Artem Glukhov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Artem Glukhov has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Daniele Ielmini
Dipartimento di Elettronica e Informazione and IU.NET, Politecnico di Milano, Milano, Italy
8 shared publications - Nicola Lepri
Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Politecnico di Milano and IU.NET
5 shared publications - Piergiulio Mannocci
Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milan, Italy
4 shared publications - Christian Wenger
IHPLeibniz-Institut fr innovative Mikroelektronik, Frankfurt (Oder), Germany
3 shared publications - Cristian Zambelli
Università degli Studi di Ferrara
3 shared publications - Andrea Baroni
IHPLeibniz-Institut fr innovative Mikroelektronik, Frankfurt (Oder), Germany
2 shared publications
Latest Publications
- Open Access
- 25 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 71 (12) , 7447-7453
Differential Phase Change Memory (PCM) Cell for Drift-Compensated In-Memory Computing
Phase change memory (PCM) is a scalable, reliable, and robust technology for embedded and stand-alone memory device. PCM has also been extensively demonstrated for analog in-memory computing (IMC), which allows energy-efficient acceleration of AI workloads. High-temperature data retention requirements in PCM devices are met by Ge-rich GeSbTe (GST), which allows to satisfy consumer-and automotive-grade reliability specifications. However, Ge-rich GST suffers from set state drift, which affects the stability of the multilevel cell (MLC), hence the accuracy of IMC. This work presents: 1) a novel multilevel programming algorithm from weak reset state to prevent conductance instabilities; 2) a drift compensation scheme through a differential weight approach, validated on matrix-vector multiplication (MVM) after high-temperature annealing; and 3) a detailed study of the impact of PCM variability and weight quantization on hardware implementation of neural networks.
- 25 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 71 (12) , 7447-7453
Open AccessDifferential Phase Change Memory (PCM) Cell for Drift-Compensated In-Memory Computing
Phase change memory (PCM) is a scalable, reliable, and robust technology for embedded and stand-alone memory device. PCM has also been extensively demonstrated for analog in-memory computing (IMC), which allows energy-efficient acceleration of AI workloads. High-temperature data retention requirements in PCM devices are met by Ge-rich GeSbTe (GST), which allows to satisfy consumer-and automotive-grade reliability specifications. However, Ge-rich GST suffers from set state drift, which affects the stability of the multilevel cell (MLC), hence the accuracy of IMC. This work presents: 1) a novel multilevel programming algorithm from weak reset state to prevent conductance instabilities; 2) a drift compensation scheme through a differential weight approach, validated on matrix-vector multiplication (MVM) after high-temperature annealing; and 3) a detailed study of the impact of PCM variability and weight quantization on hardware implementation of neural networks.
- 6 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 71 (3) , 1900-1906
Compact Modeling and Mitigation of Parasitics in Crosspoint Accelerators of Neural Networks
In-memory computing (IMC) can accelerate data-intensive tasks, such as matrix-vector multiplication (MVM) or artificial neural networks (ANNs) inference, by means of the crosspoint memory array, allowing to reduce time and energy consumption. IMC accuracy, however, is affected by nonidealities, such as variability of the conductive weights or IR drop along wires due to parasitic resistances, whose impact steeply increases with the increase of array size. This work proposes a compact model to assess the impact of nonidealities for various circuital implementations, together with architectural schemes for their mitigation based on replicated arrays. The proposed mitigation techniques allow to restore the ANN accuracy from 72.7% to 94.9%, close to the software accuracy of 96.9%, in view of an increased area and energy consumption.
- 6 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 71 (3) , 1900-1906
Compact Modeling and Mitigation of Parasitics in Crosspoint Accelerators of Neural Networks
In-memory computing (IMC) can accelerate data-intensive tasks, such as matrix-vector multiplication (MVM) or artificial neural networks (ANNs) inference, by means of the crosspoint memory array, allowing to reduce time and energy consumption. IMC accuracy, however, is affected by nonidealities, such as variability of the conductive weights or IR drop along wires due to parasitic resistances, whose impact steeply increases with the increase of array size. This work proposes a compact model to assess the impact of nonidealities for various circuital implementations, together with architectural schemes for their mitigation based on replicated arrays. The proposed mitigation techniques allow to restore the ANN accuracy from 72.7% to 94.9%, close to the software accuracy of 96.9%, in view of an increased area and energy consumption.
- Open Access
- 17 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of the Electron Devices Society
- Vol. 11, 587-601
In-Memory Computing for Machine Learning and Deep Learning
In-memory computing (IMC) aims at executing numerical operations via physical processes, such as current summation and charge collection, thus accelerating common computing tasks including the matrix-vector multiplication. While extremely promising for memory-intensive processing such as machine learning and deep learning, the IMC design and realization must face significant challenges due to device and circuit nonidealities. This work provides an overview of the research trends and options for IMC-based implementations of deep learning accelerators with emerging memory technologies. The device technologies, the computing primitives, and the digital/analog/mixed design approaches are presented. Finally, the major device issues and metrics for IMC are discussed and benchmarked.
- 17 April 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of the Electron Devices Society
- Vol. 11, 587-601
Open AccessIn-Memory Computing for Machine Learning and Deep Learning
In-memory computing (IMC) aims at executing numerical operations via physical processes, such as current summation and charge collection, thus accelerating common computing tasks including the matrix-vector multiplication. While extremely promising for memory-intensive processing such as machine learning and deep learning, the IMC design and realization must face significant challenges due to device and circuit nonidealities. This work provides an overview of the research trends and options for IMC-based implementations of deep learning accelerators with emerging memory technologies. The device technologies, the computing primitives, and the digital/analog/mixed design approaches are presented. Finally, the major device issues and metrics for IMC are discussed and benchmarked.
- 20 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Device and Materials Reliability
- Vol. 23 (3) , 328-336
Process-Voltage-Temperature Variations Assessment in Energy-Aware Resistive RAM-Based FPGAs
Resistive Random Access Memory (RRAM) technology holds promises to improve the Field Programmable Gate Array (FPGA) performance, reduce the area footprint, and dramatically lower run-time energy requirements compared to the state-of-the-art CMOS-based products. However, the integration of RRAM in FPGAs is hindered by the high programming power consumption and by non-ideal behaviors of the device due to its stochastic nature that may overshadow the benefits in normal operation mode. To cope with these challenges, optimized programming strategies have to be investigated. In this work, we explore the impact that different procedures to set the device have on the run-time performance. Process, voltage, and temperature (PVT) variations as well as time-dependent drift effect of the RRAM device are considered in the assessment of 4T1R MUX designs characteristics. The comparison with tradition CMOS implementations reveals how the choice of the target resistive state and the programming algorithm are key design aspects to reduce the run-time delay and energy metrics, while at the same time improving the robustness against the different sources of variations.
- 20 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Device and Materials Reliability
- Vol. 23 (3) , 328-336
Process-Voltage-Temperature Variations Assessment in Energy-Aware Resistive RAM-Based FPGAs
Resistive Random Access Memory (RRAM) technology holds promises to improve the Field Programmable Gate Array (FPGA) performance, reduce the area footprint, and dramatically lower run-time energy requirements compared to the state-of-the-art CMOS-based products. However, the integration of RRAM in FPGAs is hindered by the high programming power consumption and by non-ideal behaviors of the device due to its stochastic nature that may overshadow the benefits in normal operation mode. To cope with these challenges, optimized programming strategies have to be investigated. In this work, we explore the impact that different procedures to set the device have on the run-time performance. Process, voltage, and temperature (PVT) variations as well as time-dependent drift effect of the RRAM device are considered in the assessment of 4T1R MUX designs characteristics. The comparison with tradition CMOS implementations reveals how the choice of the target resistive state and the programming algorithm are key design aspects to reduce the run-time delay and energy metrics, while at the same time improving the robustness against the different sources of variations.
- Top Cited PapersOpen Access
- 14 February 2023
- Published by AIP Publishing in APL Machine Learning
- Vol. 1 (1) , 010902
In-memory computing with emerging memory devices: Status and outlook
In-memory computing (IMC) has emerged as a new computing paradigm able to alleviate or suppress the memory bottleneck, which is the major concern for energy efficiency and latency in modern digital computing. While the IMC concept is simple and promising, the details of its implementation cover a broad range of problems and solutions, including various memory technologies, circuit topologies, and programming/processing algorithms. This Perspective aims at providing an orientation map across the wide topic of IMC. First, the memory technologies will be presented, including both conventional complementary metal-oxide-semiconductor-based and emerging resistive/memristive devices. Then, circuit architectures will be considered, describing their aim and application. Circuits include both popular crosspoint arrays and other more advanced structures, such as closed-loop memory arrays and ternary content-addressable memory. The same circuit might serve completely different applications, e.g., a crosspoint array can be used for accelerating matrix-vector multiplication for forward propagation in a neural network and outer product for backpropagation training. The different algorithms and memory properties to enable such diversification of circuit functions will be discussed. Finally, the main challenges and opportunities for IMC will be presented.
- 14 February 2023
- Published by AIP Publishing in APL Machine Learning
- Vol. 1 (1) , 010902
Top Cited PapersOpen AccessIn-memory computing with emerging memory devices: Status and outlook
In-memory computing (IMC) has emerged as a new computing paradigm able to alleviate or suppress the memory bottleneck, which is the major concern for energy efficiency and latency in modern digital computing. While the IMC concept is simple and promising, the details of its implementation cover a broad range of problems and solutions, including various memory technologies, circuit topologies, and programming/processing algorithms. This Perspective aims at providing an orientation map across the wide topic of IMC. First, the memory technologies will be presented, including both conventional complementary metal-oxide-semiconductor-based and emerging resistive/memristive devices. Then, circuit architectures will be considered, describing their aim and application. Circuits include both popular crosspoint arrays and other more advanced structures, such as closed-loop memory arrays and ternary content-addressable memory. The same circuit might serve completely different applications, e.g., a crosspoint array can be used for accelerating matrix-vector multiplication for forward propagation in a neural network and outer product for backpropagation training. The different algorithms and memory properties to enable such diversification of circuit functions will be discussed. Finally, the main challenges and opportunities for IMC will be presented.
- 10 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Device and Materials Reliability
- Vol. 22 (3) , 340-347
Low Conductance State Drift Characterization and Mitigation in Resistive Switching Memories (RRAM) for Artificial Neural Networks
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.
- 10 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Device and Materials Reliability
- Vol. 22 (3) , 340-347
Low Conductance State Drift Characterization and Mitigation in Resistive Switching Memories (RRAM) for Artificial Neural Networks
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.
- 26 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 69 (3) , 1575-1581
Modeling and Compensation of IR Drop in Crosspoint Accelerators of Neural Networks
In-memory computing (IMC) has the potential of accelerating data-intensive computing tasks, such as inference and training of neural networks, by the matrix vector multiplication (MVM) in the crosspoint array. As the array size increases, however, a significant problem arises due to the parasitic IR drop at row and column lines. Understanding and compensating IR drop is essential to enable high-density accelerators of MVM. This work presents an analytical model for the IR drop and a numerical algorithm capable of accelerating the nodal analysis of crosspoint arrays up to five orders of magnitude with respect to SPICE analysis. The numerical algorithm is used to study the impact of array size, data density, device/wire resistance, and nonlinearity on the IR drop and the related loss of accuracy in IMC. We also derive two simple compensation schemes and an architectural solution for the mitigation of IR drop that are able to increase the accuracy of neural networks from 59% up to 96.6%, compared to an ideal accuracy of 97%.
- 26 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 69 (3) , 1575-1581
Modeling and Compensation of IR Drop in Crosspoint Accelerators of Neural Networks
In-memory computing (IMC) has the potential of accelerating data-intensive computing tasks, such as inference and training of neural networks, by the matrix vector multiplication (MVM) in the crosspoint array. As the array size increases, however, a significant problem arises due to the parasitic IR drop at row and column lines. Understanding and compensating IR drop is essential to enable high-density accelerators of MVM. This work presents an analytical model for the IR drop and a numerical algorithm capable of accelerating the nodal analysis of crosspoint arrays up to five orders of magnitude with respect to SPICE analysis. The numerical algorithm is used to study the impact of array size, data density, device/wire resistance, and nonlinearity on the IR drop and the related loss of accuracy in IMC. We also derive two simple compensation schemes and an architectural solution for the mitigation of IR drop that are able to increase the accuracy of neural networks from 59% up to 96.6%, compared to an ideal accuracy of 97%.
- 2 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 68 (8) , 3832-3837
Accurate Program/Verify Schemes of Resistive Switching Memory (RRAM) for In-Memory Neural Network Circuits
Resistive switching memory (RRAM) is a promising technology for embedded memory and its application in computing. In particular, RRAM arrays can provide a convenient primitive for matrix-vector multiplication (MVM) with strong impact on the acceleration of neural networks for artificial intelligence (AI). At the same time, RRAM is affected by intrinsic conductance variations, which might cause degradation of accuracy in AI inference hardware. This work provides a detailed study of the multilevel-cell (MLC) programming of RRAM for neural network applications. We compare three MLC programming schemes and discuss their variations in terms of the different slopes in the programming characteristics. We test the accuracy of a two-layer fully connected neural network (FC-NN) as a function of the MLC scheme, the number of weight levels, and the weight mapping configuration. We find a tradeoff between the FC-NN accuracy, size, and current consumption. This work highlights the importance of a holistic approach to AI accelerators encompassing the device properties, the overall circuit performance, and the AI application specifications.
- 2 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 68 (8) , 3832-3837
Accurate Program/Verify Schemes of Resistive Switching Memory (RRAM) for In-Memory Neural Network Circuits
Resistive switching memory (RRAM) is a promising technology for embedded memory and its application in computing. In particular, RRAM arrays can provide a convenient primitive for matrix-vector multiplication (MVM) with strong impact on the acceleration of neural networks for artificial intelligence (AI). At the same time, RRAM is affected by intrinsic conductance variations, which might cause degradation of accuracy in AI inference hardware. This work provides a detailed study of the multilevel-cell (MLC) programming of RRAM for neural network applications. We compare three MLC programming schemes and discuss their variations in terms of the different slopes in the programming characteristics. We test the accuracy of a two-layer fully connected neural network (FC-NN) as a function of the MLC scheme, the number of weight levels, and the weight mapping configuration. We find a tradeoff between the FC-NN accuracy, size, and current consumption. This work highlights the importance of a holistic approach to AI accelerators encompassing the device properties, the overall circuit performance, and the AI application specifications.