Song Jin

Dr. Song Jin


Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
16 July 2021 in IEEE Access
Verified
Journal Article
Open access
YXYatou Xu
Yatou Xu
SJSong Jin
Song Jin
YWYu Wang
Yu Wang
Yincheng QiYincheng Qi
Yincheng Qi
The memristor crossbar has the characteristic of high parallelism in implementing the matrix vector multiplication which can speed up the computation of the neural network. However, faulty memristors resulted from the hardware defects significantly degrade the classification accuracy of neural networks deployed onto the crossbar. Weight mapping is a type of low cost fault tolerant scheme. Unfortunately, the existing schemes usually conduct fault aware weight mapping in the entire row granularity which constrains the optimization space for fault tolerance. To overcome above mentioned problem, in this paper, we propose the operational unit (OU) level weight mapping which further adjusts mapping of the weight blocks inside each OU after the row granularity weight mapping. Such strategy can implement fine-grained fault tolerance. Moreover, we unify the similar inputs for the different OUs in order to constrain the increase in the number of input vectors resulted from the OU level mapping adjustment. The simulation results demonstrate that with the defect rates of 5%, 10%, 15% and 20%, on average classification accuracies of the networks optimized by the proposed scheme are improved by 1.165%, 4.38%, 10.73% and 12.58% compared to the ones of the row level weight mapping. Moreover, on average numbers of the input vectors are reduced by 61.8%, 73.2%, 75.3% and 64.9%, compared with the OU level weight mapping without considering unification of the similar inputs.

1 November 2012 in Microelectronics Journal
Verified
Journal Article
Closed access
SJSong Jin
Song Jin
YHYinhe Han
Yinhe Han

3 October 2020 in Cluster Computing
Verified
Journal Article
Closed access
PDF file
SJSong Jin
Song Jin
SPSongwei Pei
Songwei Pei
YWYu Wang
Yu Wang
YQYincheng Qi
Yincheng Qi

1 January 2009
Verified
Conference Paper
Closed access
SJSong Jin
Song Jin
YHYinhe Han
Yinhe Han
LZLei Zhang
Lei Zhang
HLHuawei Li
Huawei Li
XLXiaowei Li
Xiaowei Li
GYGuihai Yan
Guihai Yan
Negative bias temperature instability (NBTI) has been a significant reliability concern in current digital circuit design due to its effect of increasing the path delay with time and in turn degrading the circuit performance. NBTI degradation has strong dependence on input pattern and duty cycles. Based on this observation, we propose to apply multiple input vectors to the combination circuit in a non-uniform way during standby mode. Multiple input vectors can enhance the capability to control the circuit nodes, achieve smaller duty cycles to reduce the stress time of gates and thus mitigate static NBTI. A constrained multi-object optimization model is formalized to find the optimal combination of duty cycles for timing-critical paths, which in turn minimizes the increase of path delay. An ATPG-like procedure is then presented to generate the corresponding input vectors. Experimental results demonstrate that the delay increase of timing-critical paths can be mitigated significantly under long time NBTI effect (10-year) by only applying a small number of vectors.

1 December 2010
Verified
Conference Paper
Closed access
SJSong Jin
Song Jin
YHYinhe Han
Yinhe Han
HLHuawei Li
Huawei Li
XLXiaowei Li
Xiaowei Li
Statistical static timing analysis (SSTA) considering process variation and aging effects is usually used to analyze circuit lifetime reliability at design phase. A key challenge for statistical lifetime reliability analysis is that an accurate statistical timing model is needed to carefully model practical variation distribution as well as delay correlation. In this work, P2CLRAF, a circuit lifetime reliability analysis framework is proposed. It calibrates pre-silicon SSTA result by learning the collected data from path delay testing at post-silicon timing validation phase. A neural network inside P2CLRAF is trained to learn variation distribution and delay correlation based on the statistic of path delay testing. The learned information is then fed back to SSTA to further improve the accuracy of circuit lifetime reliability analysis. Experimental results demonstrate the effectiveness of the proposed analysis framework.

24 March 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SJSong Jin
Song Jin
SLShuaihang Li
Shuaihang Li
This paper presents a high-precision angle demodulation method for magnetic encoders by integrating orthogonal-signal correction with space–time modulation (STM). The proposed approach specifically addresses a critical vulnerability of STM-based high-frequency pulse interpolation: its interpolation accuracy is highly sensitive to zero-crossing timing jitter of the quadrature signals. In practical magnetic encoders, non-idealities such as DC offsets, amplitude mismatch, and phase non-orthogonality in the sine/cosine outputs induce jitter and shift in the zero-crossing points. This directly leads to fluctuations in high-frequency counts and amplifies the final angle error. To mitigate this issue, an online orthogonal-signal correction module is first developed. This module sequentially performs offset estimation, amplitude normalization, and real-time phase orthogonalization, thereby enhancing the orthogonality and zero-crossing stability of the quadrature signals at the source. This preprocessing significantly reduces the sensitivity of the subsequent interpolation counting to noise and signal imperfections. Based on the corrected signals, an STM pulse-counting interpolator is adopted to convert angle information into a time-domain phase (time) difference, and high-frequency counting is used for fine subdivision. A Kalman-filter-based predictor is employed to estimate angular velocity and compensate the intrinsic latency of counting-based demodulation in dynamic conditions. Experimental results demonstrate that the proposed phase orthogonalization correction markedly suppresses zero-crossing timing jitter and enhances the stability of high-frequency pulse interpolation. Consequently, the overall demodulation error is reduced by more than 30 percent compared with existing methods, and the final angle error is maintained within 0.033°.