Acore-CIM: build accurate and reliable mixed-signal CIM cores with RISC-V controlled self-calibration

TL;DR

This paper presents a self-calibrated mixed-signal CIM accelerator SoC in 22nm FDSOI technology, combining SRAM and resistive memory for efficient, reliable AI computation with RISC-V control and open-source tools.

Contribution

It introduces a novel integrated CIM architecture with on-chip RISC-V controlled self-calibration, improving accuracy and reliability for AI tasks.

Findings

Achieved 25-45% improvement in compute SNR through calibration.

Demonstrated integration of SRAM and resistive memory in a 22nm SoC.

Showcased potential for extending to high-density resistor technologies.

Abstract

Developing accurate and reliable Compute-In-Memory (CIM) architectures is becoming a key research focus to accelerate Artificial Intelligence (AI) tasks on hardware, particularly Deep Neural Networks (DNNs). In that regard, there has been significant interest in analog and mixed-signal CIM architectures aimed at increasing the efficiency of data storage and computation to handle the massive amount of data needed by DNNs. Specifically, resistive mixed-signal CIM cores are pushed by recent progresses in emerging Non-Volatile Memory (eNVM) solutions. Yet, mixed-signal CIM computing cores still face several integration and reliability challenges that hinder their large-scale adoption into end-to-end AI computing systems. In terms of integration, resistive and eNVM-based CIM cores need to be integrated with a control processor to realize end-to-end AI acceleration. Moreover, SRAM-based CIM architectures are still more efficient and easier to program than their eNVM counterparts. In terms of reliability, analog circuits are more susceptible to variations, leading to computation errors and degraded accuracy. This work addresses these two challenges by proposing a self-calibrated mixed-signal CIM accelerator SoC, fabricated in 22-nm FDSOI technology. The integration is facilitated by (1) the CIM architecture, combining the density and ease of SRAM-based weight storage with multi-bit computation using linear resistors, and (2) an open-source programming and testing strategy for CIM systems. The accuracy and reliability are enabled through an automated RISC-V controlled on-chip calibration, allowing us to improve the compute SNR by 25 to 45% across multiple columns to reach 18-24 dB. To showcase further integration possibilities, we show how our proof-of-concept SoC can be extended to recent high-density linear resistor technologies for enhanced computing performance.