A Distributed Emulation Environment for In-Memory Computing Systems

Abstract--In-memory computing technology is used extensively in artificial intelligence devices due to lower power consumption and fast calculation of matrix-based functions. The development of such a device and its integration in a system takes a significant amount of time and requires the use of a real-time emulation environment, where various system aspects are analyzed, microcode is tested, and applications are deployed, even before the real chip is available. In this work, we present the architecture, the software development tools, and experimental results of a distributed and expandable emulation system for rapid prototyping of integrated circuits based on in-memory computing technologies. Presented experimental results demonstrate the usefulness of the proposed emulator . Edge computing is a key technology for the successful deployment of the Internet of Things (IoT), by providing decentralized processing, offering high processing rates with low latency, thus resulting to efficient bandwidth usage and improved reliability, due to its fault tolerant approach [1]. One of the most promising technologies used in edge computing devices is In-Memory Computing (IMC), which utilizes volatile or non-volatile memory (NVM) cells to store the weights of matrix-based functions and to perform in-situ computations with reduced latency and less power consumption. Digital IMCs (DIMCs) are based on SRAMs or DRAMs, while analog IMCs (AIMC) modules are based on non-volatile memories, like PCM [2].