Shaowei Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Shaowei Wang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Yongqiang Zhang
Hefei University of Technology
6 shared publications - Guangjun Xie
Hefei University of Technology
4 shared publications - Jie Han
University of Alberta
3 shared publications - Xin Cheng
School of Microelectronics, Hefei University of Technology, Hefei, China
3 shared publications - Yaohua Xu
Anhui University
3 shared publications - Na Bai
School of Integrated Circuits, Anhui University, Hefei, China
2 shared publications
Latest Publications
- 25 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. PP (19430663) , 1
Stochastic Computing Circuits for Nonlinear Functions Based on Multiplexers
Stochastic computing (SC) is a renewing computing paradigm that differs from weighted binary ones. It operates on binary stochastic bitstreams, or called stochastic numbers (SNs), instead of binary numbers (BNs). This work proposes circuits based on multiplexers (MUXs) to address the issue of SC in computing nonlinear functions. These circuits significantly reduce the number of required stochastic number generators (SNGs) and shorten critical path delay (CPD), thereby lowering hardware costs. Simulation and experimental results demonstrate that the proposed designs outperform existing designs in both computing accuracy and hardware overhead. For example, the proposed design for sin(x) using a 3rd-order Maclaurin series achieves averaged reductions of 66.84% in mean square error (MSE) and 24.62% in power-delay product (PDP), respectively, compared with previous designs.
- 25 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Embedded Systems Letters
- Vol. PP (19430663) , 1
Stochastic Computing Circuits for Nonlinear Functions Based on Multiplexers
Stochastic computing (SC) is a renewing computing paradigm that differs from weighted binary ones. It operates on binary stochastic bitstreams, or called stochastic numbers (SNs), instead of binary numbers (BNs). This work proposes circuits based on multiplexers (MUXs) to address the issue of SC in computing nonlinear functions. These circuits significantly reduce the number of required stochastic number generators (SNGs) and shorten critical path delay (CPD), thereby lowering hardware costs. Simulation and experimental results demonstrate that the proposed designs outperform existing designs in both computing accuracy and hardware overhead. For example, the proposed design for sin(x) using a 3rd-order Maclaurin series achieves averaged reductions of 66.84% in mean square error (MSE) and 24.62% in power-delay product (PDP), respectively, compared with previous designs.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 4411-4421
A Highly Robust and Low-Cost Multiple Node Upset Resilient Fast Latch for Radiation Applications
As the size of semiconductor process continues to shrink and deep space exploration continues to advance, the design of multiple-node-upset (MNU)-resilient latches has become indispensable for radiation hardening by design (RHBD). The C-element (CE) and the clock-gated C-element (CG-CE) are the basic elements for most conventional MNU resilient latches. However, most MNU-resilient latches improve the anti-radiation ability with the redundant nodes or redundant CE and CG-CE, causing a large area overhead. Some other MNU-resilient latches have less area overhead but have less anti-radiation ability. To overcome this problem, this paper proposes a corresponding MNU resilient latch design named (HLDRF). The proposed design consists of a generation module and a feedback module. The generation module transfers the generation nodes voltage to the feedback module, while the feedback module feeds the feedback nodes voltage back to the generation nodes through the pull-up/pull-down paths of the CE. This bidirectional interaction forms a closed-loop feedback circuit, ensuring the strong anti-radiation ability. While the proposed latch can fix errors quickly through feedback loops and without causing the propagation of faulty logic. The proposed latch achieves an optimal balance between area overhead and radiation hardness, offering superior comprehensive performance for deep space exploration. Furthermore, the proposed latch exhibits a lower sensitivity to process, supply voltage, and temperature (PVT) variations compared to similar latches.
- 19 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 4411-4421
A Highly Robust and Low-Cost Multiple Node Upset Resilient Fast Latch for Radiation Applications
As the size of semiconductor process continues to shrink and deep space exploration continues to advance, the design of multiple-node-upset (MNU)-resilient latches has become indispensable for radiation hardening by design (RHBD). The C-element (CE) and the clock-gated C-element (CG-CE) are the basic elements for most conventional MNU resilient latches. However, most MNU-resilient latches improve the anti-radiation ability with the redundant nodes or redundant CE and CG-CE, causing a large area overhead. Some other MNU-resilient latches have less area overhead but have less anti-radiation ability. To overcome this problem, this paper proposes a corresponding MNU resilient latch design named (HLDRF). The proposed design consists of a generation module and a feedback module. The generation module transfers the generation nodes voltage to the feedback module, while the feedback module feeds the feedback nodes voltage back to the generation nodes through the pull-up/pull-down paths of the CE. This bidirectional interaction forms a closed-loop feedback circuit, ensuring the strong anti-radiation ability. While the proposed latch can fix errors quickly through feedback loops and without causing the propagation of faulty logic. The proposed latch achieves an optimal balance between area overhead and radiation hardness, offering superior comprehensive performance for deep space exploration. Furthermore, the proposed latch exhibits a lower sensitivity to process, supply voltage, and temperature (PVT) variations compared to similar latches.
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 73 (2) , 198-202
A Counter-Based Addition Circuit Design for Stochastic Computing
Stochastic computing (SC) encodes real values via probabilistic bitstreams, enabling complex arithmetic operations to be realized by simple logic gates. However, the requirement of longer bitstreams to ensure computing accuracy leads to higher latency, partially offsetting the low-complexity advantage of SC. To address this, this work utilizes a dynamic truncation method for stochastic bitstreams, and designs an energy-efficient counter-based addition circuit (CBAC) through effective bit recognition and correlation. Further, a tree-structured cascading architecture is then used to perform multi-input addition computing. Experimental results demonstrate that the proposed CBAC outperforms the state-of-the-art designs. For instance, a 16-input configuration achieves at least 75.9% reduction in mean square error (MSE) and a more than 43.1% reduction in area. When applied to polynomial computation and Gaussian filtering, the proposed architecture exhibits superior accuracy and efficiency, delivering MSE reductions of at least 10.7% and area reductions exceeding 6.8%.
- 11 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 73 (2) , 198-202
A Counter-Based Addition Circuit Design for Stochastic Computing
Stochastic computing (SC) encodes real values via probabilistic bitstreams, enabling complex arithmetic operations to be realized by simple logic gates. However, the requirement of longer bitstreams to ensure computing accuracy leads to higher latency, partially offsetting the low-complexity advantage of SC. To address this, this work utilizes a dynamic truncation method for stochastic bitstreams, and designs an energy-efficient counter-based addition circuit (CBAC) through effective bit recognition and correlation. Further, a tree-structured cascading architecture is then used to perform multi-input addition computing. Experimental results demonstrate that the proposed CBAC outperforms the state-of-the-art designs. For instance, a 16-input configuration achieves at least 75.9% reduction in mean square error (MSE) and a more than 43.1% reduction in area. When applied to polynomial computation and Gaussian filtering, the proposed architecture exhibits superior accuracy and efficiency, delivering MSE reductions of at least 10.7% and area reductions exceeding 6.8%.
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 45 (4) , 1963-1974
A Low-Cost Input-Split Inverter-Based Triple-Node-Upset Recoverable Latch Design
As the integration level of integrated circuits continues to increase and the feature size of nanoscale chips continues to shrink, the possibility of triple-node-upsets (TNUs) occurring in circuits increases significantly. This article proposes a latch, namely, CLTNUSL, which offers stable resilience against TNUs in radiative environments while achieving a good balance between reliability and overhead. Unlike the conventional latches consisting of multi-input C-elements (CEs), the proposed CLTNUSL latch mainly consists of 16 interlocked dual-input inverters (DIs). Due to the small number of transistors, CLTNUSL achieves low area overhead. Due to the use of high-speed paths and clock-gating techniques, CLTNUSL achieves low-latency and low-power consumption. Simulation results demonstrate CLTNUSL’s full recovery from TNU in all scenarios. Compared with the conventional TNU-hardened latch, CLTNUSL achieves minimal latency, power consumption, area overhead, and the delay-power-area product (DPAP). CLTNUSL reduces delay by 13.22%, power by 52.74%, area by 40.90%, and DPAP by 71.44% on average, compared with state-of-the-art latches. Process, voltage, and temperature (PVT) and Monte Carlo simulation results show that the CLTNUSL latch is less sensitive to temperature, voltage, and process variations compared with conventional TNU self-recovery latches.
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 45 (4) , 1963-1974
A Low-Cost Input-Split Inverter-Based Triple-Node-Upset Recoverable Latch Design
As the integration level of integrated circuits continues to increase and the feature size of nanoscale chips continues to shrink, the possibility of triple-node-upsets (TNUs) occurring in circuits increases significantly. This article proposes a latch, namely, CLTNUSL, which offers stable resilience against TNUs in radiative environments while achieving a good balance between reliability and overhead. Unlike the conventional latches consisting of multi-input C-elements (CEs), the proposed CLTNUSL latch mainly consists of 16 interlocked dual-input inverters (DIs). Due to the small number of transistors, CLTNUSL achieves low area overhead. Due to the use of high-speed paths and clock-gating techniques, CLTNUSL achieves low-latency and low-power consumption. Simulation results demonstrate CLTNUSL’s full recovery from TNU in all scenarios. Compared with the conventional TNU-hardened latch, CLTNUSL achieves minimal latency, power consumption, area overhead, and the delay-power-area product (DPAP). CLTNUSL reduces delay by 13.22%, power by 52.74%, area by 40.90%, and DPAP by 71.44% on average, compared with state-of-the-art latches. Process, voltage, and temperature (PVT) and Monte Carlo simulation results show that the CLTNUSL latch is less sensitive to temperature, voltage, and process variations compared with conventional TNU self-recovery latches.
- 26 December 2023
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 33 (09)
A Low-Cost and Fault-Tolerant Stochastic Architecture for the Bernsen Algorithm Using Bitstream Correlation
Many algorithms for image processing do not require particularly high precision, but they rely on complicated arithmetic operations for every pixel in an image. The Bernsen algorithm is a typical local thresholding algorithm for solving the problem of uneven lighting. However, this algorithm requires a significant computing overhead and is extremely sensitive to noise. In this work, two stochastic computing architectures are proposed for implementing the Bernsen algorithm by using, respectively, uncorrelated and correlated input bitstreams. Experimental results show that both designs, especially the one using correlated bitstreams, present high fault tolerance of soft errors and low hardware cost in comparison with its conventional binary implementation. However, SC logic with uncorrelated inputs is not always superior to its corresponding binary circuit in energy consumption, especially the circuit that needs long input bitstreams. That means that a reasonable use of correlation can further optimize the SC circuit design.
- 26 December 2023
- Published by World Scientific Pub Co Pte Ltd in Journal of Circuits, Systems and Computers
- Vol. 33 (09)
A Low-Cost and Fault-Tolerant Stochastic Architecture for the Bernsen Algorithm Using Bitstream Correlation
Many algorithms for image processing do not require particularly high precision, but they rely on complicated arithmetic operations for every pixel in an image. The Bernsen algorithm is a typical local thresholding algorithm for solving the problem of uneven lighting. However, this algorithm requires a significant computing overhead and is extremely sensitive to noise. In this work, two stochastic computing architectures are proposed for implementing the Bernsen algorithm by using, respectively, uncorrelated and correlated input bitstreams. Experimental results show that both designs, especially the one using correlated bitstreams, present high fault tolerance of soft errors and low hardware cost in comparison with its conventional binary implementation. However, SC logic with uncorrelated inputs is not always superior to its corresponding binary circuit in energy consumption, especially the circuit that needs long input bitstreams. That means that a reasonable use of correlation can further optimize the SC circuit design.
- 28 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 31 (9) , 1439-1443
An Energy-Efficient Binary-Interfaced Stochastic Multiplier Using Parallel Datapaths
Stochastic computing (SC) typically requires a low design complexity compared with weighted binary computing, so it has been successfully applied in neural networks (NNs). Usually, SC utilizes random bitstreams as its medium, which makes it suffer from a long delay that offsets its advantages. This drawback can be alleviated by utilizing parallel datapaths, which, however, will significantly increase the hardware cost due to the requirement of multiple parallel computing units. In this article, a hybrid bit-splitting generator (HBSG) is proposed to efficiently produce parallel bitstreams in a single clock cycle to reduce delay. The HBSG uniformly splits binary numbers into $R$ segments, each of which is encoded in parallel by using hardwired connections according to the weight of each bit. A binary-interfaced parallel stochastic multiplier (BipSMul) using the HBSG is then proposed to accelerate the multiplication in SC. Experimental results show that the BipSMul is more energy efficient than the state-of-the-art parallel and serial stochastic designs, as well as their binary and Booth counterparts, in delay, power-delay product (PDP), and area-delay product (ADP).
- 28 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
- Vol. 31 (9) , 1439-1443
An Energy-Efficient Binary-Interfaced Stochastic Multiplier Using Parallel Datapaths
Stochastic computing (SC) typically requires a low design complexity compared with weighted binary computing, so it has been successfully applied in neural networks (NNs). Usually, SC utilizes random bitstreams as its medium, which makes it suffer from a long delay that offsets its advantages. This drawback can be alleviated by utilizing parallel datapaths, which, however, will significantly increase the hardware cost due to the requirement of multiple parallel computing units. In this article, a hybrid bit-splitting generator (HBSG) is proposed to efficiently produce parallel bitstreams in a single clock cycle to reduce delay. The HBSG uniformly splits binary numbers into $R$ segments, each of which is encoded in parallel by using hardwired connections according to the weight of each bit. A binary-interfaced parallel stochastic multiplier (BipSMul) using the HBSG is then proposed to accelerate the multiplication in SC. Experimental results show that the BipSMul is more energy efficient than the state-of-the-art parallel and serial stochastic designs, as well as their binary and Booth counterparts, in delay, power-delay product (PDP), and area-delay product (ADP).
- 27 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 69 (11) , 4528-4532
Weighted-Adder-Based Polynomial Computation Using Correlated Unipolar Stochastic Bitstreams
Stochastic computing (SC) is an unconventional computing paradigm, which processes numerical values through stochastic bitstreams. This representation can be interpreted as probabilities and makes stochastic circuits implemented with simple logic gates. This brief proposes a stochastic weighted-adder based approach for computing polynomials by using correlation logic in unipolar format. This approach can significantly reduce the use of RNGs to lower hardware cost and can handily compute polynomials with arbitrary coefficients. Experimental results show that the proposed designs outperform previous counterparts in computing accuracy and hardware cost. For example, the $5^{th}$ -order Maclaurin polynomial of the sigmoid( ${x}$ ) that contains positive and negative coefficients can have at least an 87% improvement in mean squared error and a 21% reduction in area.
- 27 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 69 (11) , 4528-4532
Weighted-Adder-Based Polynomial Computation Using Correlated Unipolar Stochastic Bitstreams
Stochastic computing (SC) is an unconventional computing paradigm, which processes numerical values through stochastic bitstreams. This representation can be interpreted as probabilities and makes stochastic circuits implemented with simple logic gates. This brief proposes a stochastic weighted-adder based approach for computing polynomials by using correlation logic in unipolar format. This approach can significantly reduce the use of RNGs to lower hardware cost and can handily compute polynomials with arbitrary coefficients. Experimental results show that the proposed designs outperform previous counterparts in computing accuracy and hardware cost. For example, the $5^{th}$ -order Maclaurin polynomial of the sigmoid( ${x}$ ) that contains positive and negative coefficients can have at least an 87% improvement in mean squared error and a 21% reduction in area.
- 6 June 2022
- Published by Wiley in International Journal of Circuit Theory and Applications
- Vol. 50 (10) , 3692-3703
High‐accuracy mean circuits design by manipulating correlation for stochastic computing
Stochastic computing (SC) encodes numerical values into probabilistic binary bitstreams to enable complex arithmetic operations to be transformed into simple bit operations. Different operations can be performed through the same SC element by adjusting the correlation between bitstreams. In this work, two stochastic mean circuits (MCs) are proposed by manipulating positively and negatively correlated bitstreams, respectively named PCMC and NCMC, to improve computing accuracy, lower area, and power consumption. Furthermore, a general structure for MCs, denoted as GMC, is also proposed to generalize their design approach. Compared with the existing multiplexer (MUX)‐based stochastic MCs, the proposed circuits have approximately 50%, 59%, 61%, and 64% reduction in area, and 100×, 10×, 151×, and 12 × improvement in MSE, for 2‐, 3‐, 4‐, and 5‐input situations, respectively. With applications to edge detection and mean filtering, the proposed designs are superior to the existing counterparts in terms of accuracy and hardware cost.
- 6 June 2022
- Published by Wiley in International Journal of Circuit Theory and Applications
- Vol. 50 (10) , 3692-3703
High‐accuracy mean circuits design by manipulating correlation for stochastic computing
Stochastic computing (SC) encodes numerical values into probabilistic binary bitstreams to enable complex arithmetic operations to be transformed into simple bit operations. Different operations can be performed through the same SC element by adjusting the correlation between bitstreams. In this work, two stochastic mean circuits (MCs) are proposed by manipulating positively and negatively correlated bitstreams, respectively named PCMC and NCMC, to improve computing accuracy, lower area, and power consumption. Furthermore, a general structure for MCs, denoted as GMC, is also proposed to generalize their design approach. Compared with the existing multiplexer (MUX)‐based stochastic MCs, the proposed circuits have approximately 50%, 59%, 61%, and 64% reduction in area, and 100×, 10×, 151×, and 12 × improvement in MSE, for 2‐, 3‐, 4‐, and 5‐input situations, respectively. With applications to edge detection and mean filtering, the proposed designs are superior to the existing counterparts in terms of accuracy and hardware cost.