Mingyang Zhou

Mingyang Zhou

Auto-generated profile, based on publicly available information

Mingyang Zhou

National ASIC System Engineering Center, Southeast University, Nanjing, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 January 2022 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
HCHao Cai
Hao Cai
YGYanan Guo
Yanan Guo
BLBo Liu
Bo Liu
MZMingyang Zhou
Mingyang Zhou
JCJuntong Chen
Juntong Chen
LHLuchi Hua
Luchi Hua
In-memory computing (IMC) is an effective solution for energy-efficient artificial intelligence applications. Analog IMC amortizes the power consumption of multiple sensing amplifiers with an analog-to-digital converter (ADC) and simultaneously completes the calculation of multi-line data with a high parallelism degree. Based on a universal one-transistor one-magnetic tunnel junction (MTJ) spin transfer torque magnetic RAM (STT-MRAM) cell, this paper demonstrates a novel tunneling magnetoresistance (TMR) ratio magnifying method to realize analog IMC. Previous concerns including low TMR ratio and analog calculation nonlinearity are addressed using device-circuit interaction. The TMR is magnified $7500\times $ using a latch structure in combination with the device. Peripheral circuits are minimally modified to enable in-memory matrix-vector multiplication. A current mirror with a feedback structure is implemented to enhance analog computing linearity and calculation accuracy. The proposed design maximumly supports 1024 2-bit input and 1-bit weight multiply-and-accumulate (MAC) computations simultaneously. The proposal is simulated using the 28-nm CMOS process and MTJ compact model. The integral nonlinearity is reduced by 57.6% compared with the conventional structure. 9.47-25.4 TOPS/W is realized with 2-bit input, 1-bit weight, and 4-bit output convolution neural network (CNN).

15 June 2023 in IEEE Transactions on Magnetics
Verified
Journal Article
Closed access
MZMingyang Zhou
Mingyang Zhou
HDHaoran Du
Haoran Du
YGYanan Guo
Yanan Guo
HCHao Cai
Hao Cai
Analog in-memory computing (AiMC) reduces the cost of data transfer by processing data inside memory. Compared with other emerging nonvolatile memories, AiMC with magnetic random-access memory (MRAM) shows potential with logic compatible supply voltage, small variability issues, and high endurance. However, the analog output of the array must be converted to digital using an analog-to-digital converter (ADC), which significantly offsets the benefits of AiMC. This paper presents power-aware quantization circuits in AiMC with spin transfer torque MRAM (STT-MRAM) macro, in which a successive approximation register (SAR) ADC with reconfigurable 3/4-bit resolution and 250MS/s sampling rate addresses the need of high speed and low power for AiMC. By using 28-nm CMOS process, simulation results show that the proposed ADC consumes only 31.6 μW at a 900mV supply and 250MS/s. 10.4-25.7 TOPS/W is realized with 2-bit input, 1-bit weight, and 4-bit output convolution neural network (CNN).

31 May 2023
Verified
Conference Paper
Closed access
PDF file
YWYan Wang
Yan Wang
XLXun Li
Xun Li
TFTong Fu
Tong Fu
MZMingyang Zhou
Mingyang Zhou
ZKZhengbang Kang
Zhengbang Kang
AHAnping He
Anping He
The GasP circuit is a high-speed controller that has been used more often in the field of asynchronous circuits. However, in the conventional GasP design method, the matching process of its internal delay lacks the consideration of the circuit application environment. In view of this, this paper proposes three delay adjustment methods by combining the usage scenario of the circuit and the logical effort. The method first adjusts the pulse width of the digital circuit, the ability to drive the DFF and the maximum equivalent frequency of the circuit, then customizes the delay and drive of the GasP, and finally verifies the performance with a NoC built with the GasP. The experimental results show that the maximum equivalent frequency of GasP can reach 2.28GHz in 110nm CMOS process, which is about 10 times of the classical synchronous design.