F. Carletti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
F. Carletti has a total of 22 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
4 shared publications - Matteo Farronato
Informazione e Bioingegneria (DEIB) Politecnico di Milano and IU.NET
4 shared publications - Matteo Porzani
Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano and IU.NET, Milan, Italy
2 shared publications S. Ricci
Politecnico di Milano, IU.NET
2 shared publicationsA. Pirovano
Micron Technology Inc., Vimercate, Italy
1 shared publicationC. F. Hsu
Taiwan Semiconductor Manufacturing Company, Corporate Research, Hsinchu, Taiwan
1 shared publication
Latest Publications
- Open Access
- 10 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 73 (1) , 325-331
High-Accuracy, High-Performance In-Memory Computing With High-Resistance Spin-Orbit Torque (SOT) Magnetic Memory
In-memory computing (IMC) has emerged as a promising solution for artificial intelligence (AI) accelerators due to the reduced data movement and improved parallelism in the crosspoint array. However, IMC faces several limitations such as the device variations affecting the computing accuracy, the area- and energy-consuming peripheral circuitry, and the time-consuming high-voltage program-verify operations of the nonvolatile memory (NVM). In addition, the relatively large summation currents cause IR drop within the array, leading to further loss of accuracy. To overcome these issues, this work presents 1-bit quantized networks based on spin-orbit-torque magnetoresistive random access-memory (SOT-MRAM) with high resistance–area (RA) product. We provide a detailed statistical characterization of SOT-MRAM arrays and develop quantization-aware training of various neural networks. Our results indicate that SOT-MRAM enables: 1) high inference accuracy, thanks to excellent uniformity; 2) negligible input-dependent IR drop nonlinearity, thanks to high resistance; and 3) high-speed, low-power reconfiguration, thanks to fast device programming. These results support high-RA SOT-MRAM for digital-like and reconfigurable IMC accelerators of edge AI.
- 10 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 73 (1) , 325-331
Open AccessHigh-Accuracy, High-Performance In-Memory Computing With High-Resistance Spin-Orbit Torque (SOT) Magnetic Memory
In-memory computing (IMC) has emerged as a promising solution for artificial intelligence (AI) accelerators due to the reduced data movement and improved parallelism in the crosspoint array. However, IMC faces several limitations such as the device variations affecting the computing accuracy, the area- and energy-consuming peripheral circuitry, and the time-consuming high-voltage program-verify operations of the nonvolatile memory (NVM). In addition, the relatively large summation currents cause IR drop within the array, leading to further loss of accuracy. To overcome these issues, this work presents 1-bit quantized networks based on spin-orbit-torque magnetoresistive random access-memory (SOT-MRAM) with high resistance–area (RA) product. We provide a detailed statistical characterization of SOT-MRAM arrays and develop quantization-aware training of various neural networks. Our results indicate that SOT-MRAM enables: 1) high inference accuracy, thanks to excellent uniformity; 2) negligible input-dependent IR drop nonlinearity, thanks to high resistance; and 3) high-speed, low-power reconfiguration, thanks to fast device programming. These results support high-RA SOT-MRAM for digital-like and reconfigurable IMC accelerators of edge AI.
- Open Access
- 3 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 73 (1) , 264-270
3-D Crosspoint (3DXP) Memory Arrays With Subthreshold Operation for Low-Energy, High-Accuracy Neural Network Accelerators
In-memory computing (IMC) has been identified as a promising paradigm for hardware neural network accelerators thanks to the reduced data movement and improved parallelism. A known issue of IMC is the relatively large summation current within the memory array, which causes energy inefficiency and computing inaccuracy due to IR drop. An additional burden is the area and energy-demanding readout circuits, which limit the density and energy efficiency of computing. This work reports a hardware demonstration of IMC using 3-D crosspoint (3DXP) arrays of ovonic threshold switches and phase change memories (PCMs). We demonstrate a precise program–verify (PV) algorithm optimized for the subthreshold regime, allowing for a reduction of the operating currents by more than two orders of magnitude with respect to the conventional 3DXP technology. We experimentally demonstrate vector–vector multiplication (VVM) and feature extractions, which are key operations of convolutional neural networks (CNNs). Simulation study of LeNet5 with binary and ternary quantization, including device variability, 1/f noise, and drift, demonstrates high accuracy and low-energy inference thanks to precise programming, subthreshold operation, and careful drift compensation.
- 3 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 73 (1) , 264-270
Open Access3-D Crosspoint (3DXP) Memory Arrays With Subthreshold Operation for Low-Energy, High-Accuracy Neural Network Accelerators
In-memory computing (IMC) has been identified as a promising paradigm for hardware neural network accelerators thanks to the reduced data movement and improved parallelism. A known issue of IMC is the relatively large summation current within the memory array, which causes energy inefficiency and computing inaccuracy due to IR drop. An additional burden is the area and energy-demanding readout circuits, which limit the density and energy efficiency of computing. This work reports a hardware demonstration of IMC using 3-D crosspoint (3DXP) arrays of ovonic threshold switches and phase change memories (PCMs). We demonstrate a precise program–verify (PV) algorithm optimized for the subthreshold regime, allowing for a reduction of the operating currents by more than two orders of magnitude with respect to the conventional 3DXP technology. We experimentally demonstrate vector–vector multiplication (VVM) and feature extractions, which are key operations of convolutional neural networks (CNNs). Simulation study of LeNet5 with binary and ternary quantization, including device variability, 1/f noise, and drift, demonstrates high accuracy and low-energy inference thanks to precise programming, subthreshold operation, and careful drift compensation.
- 21 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 71 (5) , 3246-3251
Programming Characteristics of Electrochemical Random Access Memory (ECRAM)—Part II: Physics-Based Modeling
Modeling of electrochemical random access memory (ECRAM) is essential to predict device performance and scaling, and provide simulation tools for in-memory computing (IMC) circuits. This article addresses physical modeling of ECRAM capable of describing both the quasistatic characteristics and the pulsed programming dynamics of the device. Channel potentiation and depression are described in terms of nonlinear drift diffusion of mobile oxygen vacancies in the layers of the device. An analytical compact model for pulsed channel potentiation is derived from the physical picture to support circuit simulations. Simulation results are extensively compared with experimental data. The model accounts for device potentiation characteristics and accurately describes second-order effects such as saturation and nonlinearity deviations.
- 21 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 71 (5) , 3246-3251
Programming Characteristics of Electrochemical Random Access Memory (ECRAM)—Part II: Physics-Based Modeling
Modeling of electrochemical random access memory (ECRAM) is essential to predict device performance and scaling, and provide simulation tools for in-memory computing (IMC) circuits. This article addresses physical modeling of ECRAM capable of describing both the quasistatic characteristics and the pulsed programming dynamics of the device. Channel potentiation and depression are described in terms of nonlinear drift diffusion of mobile oxygen vacancies in the layers of the device. An analytical compact model for pulsed channel potentiation is derived from the physical picture to support circuit simulations. Simulation results are extensively compared with experimental data. The model accounts for device potentiation characteristics and accurately describes second-order effects such as saturation and nonlinearity deviations.