Using the IBM analog in-memory hardware acceleration kit for neural network training and inference - Supplementary Material

Analog In-Memory Computing (AIMC) is a promising approach to reduce the latency and energy consumption of Deep Neural Network (DNN) inference and training. However, the noisy and non-linear device characteristics and the non-ideal peripheral circuitry in AIMC chips require adapting DNNs to be deployed on such hardware to achieve equivalent accuracy to digital computing. In this Tutorial, we provide a deep dive into how such adaptations can be achieved and evaluated using the recently released IBM Analog Hardware Acceleration Kit (AIHWKit), freely available at https://github.com/IBM/aihwkit. AIHWKit is a Python library that simulates inference and training of DNNs using AIMC. We present an in-depth description of the AIHWKit design, functionality, and best practices to properly perform inference and training. We also present an overview of the Analog AI Cloud Composer, a platform that provides the benefits of using the AIHWKit simulation in a fully managed cloud setting along with physical AIMC hardware access, freely available at https://aihw-composer.draco.res.ibm.com. Finally, we show examples of how users can expand and customize AIHWKit for their own needs. This Tutorial is accompanied by comprehensive Jupyter Notebook code examples that can be run using AIHWKit, which can be downloaded from https://github.com/IBM/aihwkit/tree/master/notebooks/tutorial.模拟内存计算（Analog In-Memory Computing, AIMC）是一种极具前景的方法，可降低深度神经网络（Deep Neural Network, DNN）推理与训练的延迟与能耗。但AIMC芯片存在器件特性带噪声、非线性，以及外围电路非理想等问题，因此需要对DNN进行适配，才能在这类硬件上部署并达到与数字计算相当的精度。本教程深入阐述了如何借助近期发布的IBM模拟硬件加速套件（IBM Analog Hardware Acceleration Kit, AIHWKit）完成此类适配与性能评估，该套件可从https://github.com/IBM/aihwkit免费获取。AIHWKit是一款Python库，用于模拟基于AIMC的DNN推理与训练。我们将详细介绍AIHWKit的设计架构、功能特性，以及正确开展推理与训练的最佳实践。此外，我们还将概述模拟AI云编排器（Analog AI Cloud Composer）——该平台可在完全托管的云环境中提供AIHWKit模拟的全部优势，并支持物理AIMC硬件访问，其访问地址为https://aihw-composer.draco.res.ibm.com，可免费使用。最后，我们将展示用户如何针对自身需求扩展与自定义AIHWKit的具体示例。本教程配套了可通过AIHWKit运行的完整Jupyter笔记本（Jupyter Notebook）代码示例，可从https://github.com/IBM/aihwkit/tree/master/notebooks/tutorial下载获取。