A 115.1 TOPS/W, 12.1 TOPS/mm²Computation-in-Memory using Ring-Oscillator based ADC for Edge AI

A 115.1 TOPS/W, 12.1 TOPS/mm²Computation-in-Memory using Ring-Oscillator based ADC for Edge AI

Singh, A. (TU Delft Computer Engineering)
Bishnoi, R.K. (TU Delft Computer Engineering)
Kaichouhi, A. (TU Delft Electrical Engineering, Mathematics and Computer Science)
Diware, S.S. (TU Delft Computer Engineering)
Joshi, R.V. (TU Delft Computer Engineering; IBM Thomas J. Watson Research Centre)
Hamdioui, S. (TU Delft Quantum & Computer Engineering)

Electrical Engineering, Mathematics and Computer Science

Quantum & Computer Engineering

2023

Analog computation-in-memory (CIM) architecture alleviates massive data movement between the memory and the processor, thus promising great prospects to accelerate certain computational tasks in an energy-efficient manner. However, data converters involved in these architectures typically achieve the required computing accuracy at the expense of high area and energy footprint which can potentially determine CIM candidacy for low-power and compact edge-AI devices. In this work, we present a memory-periphery co-design to perform accurate A/D conversions of analog matrix-vector-multiplication (MVM) outputs. Here, we introduce a scheme where select-lines and bit-lines in the memory are virtually fixed to improve conversion accuracy and aid a ring-oscillator-based A/D conversion, equipped with component sharing and inter-matching of the reference blocks. In addition, we deploy a self-timed technique to further ensure high robustness addressing global design and cycle-to-cycle variations. Based on measurement results of a 4Kb CIM chip prototype equipped with TSMC 40nm, a relative accuracy of up to 99.71% is achieved with an energy efficiency of 115.1 TOPS/W and computational density of 12.1 TOPS/mm2 for the MNIST dataset. Thus, an improvement of up to 11.3X and 7.5X compared to the state-of-the-art, respectively.

analog computing
analog-to-digital converters
Computation-in-memory
ring-oscillator

http://resolver.tudelft.nl/uuid:f33618c9-a551-4663-9cf5-9772e0d8f205

https://doi.org/10.1109/AICAS57966.2023.10168647

Institute of Electrical and Electronics Engineers (IEEE)

2024-01-08

9798350332674

AICAS 2023 - IEEE International Conference on Artificial Intelligence Circuits and Systems, Proceeding

5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023, 2023-06-11 → 2023-06-13, Hangzhou, China

AICAS 2023 - IEEE International Conference on Artificial Intelligence Circuits and Systems, Proceeding

Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

conference paper

© 2023 A. Singh, R.K. Bishnoi, A. Kaichouhi, S.S. Diware, R.V. Joshi, S. Hamdioui