282-to-607 TOPS/W, 7T-SRAM Based CiM with Reconfigurable Column SAR ADC for Neural Network Processing

282-to-607 TOPS/W, 7T-SRAM Based CiM with Reconfigurable Column SAR ADC for Neural Network Processing

2023 IEEE International Symposium on Circuits and Systems (ISCAS)

10.1109/ISCAS46773.2023.10181435

http://dx.doi.org/10.1109/iscas46773.2023.10181435

Qibang Zang, Wang Ling Goh, Lu Lu, Chengshuo Yu, Junjie Mu, Tony Tae-Hyoung Kim, Bongjin Kim, Dongrui Li, Anh Tuan Do

21 July 2023

Zang, Q., Goh, W. L., Lu, L., Yu, C., Mu, J., Kim, T. T.-H., Kim, B., Li, D., & Do, A. T. (2023, May 21). 282-to-607 TOPS/W, 7T-SRAM Based CiM with Reconfigurable Column SAR ADC for Neural Network Processing. 2023 IEEE International Symposium on Circuits and Systems (ISCAS). https://doi.org/10.1109/iscas46773.2023.10181435

Compute in memory ( C iM) is a promising solution for solving the bottleneck of frequent data interface between memory and processor in Von-Neumann architecture. In this work, a hybrid current/charge domain 7T-SRAM based CiM architecture is proposed to mitigate the PVT-induced RBL variation during computation and thus offer a better linearity without significant impact on the operating frequency and area efficiency. Additionally, a column-referenced 1b to 5b reconfigurable SAR ADC is proposed to support multi-bit output. The proposed design is verified by the Monte-Carlo simulations using 40nm CMOS technology. The 5b mode ADC transferred MAC curve's DNL (LSB) ranges from −0.025 to 0.02 and INL (LSB) ranges from −0.13 to 0.25. The largest RBL variation (σ) from MAC value −64 to MAC value +64 is 2.08 mV, resulting in a MNIST classification accuracy of 97.5%, which is only 0.1% degradation and Google Speech Command classification accuracy of 80.5%, which is only 0.5% degradation compared to the software baseline, respectively. The whole architecture offers energy efficiency of 282-to-607 TOPS/W for 1-5b output in the MAC operation, which is competitive when compared to other state-of-art C iM architectures.

Publisher Copyright

This research / project is supported by the A*STAR - Spin-Orbit Technologies for intelligence at the Edge (SpOT-LITE)
Grant Reference no. : A18A6b0057

© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

https://oar.a-star.edu.sg/communities-collections/articles/20266

2158-1525

Institute of Microelectronics