RelaxCIM: A Power- and Area-Efficient RxO-based Readout Cell for ADC-less CIM Accelerators

Loading...
Thumbnail Image

Access rights

openAccess
CC BY
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

Major/Subject

Mcode

Degree programme

Language

en

Pages

Series

2025 20th International Conference on PhD Research in Microelectronics and Electronics, PRIME 2025

Abstract

Compute-In-Memory (CIM) architectures are becoming standard solutions for accelerating AI workloads. Yet, the performance of analog CIM cores is generally constrained by the quantization resolution and energy consumption of the readout stage, typically dominated by Analog-to-Digital Converters (ADCs). To address this issue, we present RelaxCIM, a compact, low-power readout approach that replaces traditional resource-intensive ADCs with a Relaxation Oscillator (RxO) and a digital counter for current-based CIM accelerators. Implemented in 65 nm CMOS, each RxO-based cell occupies 0.0015 mm2, consumes an average power of 0.21 mW, and achieves a resolution of 100 nA per Least-Significant Bit (LSB) at a 100 MHz counting frequency. This fine resolution is particularly beneficial for large neural networks mapped onto small CIM arrays employing time-multiplexed Vector-Matrix Multiplication (VMM) and partialsum operations, effectively reducing quantization errors and finite-precision limitations.

Description

Publisher Copyright: © 2025 IEEE.

Other note

Citation

Singh, G, Numan, O, Chouhan, S S, Mohey, A & Halonen, K 2025, RelaxCIM: A Power- and Area-Efficient RxO-based Readout Cell for ADC-less CIM Accelerators. in 2025 20th International Conference on PhD Research in Microelectronics and Electronics, PRIME 2025. IEEE, Conference on Ph.D. Research in Microelectronics and Electronics, Taormina, Italy, 21/09/2025. https://doi.org/10.1109/PRIME66228.2025.11203462