YGYu Gong

Yu Gong

*This is an algorithmically generated author record based on publicly available information.

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


Yu Gong has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Crane: Inter-Layer Scheduling Framework for DNN Inference and Training Co-Support on Tiled Architecture

    by Yu Gong, Lingyi Huang, Haodong Chang, Rongjian Liang, Cheng Yang, Zhexiang Tang, Jiang Hu, Bo Yuan


  • Co-Exploring Structured Sparsification and Low-Rank Tensor Decomposition for Compact DNNs

    by Yang Sui, Miao Yin, Yu Gong, Bo Yuan

    Sparsification and low-rank decomposition are two important techniques to compress deep neural network (DNN) models. To date, these two popular yet distinct approaches are typically used in separate ways; while their efficient integration for better compression performance is little explored, especially for structured sparsification and decomposition. In this article, we perform systematic co-exploration on structured sparsification and decomposition toward compact DNN models. We first investigate and analyze several important design factors for joint structured sparsification and decomposition, including operational sequence, decomposition format, and optimization procedure. Based on the observations from our analysis, we then propose CEPD, a unified DNN compression framework that can co-explore the benefits of structured sparsification and tensor decomposition in an efficient way. Empirical experiments demonstrate the promising performance of our proposed solution. Notably, on the CIFAR-10 dataset, CEPD brings 0.72%–0.45% accuracy increase over the baseline ResNet-56 and MobileNetV2 models, respectively, and meanwhile, the computational costs are reduced by 43.0%–44.2%, respectively. On the ImageNet dataset, our approach can enable 0.10%–1.39% accuracy increase over the baseline ResNet-18 and ResNet-50 models with 59.4%–54.6% fewer parameters, respectively.


  • Open Access

    Invited: Algorithm and Hardware Co-Design for Energy-Efficient Neural SLAM

    by Lingyi Huang, Cheng Yang, Yu Gong, Yang Sui, Xiao Zang, Anthony Goeckner, Qi Zhu, Bo Yuan

    In this paper, we introduce a novel approach to enhancing neural network-based Simultaneous Localization and Mapping (SLAM) through the integration of model compression techniques and customized hardware architecture that focuses on micro-architectural and dataflow optimizations to improve computational efficiency and performance. Experiments across different scenarios demonstrate that the proposed approach achieves significant improvement.


  • Open Access

    ETTE: Efficient Tensor-Train-based Computing Engine for Deep Neural Networks

    by Yu Gong, Miao Yin, Lingyi Huang, Jinqi Xiao, Yang Sui, Chunhua Deng, Bo Yuan

    Tensor-train (TT) decomposition enables ultra-high compression ratio, making the deep neural network (DNN) accelerators based on this method very attractive. TIE, the state-of-the-art TT based DNN accelerator, achieved high performance by leveraging a compact inference scheme to remove unnecessary computations and memory access. However, TIE increases memory costs for stage-wise intermediate results and additional intra-layer data transfer, leading to limited speedups even the models are highly compressed. To unleash the full potential of TT decomposition, this paper proposes ETTE, an algorithm and hardware co-optimization framework for Efficient Tensor-Train Engine. At the algorithm level, ETTE proposes new tensor core construction and computation ordering mechanism to reduce stage-wise computation and storage cost at the same time. At the hardware level, ETTE proposes a lookahead-style across-stage processing scheme to eliminate the unnecessary stage-wise data movement. By fully leveraging the decoupled input and output dimension factors, ETTE develops an efficient low-cost memory partition-free access scheme to efficiently support the desired matrix transformation. We demonstrate the effectiveness of ETTE via implementing a 16-PE hardware prototype with CMOS 28nm technology. Compared with GPU on various workloads, ETTE achieves 6.5× − 253.1× higher throughput and 189.2× − 9750.5× higher energy efficiency. Compared with the state-of-the-art DNN accelerators, ETTE brings 1.1× − 58.3×, 2.6× − 1170.4× and 1.8× − 2098.2× improvement on throughput, energy efficiency and area efficiency, respectively.


  • Algorithm and Hardware Co-Design of Energy-Efficient LSTM Networks for Video Recognition with Hierarchical Tucker Tensor Decomposition

    by Yu Gong, Miao Yin, Lingyi Huang, Chunhua Deng, Bo Yuan

    Long short-term memory (LSTM) is a type of powerful deep neural network that has been widely used in many sequence analysis and modeling applications. However, the large model size problem of LSTM networks make their practical deployment still very challenging, especially for the video recognition tasks that require high-dimensional input data. Aiming to overcome this limitation and fully unlock the potentials of LSTM models, in this paper we propose to perform algorithm and hardware co-design towards high-performance energy-efficient LSTM networks. At algorithm level, we propose to develop fully decomposed hierarchical Tucker (FDHT) structure-based LSTM, namely FDHT-LSTM, which enjoys ultra-low model complexity while still achieving high accuracy. In order to fully reap such attractive algorithmic benefit, we further develop the corresponding customized hardware architecture to support the efficient execution of the proposed FDHT-LSTM model. With the delicate design of memory access scheme, the complicated matrix transformation can be efficiently supported by the underlying hardware without any access conflict in an on-the-fly way. Our evaluation results show that both the proposed ultra-compact FDHT-LSTM models and the corresponding hardware accelerator achieve very high performance. Compared with the state-of-the-art compressed LSTM models, FDHT-LSTM enjoys both order-of-magnitude reduction (more than $1000 \times$ ) in model size and significant accuracy improvement (0.6% to 12.7%) across different video recognition datasets. Meanwhile, compared with the state-of-the-art tensor decomposed model-oriented hardware TIE, our proposed FDHT-LSTM architecture achieve $2.5\times$ , $1.46\times$ and $2.41\times$ increase in throughput, area efficiency and energy efficiency, respectively on LSTM-Youtube workload. For LSTM-UCF workload, our proposed design also outperforms TIE with $1.9\times$ higher throughput, $1.83\times$ higher energy efficiency and comparable area efficiency.


  • Management Technology of Virtual Watchman in Power Plant Based on Expert Knowledge Base

    by Yu Gong, Yingdong Ni, Hao Zhang, Zhidong Wang

    In the future, a large-scale centralized control center will be planned to manage multiple storage hydropower stations. Under this circumstance, the existing operation monitoring technology has been unable to meet the future demand of “one seat with multiple plants”. Aiming at this goal, this paper proposes a virtual watchman system with expert knowledge base as the core to replace or assist watchman. This article first classified the alarm signals of the alarm stations, and used the expert knowledge base established on the original historical alarm information database to analyze and filter the system alarm information. At the same time, the virtual watchman system realizes the assistance of all stages of early warning, processing and recovery before and after the fault, and reduces the burden on the watchman. Then for the monitoring work, the operation situation of the relevant equipment of the unit was monitored by means of area scanning. In addition, the multi-service interface designed for the virtual watchman system can greatly improve the efficiency of business processing during the handover of power plant personnel.