TY - GEN A1 - Baroni, Andrea A1 - Zambelli, Cristian A1 - Olivo, Piero A1 - Pérez, Eduardo A1 - Wenger, Christian A1 - Ielmini, Daniele T1 - Tackling the Low Conductance State Drift through Incremental Reset and Verify in RRAM Arrays T2 - 2021 IEEE International Integrated Reliability Workshop (IIRW), South Lake Tahoe, CA, USA, 10 December 2021 N2 - Resistive switching memory (RRAM) is a promising technology for highly efficient computing scenarios. RRAM arrays enabled the acceleration of neural networks for artificial intelligence and the creation of In-Memory Computing circuits. However, the arrays are affected by several issues materializing in conductance variations that might cause severe performance degradation in those applications. Among those, one is related to the drift of the low conductance states appearing immediately at the end of program and verify algorithms that are fundamental for an accurate Multi-level conductance operation. In this work, we tackle the issue by developing an Incremental Reset and Verify technique showing enhanced variability and reliability features compared with a traditional refresh-based approach. KW - RRAM KW - resistive switching KW - neural network Y1 - 2021 SN - 978-1-6654-1794-5 SN - 978-1-6654-1795-2 U6 - https://doi.org/10.1109/IIRW53245.2021.9635613 SN - 2374-8036 PB - Institute of Electrical and Electronics Engineers (IEEE) ER - TY - GEN A1 - Mannocci, Piergiulio A1 - Baroni, Andrea A1 - Melacarne, Enrico A1 - Zambelli, Cristian A1 - Olivo, Piero A1 - Pérez, Eduardo A1 - Wenger, Christian A1 - Ielmini, Daniele T1 - In-Memory Principal Component Analysis by Crosspoint Array of Rresistive Switching Memory T2 - IEEE Nanotechnology Magazine N2 - In Memory Computing (IMC) is one of the most promising candidates for data-intensive computing accelerators of machine learning (ML). A key ML algorithm for dimensionality reduction and classification is principal component analysis (PCA), which heavily relies on matrixvector multiplications (MVM) for which classic von Neumann architectures are not optimized. Here, we provide the experimental demonstration of a new IMCbased PCA algorithm based on power iteration and deflation executed in a 4-kbit array of resistive switching random-access memory (RRAM). The classification accuracy of the Wisconsin Breast Cancer data set reaches 95.43%, close to floatingpoint implementation. Our simulations indicate a 250× improvement in energy efficiency compared to commercial GPUs, thus supporting IMC for energy-efficient ML in modern data-intensive computing. KW - RRAM KW - Multilevel switching KW - neural network Y1 - 2022 U6 - https://doi.org/10.1109/MNANO.2022.3141515 SN - 1932-4510 VL - 16 IS - 2 SP - 4 EP - 13 ER - TY - GEN A1 - Glukhov, Artem A1 - Milo, Valerio A1 - Baroni, Andrea A1 - Lepri, Nicola A1 - Zambelli, Cristian A1 - Olivo, Piero A1 - Pérez, Eduardo A1 - Wenger, Christian A1 - Ielmini, Daniele T1 - Statistical model of program/verify algorithms in resistive-switching memories for in-memory neural network accelerators T2 - 2022 IEEE International Reliability Physics Symposium (IRPS) N2 - Resistive-switching random access memory (RRAM) is a promising technology for in-memory computing (IMC) to accelerate training and inference of deep neural networks (DNNs). This work presents the first physics-based statistical model describing (i) multilevel RRAM device program/verify (PV) algorithms by controlled set transition, (ii) the stochastic cycle-to-cycle (C2C) and device-to-device (D2D) variations within the array, and (iii) the impact of such imprecisions on the accuracy of DNN accelerators. The model can handle the full chain from RRAM materials/device parameters to the DNN performance, thus providing a valuable tool for device/circuit codesign of hardware DNN accelerators. KW - RRAM KW - Multilevel switching KW - neural network Y1 - 2022 SN - 978-1-6654-7950-9 SN - 978-1-6654-7951-6 U6 - https://doi.org/10.1109/IRPS48227.2022.9764497 SN - 2473-2001 SP - 3C.3-1 EP - 3C.3-7 PB - Institute of Electrical and Electronics Engineers (IEEE) ER - TY - GEN A1 - Baroni, Andrea A1 - Glukhov, Artem A1 - Pérez, Eduardo A1 - Wenger, Christian A1 - Ielmini, Daniele A1 - Olivo, Piero A1 - Zambelli, Cristian T1 - Low Conductance State Drift Characterization and Mitigation in Resistive Switching Memories (RRAM) for Artificial Neural Networks T2 - IEEE Transactions on Device and Materials Reliability N2 - The crossbar structure of Resistive-switching random access memory (RRAM) arrays enabled the In-Memory Computing circuits paradigm, since they imply the native acceleration of a crucial operations in this scenario, namely the Matrix-Vector-Multiplication (MVM). However, RRAM arrays are affected by several issues materializing in conductance variations that might cause severe performance degradation. A critical one is related to the drift of the low conductance states appearing immediately at the end of program and verify algorithms that are mandatory for an accurate multi-level conductance operation. In this work, we analyze the benefits of a new programming algorithm that embodies Set and Reset switching operations to achieve better conductance control and lower variability. Data retention analysis performed with different temperatures for 168 hours evidence its superior performance with respect to standard programming approach. Finally, we explored the benefits of using our methodology at a higher abstraction level, through the simulation of an Artificial Neural Network for image recognition task (MNIST dataset). The accuracy achieved shows higher performance stability over temperature and time. KW - RRAM KW - neural network KW - Multilevel switching Y1 - 2022 U6 - https://doi.org/10.1109/TDMR.2022.3182133 SN - 1530-4388 VL - 22 IS - 3 SP - 340 EP - 347 ER - TY - GEN A1 - Glukhov, Artem A1 - Lepri, Nicola A1 - Milo, Valerio A1 - Baroni, Andrea A1 - Zambelli, Cristian A1 - Olivo, Piero A1 - Pérez, Eduardo A1 - Wenger, Christian A1 - Ielmini, Daniele T1 - End-to-end modeling of variability-aware neural networks based on resistive-switching memory arrays T2 - Proc. 30th IFIP/IEEE International Conference on Very Large Scale Integration (VLSI-SoC 2022) N2 - Resistive-switching random access memory (RRAM) is a promising technology that enables advanced applications in the field of in-memory computing (IMC). By operating the memory array in the analogue domain, RRAM-based IMC architectures can dramatically improve the energy efficiency of deep neural networks (DNNs). However, achieving a high inference accuracy is challenged by significant variation of RRAM conductance levels, which can be compensated by (i) advanced programming techniques and (ii) variability-aware training (VAT) algorithms. In both cases, however, detailed knowledge and accurate physics-based statistical models of RRAM are needed to develop programming and VAT methodologies. This work presents an end-to-end approach to the development of highly-accurate IMC circuits with RRAM, encompassing the device modeling, the precise programming algorithm, and the VAT simulations to maximize the DNN classification accuracy in presence of conductance variations. KW - RRAM KW - HfO2 KW - neural network KW - memristive switching Y1 - 2022 U6 - https://doi.org/10.1109/VLSI-SoC54400.2022.9939653 SP - 1 EP - 5 ER -