Zeyu Yang

Zeyu Yang

Auto-generated profile, based on publicly available information

Zeyu Yang

College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, 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
7 March 2023 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
QHQingrong Huang
Qingrong Huang
ZYZeyu Yang
Zeyu Yang
KNKai Ni
Kai Ni
MIMohsen Imani
Mohsen Imani
CZCheng Zhuo
Cheng Zhuo
XYXunzhao Yin
Xunzhao Yin
The data explosion of Internet of Things (IoT) and machine learning tasks raises a great demand on highly efficient computing hardware and paradigms. Brain-inspired hyperdimensional computing (HDC) is becoming a promising computing paradigm, which encodes data as hypervectors with homogeneous elements instead of numbers, and can perform learning/classification tasks through simple logical or arithmetic operations on the encoded hypervectors. Therefore HDC has much lower computational complexity than conventional computational models such as neural networks. However, due to its high-dimensional data representation, processing, and encoding hypervectors in conventional Von–Neumann architectures (e.g., CPU and GPU) requires a large amount of energy- and time-consuming data transfer, thus weakening its efficiency benefiting from low complexity. In this article, we proposed an ultralow power and fast computing-in-memory (CiM) design based on nonvolatile (NV) ferroelectric FET (FeFET) for HDC encoding. The proposed design mainly support hyperdimensional bit-wise XOR and parallel majority vote (MAJ) operations for HDC encoding, which are implemented by FeFET-based memories together with CMOS peripheral circuits. The 1FeFET1T-based memory cell effectively mitigates the impact of transistor variations on the operation. A highly parallel and pipelined computing workflow of the proposed design further boosts the energy efficiency and performance with a negligible extra area overhead. Experimental results demonstrate that our proposed design achieves $5.04\times $ energy efficiency improvement over other CiM designs for HDC encoding.

6 September 2022 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
CZCheng Zhuo
Cheng Zhuo
ZYZeyu Yang
Zeyu Yang
KNKai Ni
Kai Ni
MIMohsen Imani
Mohsen Imani
YLYuxuan Luo
Yuxuan Luo
XYXunzhao Yin
Xunzhao Yin
Content addressable memories (CAMs) are a promising category of computing-in-memory (CiM) elements that can perform highly parallel and efficient search operations for routers, pattern matching, and other data-intensive applications. Various magnetic tunnel junction (MTJ)-based CAM designs have been proposed to realize zero standby power and high-performance search. However, due to the relatively small tunnel magneto-resistance (TMR) ratio, MTJ-based CAMs require extra transistors and differential MTJ branches to distinguish between the parallel and anti-parallel resistance states, resulting in significant area and energy overhead. In this article, we propose a device-circuit co-design approach for an ultracompact CAM design by only exploiting a 1T-1MTJ structure in each cell. We propose a 2-step search scheme to enable the parallel in-memory search operation across the proposed CAM array and demonstrate the sufficient sensing margin of the array in a successful search operation. Evaluation results suggest that our proposed 1T-1MTJ-based CAM design improves $179\times /301\times $ area efficiency compared with the state-of-the-art 15T-4MTJ/20T-6MTJ CAM design. Application benchmarking on hyperdimensional computing (HDC) inference shows a $54.6\times /12.8\times $ speedup compared with GPU/20T-6MTJ CAM-based approaches.

17 October 2022 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
DGDi Gao
Di Gao
ZYZeyu Yang
Zeyu Yang
QHQingrong Huang
Qingrong Huang
GZGrace Li Zhang
Grace Li Zhang
XYXunzhao Yin
Xunzhao Yin
CZCheng Zhuo
Cheng Zhuo
Memristor crossbar arrays are considered to be a promising platform for neuromorphic computing. To deploy a trained neural network model on memristor crossbars, memristors need to be programmed to the corresponding weight values. In fact, due to device based process variation and noise, deviations of the stored weights from the trained weights are inevitable, thereby causing the degradation of the actual inference performance. This paper proposes a unified Bayesian inference based framework, BRoCoM, which connects device nonidealities and algorithmic training together for robust computing on memristor crossbars. BRoCoM is able to incorporate different levels of nonidealities into prior weight distribution, and transform robustness optimization to Bayesian neural network training, the weights of neural networks are optimized to accommodate uncertainties and minimize inference degradation. Experimental results confirm the capability of the proposed BRoCoM to achieve stable inference performance while tolerating the non-ideal effects of process variation and noise.

23 June 2024
Verified
Conference Paper
Open access
ZYZeyu Yang
Zeyu Yang
QHQingrong Huang
Qingrong Huang
YQYu Qian
Yu Qian
KNKai Ni
Kai Ni
Thomas KämpfeThomas Kämpfe
Thomas Kämpfe
XYXunzhao Yin
Xunzhao Yin
In-memory computing (IMC) architecture emerges as a promising paradigm, improving the energy efficiency of multiply-and-accumulate (MAC) operations within deep neural networks (DNNs) by integrating the parallel computations within the memory arrays. Various high-precision analog IMC array designs have been developed based on both SRAM and emerging non-volatile memories (NVMs). These designs perform MAC operations of partial input and weight, with the corresponding partial products then fed into shift-add circuitry to produce the final MAC results. However, existing works often present intricate shift-add process for weight. The traditional digital shift-add process is limited in throughput due to time-multiplexing of ADCs, and advancing the shift-add process to the analog domain necessitates customized circuit implementations, resulting in compromises in energy and area efficiency. Furthermore, the joint optimization of the partial MAC operations and the weight shift-add process is rarely explored. In this paper, we propose novel, energy efficient dual designs of ferroelectric FET (FeFET) based high precision analog IMC featuring inherent shift-add capability. We introduce a FeFET based IMC paradigm that performs partial MAC in each column, and inherently integrates the shift-add process for 4-bit weights by leveraging FeFET's analog storage characteristics. This paradigm supports both 2's complement mode (2CM) and non-2's complement mode (N2CM) MAC, thereby offering flexible support for 4-/8-bit weight data in 2's complement format. Building upon this paradigm, we propose novel FeFET based dual designs, CurFe for the current mode and ChgFe for the charge mode, to accommodate the high precision analog domain IMC architecture. Evaluation results at circuit and system levels indicate that the circuit/system-level energy efficiency of the proposed FeFET-based analog IMC is 1.56×/1.37× higher when compared to the state-of-the-art analog IMC designs.

23 June 2024
Verified
Conference Paper
Open access
YQYu Qian
Yu Qian
ZYZeyu Yang
Zeyu Yang
KNKai Ni
Kai Ni
AVAlptekin Vardar
Alptekin Vardar
Thomas KämpfeThomas Kämpfe
Thomas Kämpfe
XYXunzhao Yin
Xunzhao Yin
Computationally challenging combinatorial optimization problems (COPs) play a fundamental role in various applications. To tackle COPs, many Ising machines and Quadratic Unconstrained Binary Optimization (QUBO) solvers have been proposed, which typically involve direct transformation of COPs into Ising models or equivalent QUBO forms (D-QUBO). However, when addressing COPs with inequality constraints, this D-QUBO approach introduces numerous extra auxiliary variables, resulting in a substantially larger search space, increased hardware costs, and reduced solving efficiency. In this work, we propose HyCiM, a novel hybrid computing-inmemory (CiM) based QUBO solver framework, designed to overcome aforementioned challenges. The proposed framework consists of (i) an innovative transformation method (first to our known) that converts COPs with inequality constraints into an inequality-QUBO form, thus eliminating the need of expensive auxiliary variables and associated calculations; (ii) "inequality filter", a ferroelectric FET (FeFET)-based CiM circuit that accelerates the inequality evaluation, and filters out infeasible input configurations; (iii) a FeFET-based CiM annealer that is capable of approaching global solutions of COPs via iterative QUBO computations within a simulated annealing process. The evaluation results show that HyCiM drastically narrows down the search space, eliminating 2100 to 22536 infeasible input configurations compared to the conventional D-QUBO approach. Consequently, the narrowed search space, reduced to 2100 feasible input configurations, leads to a substantial hardware area overhead reduction, ranging from 88.06% to 99.96%. Additionally, HyCiM consistently exhibits a high solving efficiency, achieving a remarkable average success rate of 98.54%, whereas D-QUBO implementatoin shows only 10.75%.

9 May 2025 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
XHXuchu Huang
Xuchu Huang
QHQingrong Huang
Qingrong Huang
ZYZeyu Yang
Zeyu Yang
MZMin Zhou
Min Zhou
ZYZheyu Yan
Zheyu Yan
XYXunzhao Yin
Xunzhao Yin
The rapid growth of the Internet of Things (IoT) promotes vision application deployments in embedded devices. To alleviate the data conversion and transmission overheads in CMOS image sensor (CIS), processing-in-sensor (PIS) has been proposed, enabling computations to occur directly within sensory systems. Meanwhile, brain-inspired hyperdimensional computing (HDC) emerges as a promising computing paradigm well-suited for PIS due to its high accuracy and efficiency in various cognitive tasks. However, HDC requires transforming the sensed signals into long hypervectors (HVs), which imposes significant overhead for PIS systems. Thus, in this article, we propose SenHDC, a hardware-software co-design framework for HDC-based PIS. We introduce a novel hardware-friendly encoding paradigm that eliminates complex HV transformations, coupled with a noise-resilient position HV generation method that mitigates the impact of capacitance load imbalance. We further present an efficient 3-D NAND flash-based compute-in-memory (CIM) hardware design, comprising an encoding module that performs encoding in charge domain and an associative search module that checks the similarity between the input and prestored classes for classification. Experimental results show that SenHDC improves energy efficiency by $40.6\times $ and $1.6\times $ in the encoding module and associative search module, respectively, compared to the state-of-the-art HDC CIM implementations.