EasyACIM: An End-to-End Automated Analog CIM with Synthesizable Architecture and Agile Design Space Exploration

TL;DR

EasyACIM introduces an automated, end-to-end design framework for Analog Computing-in-Memory architectures, enabling rapid, scalable, and customizable AI edge computing solutions with competitive performance.

Contribution

It presents a synthesizable architecture and a genetic algorithm-based design space explorer for fully automated ACIM layout generation and optimization.

Findings

Automated ACIM layout generation with customizable specifications.

High-quality ACIM solutions with wide design space.

Competitive performance compared to state-of-the-art ACIMs.

Abstract

Analog Computing-in-Memory (ACIM) is an emerging architecture to perform efficient AI edge computing. However, current ACIM designs usually have unscalable topology and still heavily rely on manual efforts. These drawbacks limit the ACIM application scenarios and lead to an undesired time-to-market. This work proposes an end-to-end automated ACIM based on a synthesizable architecture (EasyACIM). With a given array size and customized cell library, EasyACIM can generate layouts for ACIMs with various design specifications end-to-end automatically. Leveraging the multi-objective genetic algorithm (MOGA)-based design space explorer, EasyACIM can obtain high-quality ACIM solutions based on the proposed synthesizable architecture, targeting versatile application scenarios. The ACIM solutions given by EasyACIM have a wide design space and competitive performance compared to the state-of-the-art (SOTA) ACIMs.