_CR31","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y Lecun","year":"2015","unstructured":"Lecun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015).","journal-title":"Nature"},{"key":"4992_CR32","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997).","journal-title":"Neural Comput."},{"key":"4992_CR33","unstructured":"Koller, D. & Friedman, N. Probabilistic Graphical Models: Principles and Techniques (Adaptive Computation and Machine Learning series) (MIT Press, 2009)."},{"key":"4992_CR34","doi-asserted-by":"crossref","unstructured":"Su, J. W. et al. A 28nm 64Kb inference-training two-way transpose multibit 6T SRAM compute-in-memory macro for AI edge chips. In IEEE International Solid-State Circuits Conference (ISSCC), Digest of Technical Papers 240\u2013242 (IEEE, 2020).","DOI":"10.1109\/ISSCC19947.2020.9062949"},{"key":"4992_CR35","doi-asserted-by":"crossref","unstructured":"Guo, R. et al. A 5.1pJ\/neuron 127.3us\/inference RNN-based speech recognition processor using 16 computing-in-memory SRAM macros in 65nm CMOS. In IEEE Symposium on VLSI Circuits, Digest of Technical Papers 120\u2013121 (IEEE, 2019).","DOI":"10.23919\/VLSIC.2019.8778028"},{"key":"4992_CR36","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1038\/s41928-018-0023-2","volume":"1","author":"Z Wang","year":"2018","unstructured":"Wang, Z. et al. Fully memristive neural networks for pattern classification with unsupervised learning. Nat. Electron. 1, 137\u2013145 (2018).","journal-title":"Nat. Electron."},{"key":"4992_CR37","doi-asserted-by":"crossref","unstructured":"Shafiee, A. et al. ISAAC: a convolutional neural network accelerator with in-situ analog arithmetic in crossbars. In Proc. 2016 43rd International Symposium on Computer Architecture (ISCA) 14-26 (IEEE\/ACM, 2016).","DOI":"10.1109\/ISCA.2016.12"},{"key":"4992_CR38","doi-asserted-by":"crossref","unstructured":"Ankit, A. et al. PUMA: a programmable ultra-efficient memristor-based accelerator for machine learning inference. In International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 715\u2013731 (ACM, 2019).","DOI":"10.1145\/3297858.3304049"},{"key":"4992_CR39","doi-asserted-by":"crossref","unstructured":"Wan, W. et al. A voltage-mode sensing scheme with differential-row weight mapping for energy-efficient RRAM-based in-memory computing. In Symposium on VLSI Technology, Digest of Technical Papers (IEEE, 2020).","DOI":"10.1109\/VLSITechnology18217.2020.9265066"},{"key":"4992_CR40","doi-asserted-by":"crossref","unstructured":"Murmann, B. Digitally assisted data converter design. In European Conference on Solid-State Circuits (ESSCIRC) 24\u201331 (IEEE, 2013).","DOI":"10.1109\/ESSCIRC.2013.6649063"},{"key":"4992_CR41","unstructured":"Zhao, M. et al. Investigation of statistical retention of filamentary analog RRAM for neuromophic computing. In International Electron Devices Meeting (IEDM), Technical Digest 39.4.1\u201339.4.4 (IEEE, 2018)."},{"key":"4992_CR42","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1088\/0957-4484\/23\/7\/075201","volume":"23","author":"F Alibart","year":"2012","unstructured":"Alibart, F., Gao, L., Hoskins, B. D. & Strukov, D. B. High precision tuning of state for memristive devices by adaptable variation-tolerant algorithm. Nanotechnology 23, 762\u2013775 (2012).","journal-title":"Nanotechnology"},{"key":"4992_CR43","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) 770\u2013778 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"4992_CR44","unstructured":"Cauwenberghs, G. & Bayoumi, M. A. Learning on Silicon\u2014Adaptive VLSI Neural Systems (Kluwer Academic, 1999)."},{"key":"4992_CR45","doi-asserted-by":"crossref","unstructured":"Hornik, K., Stinchcombe, M. & White, H. Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359\u2013366 (1989).","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"4992_CR46","unstructured":"Choi, J. et al. PACT: parameterized clipping activation for quantized neural networks. Preprint at https:\/\/arxiv.org\/abs\/1805.06085 (2018)."},{"key":"4992_CR47","doi-asserted-by":"publisher","unstructured":"Wan, W. weierwan\/Neurram_48core: Initial Release (Version 1.0) [Computer software]. Zenodo https:\/\/doi.org\/10.5281\/zenodo.6558399 (2022).","DOI":"10.5281\/zenodo.6558399"},{"key":"4992_CR48","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1038\/s41586-021-04196-6","volume":"601","author":"S Jung","year":"2022","unstructured":"Jung, S. et al. A crossbar array of magnetoresistive memory devices for in-memory computing. Nature 601, 211\u2013216 (2022).","journal-title":"Nature"},{"key":"4992_CR49","unstructured":"Jerry, M. et al. Ferroelectric FET analog synapse for acceleration of deep neural network training. In International Electron Devices Meeting (IEDM), Technical Digest 6.2.1\u20136.2.4 (IEEE, 2018)."},{"key":"4992_CR50","doi-asserted-by":"publisher","first-page":"5147","DOI":"10.1109\/TED.2019.2950595","volume":"66","author":"Z Jiang","year":"2019","unstructured":"Jiang, Z. et al. Next-generation ultrahigh-density 3-D vertical resistive switching memory (VRSM)\u2013Part II: design guidelines for device, array, and architecture. IEEE Trans. Electron Devices 66, 5147\u20135154 (2019).","journal-title":"IEEE Trans. Electron Devices"},{"key":"4992_CR51","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1109\/72.485671","volume":"7","author":"G Cauwenberghs","year":"1996","unstructured":"Cauwenberghs, G. An analog VLSI recurrent neural network learning a continuous-time trajectory. IEEE Trans. Neural Netw. 7, 346\u2013361 (1996).","journal-title":"IEEE Trans. Neural Netw."},{"key":"4992_CR52","doi-asserted-by":"crossref","unstructured":"Wu, W. et al. A methodology to improve linearity of analog RRAM for neuromorphic computing. In Symposium on VLSI Technology, Digest of Technical Papers 103\u2013104 (IEEE, 2018).","DOI":"10.1109\/VLSIT.2018.8510690"},{"key":"4992_CR53","doi-asserted-by":"crossref","unstructured":"Ji, Y. et al. FPSA: a full system stack solution for reconfigurable ReRAM-based NN accelerator architecture. In International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) 733\u2013747 (ACM, 2019).","DOI":"10.1145\/3297858.3304048"},{"key":"4992_CR54","unstructured":"Esser, S. K., Mckinstry, J. L., Bablani, D., Appuswamy, R. & Modha, D. S. Learned step size quantization. In International Conference on Learning Representations (ICLR) (2020)."},{"key":"4992_CR55","doi-asserted-by":"crossref","unstructured":"Jung, S. et al. Learning to quantize deep networks by optimizing quantization intervals with task loss. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 4345\u20134354 (IEEE\/CVF, 2019).","DOI":"10.1109\/CVPR.2019.00448"},{"key":"4992_CR56","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/JSSC.2013.2239005","volume":"48","author":"D Stepanovic","year":"2013","unstructured":"Stepanovic, D. & Nikolic, B. A 2.8 GS\/s 44.6 mW time-interleaved ADC achieving 50.9 dB SNDR and 3 dB effective resolution bandwidth of 1.5 GHz in 65 nm CMOS. IEEE J. Solid State Circuits 48, 971\u2013982 (2013).","journal-title":"IEEE J. Solid State Circuits"},{"key":"4992_CR57","doi-asserted-by":"publisher","first-page":"2236","DOI":"10.1109\/TCSI.2014.2332264","volume":"61","author":"V Tripathi","year":"2014","unstructured":"Tripathi, V. & Murmann, B. Mismatch characterization of small metal fringe capacitors. IEEE Trans. Circuits Syst. I Regul. Pap. 61, 2236\u20132242 (2014).","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"4992_CR58","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1109\/JSSC.2016.2616357","volume":"52","author":"YH Chen","year":"2017","unstructured":"Chen, Y. H., Krishna, T., Emer, J. S. & Sze, V. Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks. IEEE J. Solid State Circuits 52, 127\u2013138 (2017).","journal-title":"IEEE J. Solid State Circuits"},{"key":"4992_CR59","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1109\/JSSC.2019.2960488","volume":"55","author":"B Zimmer","year":"2020","unstructured":"Zimmer, B. et al. A 0.32-128 TOPS, scalable multi-chip-module-based deep neural network inference accelerator with ground-referenced signaling in 16 nm. IEEE J. Solid State Circuits 55, 920\u2013932 (2020).","journal-title":"IEEE J. Solid State Circuits"},{"key":"4992_CR60","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1109\/JSSC.2018.2865489","volume":"54","author":"J Lee","year":"2019","unstructured":"Lee, J. et al. UNPU: an energy-efficient deep neural network accelerator with fully variable weight bit precision. IEEE J. Solid State Circuits 54, 173\u2013185 (2019).","journal-title":"IEEE J. Solid State Circuits"},{"key":"4992_CR61","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/s41586-019-1424-8","volume":"572","author":"J Pei","year":"2019","unstructured":"Pei, J. et al. Towards artificial general intelligence with hybrid Tianjic chip architecture. Nature 572, 106\u2013111 (2019).","journal-title":"Nature"},{"key":"4992_CR62","unstructured":"Murmann, B. ADC Performance Survey 1997\u20132021 (2021); https:\/\/web.stanford.edu\/~murmann\/adcsurvey.html"}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41586-022-04992-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-022-04992-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-022-04992-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T23:06:18Z","timestamp":1727823978000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41586-022-04992-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,17]]},"references-count":62,"journal-issue":{"issue":"7923","published-print":{"date-parts":[[2022,8,18]]}},"alternative-id":["4992"],"URL":"https:\/\/doi.org\/10.1038\/s41586-022-04992-8","relation":{},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,17]]},"assertion":[{"value":"27 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}