Combined HW/SW Drift and Variability Mitigation for PCM-Based Analog In-Memory Computing for Neural Network Applications
العنوان: | Combined HW/SW Drift and Variability Mitigation for PCM-Based Analog In-Memory Computing for Neural Network Applications |
---|---|
المؤلفون: | Alessio Antolini, Carmine Paolino, Francesco Zavalloni, Andrea Lico, Eleonora Franchi Scarselli, Mauro Mangia, Fabio Pareschi, Gianluca Setti, Riccardo Rovatti, Mattia Luigi Torres, Marcella Carissimi, Marco Pasotti |
المساهمون: | Alessio Antolini, Carmine Paolino, Francesco Zavalloni, Andrea Lico, Eleonora Franchi Scarselli, Mauro Mangia, Fabio Pareschi, Gianluca Setti, Riccardo Rovatti, Mattia Luigi Torres, Marcella Carissimi, Marco Pasotti |
المصدر: | IEEE Journal on Emerging and Selected Topics in Circuits and Systems. 13:395-407 |
بيانات النشر: | Institute of Electrical and Electronics Engineers (IEEE), 2023. |
سنة النشر: | 2023 |
مصطلحات موضوعية: | NoiseAware Training, Deep Neural Network (DNN), Phase-Change Memory (PCM), Drift Compensation, Noise-Aware Training, Analog In-memory Computing (AIMC), PhaseChange Memory (PCM), Electrical and Electronic Engineering |
الوصف: | Matrix-Vector Multiplications (MVMs) represent a heavy workload for both training and inference in Deep Neural Networks (DNNs) applications. Analog In-memory Computing (AIMC) systems based on Phase Change Memory (PCM) has been shown to be a valid competitor to enhance the energy efficiency of DNN accelerators. Although DNNs are quite resilient to computation inaccuracies, PCM non-idealities could strongly affect MVM operations precision, and thus the accuracy of DNNs. In this paper, a combined hardware and software solution to mitigate the impact of PCM non-idealities is presented. The drift of PCM cells conductance is compensated at the circuit level through the introduction of a conductance ratio at the core of the MVM computation. A model of the behaviour of PCM cells is employed to develop a device-aware training for DNNs and the accuracy is estimated in a CIFAR-10 classification task. This work is supported by a PCM-based AIMC prototype, designed in a 90-nm STMicroelectronics technology, and conceived to perform Multiply-and-Accumulate (MAC) computations, which are the kernel of MVMs. Results show that the MAC computation accuracy is around 95% even under the effect of cells drift. The use of a device-aware DNN training makes the networks less sensitive to weight variability, with a 15% increase in classification accuracy over a conventionally-trained Lenet-5 DNN, and a 36% gain when drift compensation is applied. |
وصف الملف: | ELETTRONICO |
تدمد: | 2156-3365 2156-3357 |
URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::11ada0cec13a2a0d4655f4b10b1524bb https://doi.org/10.1109/jetcas.2023.3241750 |
حقوق: | OPEN |
رقم الأكسشن: | edsair.doi.dedup.....11ada0cec13a2a0d4655f4b10b1524bb |
قاعدة البيانات: | OpenAIRE |
تدمد: | 21563365 21563357 |
---|