Rui Gong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rui Gong has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Lei Wang
National Innovation Institute of Defense Technology, Academy of Military Science, Beijing, China
6 shared publications - Zhijie Yang
National Innovation Institute of Defense Technology, Academy of Military Science, Beijing, China
5 shared publications - Chao Xiao
National University of Defense Technology
4 shared publications - Weixia Xu
National University of Defense Technology
3 shared publications - Xun Xiao
National University of Defense Technology
3 shared publications - Junbo Tie
National university of defense technology, Changsha, China
2 shared publications
Latest Publications
- Open Access
- 5 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 23 (4) , 1-26
NeuroComp: A Cross-Platform Compiler for Efficient SNN Deployment on Neuromorphic Hardware
Spiking Neural Networks (SNNs) offer substantial energy efficiency advantages, yet deploying them across diverse neuromorphic hardware remains challenging. Existing toolchains exhibit a critical tradeoff: platform-specific frameworks lack portability, while low-level programming interfaces demand extensive hardware expertise and produce non-portable code. Furthermore, conventional deep learning compilers fail to handle the unique temporal dynamics of SNNs and the idiosyncratic constraints of neuromorphic architectures. To bridge this gap, we present NeuroComp , a cross-platform compiler that automatically generates functionally correct and high-performance code for heterogeneous neuromorphic backends. Our core insight is that the diverse execution behaviors of neuromorphic hardware can be universally modeled as parallelizable scalar computations expressible via nested loops. Building on this, NeuroComp introduces a unified multi-level loop abstraction to systematically align SNN computational semantics with hardware capacities. To efficiently navigate the vast implementation space, we propose a decoupled two-stage scheduling strategy. The first stage performs batch partitioning to guarantee functional correctness and strict architectural compliance, while the second stage optimizes inter-batch execution orders for maximum data reuse, guided by lightweight, hardware-specific cost models and heuristic pruning. We evaluate NeuroComp on three representative architectural paradigms: an instruction-extended CPU, a dedicated accelerator, and a many-core hardware. Experimental results demonstrate that NeuroComp consistently achieves competitive performance compared to meticulously hand-optimized implementations and significantly outperforms existing generic automated compilers, effectively minimizing development effort while unlocking cross-platform portability.
- 5 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Architecture and Code Optimization
- Vol. 23 (4) , 1-26
Open AccessNeuroComp: A Cross-Platform Compiler for Efficient SNN Deployment on Neuromorphic Hardware
Spiking Neural Networks (SNNs) offer substantial energy efficiency advantages, yet deploying them across diverse neuromorphic hardware remains challenging. Existing toolchains exhibit a critical tradeoff: platform-specific frameworks lack portability, while low-level programming interfaces demand extensive hardware expertise and produce non-portable code. Furthermore, conventional deep learning compilers fail to handle the unique temporal dynamics of SNNs and the idiosyncratic constraints of neuromorphic architectures. To bridge this gap, we present NeuroComp , a cross-platform compiler that automatically generates functionally correct and high-performance code for heterogeneous neuromorphic backends. Our core insight is that the diverse execution behaviors of neuromorphic hardware can be universally modeled as parallelizable scalar computations expressible via nested loops. Building on this, NeuroComp introduces a unified multi-level loop abstraction to systematically align SNN computational semantics with hardware capacities. To efficiently navigate the vast implementation space, we propose a decoupled two-stage scheduling strategy. The first stage performs batch partitioning to guarantee functional correctness and strict architectural compliance, while the second stage optimizes inter-batch execution orders for maximum data reuse, guided by lightweight, hardware-specific cost models and heuristic pruning. We evaluate NeuroComp on three representative architectural paradigms: an instruction-extended CPU, a dedicated accelerator, and a many-core hardware. Experimental results demonstrate that NeuroComp consistently achieves competitive performance compared to meticulously hand-optimized implementations and significantly outperforms existing generic automated compilers, effectively minimizing development effort while unlocking cross-platform portability.
- Open Access
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Factored Floating-Point MAC: Eliminating Redundant Normalization for Energy-Efficient Systolic Arrays
- 26 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessFactored Floating-Point MAC: Eliminating Redundant Normalization for Energy-Efficient Systolic Arrays
- Open Access
- 25 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
A2SPM: A Memory Access Acceleration for Neuromorphic Processing with the SPM
Owing to their low power consumption and high energy efficiency, neuromorphic processors have found extensive applications across various intelligent computing domains, including artificial intelligence (AI) and low-power edge computing. Homogeneous neuromorphic processors demonstrate a unique integration of general-purpose computing versatility and neuromorphic computing acceleration capabilities. These processors effectively address the intensive memory access demands inherent in neuromorphic computing through the implementation of tightly coupled local memory, specifically Scratchpad Memory (SPM). This paper presents the design of SPM-based memory access acceleration mechanisms, which have been specifically developed and optimized to accommodate the data characteristics and computational processes of typical Spiking Neural Networks (SNNs). The proposed scheme significantly enhances computational efficiency by reducing both memory access operations and computational instruction processing. Comparative performance evaluations reveal that the proposed design achieves a 28.99% speedup in Liquid State Machine operations and a 14.95% speedup in Spiking Convolutional Neural Network computations when benchmarked against a baseline homogeneous processor equipped with SPM.
- 25 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
Open AccessA2SPM: A Memory Access Acceleration for Neuromorphic Processing with the SPM
Owing to their low power consumption and high energy efficiency, neuromorphic processors have found extensive applications across various intelligent computing domains, including artificial intelligence (AI) and low-power edge computing. Homogeneous neuromorphic processors demonstrate a unique integration of general-purpose computing versatility and neuromorphic computing acceleration capabilities. These processors effectively address the intensive memory access demands inherent in neuromorphic computing through the implementation of tightly coupled local memory, specifically Scratchpad Memory (SPM). This paper presents the design of SPM-based memory access acceleration mechanisms, which have been specifically developed and optimized to accommodate the data characteristics and computational processes of typical Spiking Neural Networks (SNNs). The proposed scheme significantly enhances computational efficiency by reducing both memory access operations and computational instruction processing. Comparative performance evaluations reveal that the proposed design achieves a 28.99% speedup in Liquid State Machine operations and a 14.95% speedup in Spiking Convolutional Neural Network computations when benchmarked against a baseline homogeneous processor equipped with SPM.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (5) , 1442-1455
Hierarchical Mapping of Large-Scale Spiking Convolutional Neural Networks Onto Resource-Constrained Neuromorphic Processor
Neuromorphic processors have been designed as nonvon Neumann systems for energy-efficient spiking neural network (SNN) execution. Spiking convolutional neural networks (SCNNs), combining the advantage of convolutional neural network (CNN) and SNN, have been widely applied to vision tasks. However, as the scale of SCNNs increases, executing large-scale SCNNs on resource-constrained neuromorphic processor faces many challenges, including massive synapse pruning, caused by resource competition, execution performance degradation, etc. Addressing these problems, we propose an efficient approach to map large-scale SCNNs onto resource-constrined neuromorphic processor. The approach consists of three steps: 1) splitting; 2) partitioning; and 3) mapping. We explore three acyclic splitting strategies to divide large-scale SCNNs into subnetworks without cyclic dependency. Axon sharing is the guiding principle to partition subnetworks into multiple clusters. To obtain an optimal cluster-to-core mapping scheme, we use nondominated sorting genetic algorithm to collaboratively optimize two metrics. We evaluate our approach with eight realistic SCNN applications. The results show that compared with existing state-of-the-art methods, our approach significantly reduces the synapse pruning and accuracy loss, and increases the execution performance.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (5) , 1442-1455
Hierarchical Mapping of Large-Scale Spiking Convolutional Neural Networks Onto Resource-Constrained Neuromorphic Processor
Neuromorphic processors have been designed as nonvon Neumann systems for energy-efficient spiking neural network (SNN) execution. Spiking convolutional neural networks (SCNNs), combining the advantage of convolutional neural network (CNN) and SNN, have been widely applied to vision tasks. However, as the scale of SCNNs increases, executing large-scale SCNNs on resource-constrained neuromorphic processor faces many challenges, including massive synapse pruning, caused by resource competition, execution performance degradation, etc. Addressing these problems, we propose an efficient approach to map large-scale SCNNs onto resource-constrined neuromorphic processor. The approach consists of three steps: 1) splitting; 2) partitioning; and 3) mapping. We explore three acyclic splitting strategies to divide large-scale SCNNs into subnetworks without cyclic dependency. Axon sharing is the guiding principle to partition subnetworks into multiple clusters. To obtain an optimal cluster-to-core mapping scheme, we use nondominated sorting genetic algorithm to collaboratively optimize two metrics. We evaluate our approach with eight realistic SCNN applications. The results show that compared with existing state-of-the-art methods, our approach significantly reduces the synapse pruning and accuracy loss, and increases the execution performance.
- 30 September 2023
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 38 (5) , 1098-1112
Path-Based Multicast Routing for Network-on-Chip of the Neuromorphic Processor
- 30 September 2023
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 38 (5) , 1098-1112
Path-Based Multicast Routing for Network-on-Chip of the Neuromorphic Processor
- 22 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 34 (11) , 2910-2927
Back to Homogeneous Computing: A Tightly-Coupled Neuromorphic Processor With Neuromorphic ISA
In recent years, neuromorphic processors are widely used in many scenarios, showing extreme energy efficiency over traditional architectures. However, almost all existing neuromorphic hardware are following the heterogeneous computing methodology without Instruction Set Architecture (ISA), leading to inflexibility in programming. In this paper, we first propose a RISC-V Neuromorphic Extension (RVNE) to enable fine-grained and flexible homogeneous programming for neuromorphic algorithms while utilizing SNN sparsity from different levels of granularity and computing flows. Based on RVNE, we next implement a neuromorphic micro-architecture that is tightly coupled to the CPU pipeline to accelerate neuromorphic computing. To demonstrate the proposed homogeneous neuromorphic architecture, we implement a prototype processor called NeuroRVcore based on RISC-V ISA and an open-source RISC-V core. The evaluation results show that RVNE achieves a 2.8 × −4.3 × reduction in code density compared with the general-purpose ISAs. Compared with the state-of-the-art neuromorphic processor, the proposed homogeneous computing reduces energy consumption by 3.4%−22.5% while enabling fine-grained and flexible homogeneous programming.
- 22 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Parallel and Distributed Systems
- Vol. 34 (11) , 2910-2927
Back to Homogeneous Computing: A Tightly-Coupled Neuromorphic Processor With Neuromorphic ISA
In recent years, neuromorphic processors are widely used in many scenarios, showing extreme energy efficiency over traditional architectures. However, almost all existing neuromorphic hardware are following the heterogeneous computing methodology without Instruction Set Architecture (ISA), leading to inflexibility in programming. In this paper, we first propose a RISC-V Neuromorphic Extension (RVNE) to enable fine-grained and flexible homogeneous programming for neuromorphic algorithms while utilizing SNN sparsity from different levels of granularity and computing flows. Based on RVNE, we next implement a neuromorphic micro-architecture that is tightly coupled to the CPU pipeline to accelerate neuromorphic computing. To demonstrate the proposed homogeneous neuromorphic architecture, we implement a prototype processor called NeuroRVcore based on RISC-V ISA and an open-source RISC-V core. The evaluation results show that RVNE achieves a 2.8 × −4.3 × reduction in code density compared with the general-purpose ISAs. Compared with the state-of-the-art neuromorphic processor, the proposed homogeneous computing reduces energy consumption by 3.4%−22.5% while enabling fine-grained and flexible homogeneous programming.
- 13 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 14, 1-8
Local Sharing Method of Accounting Information Based on Optimized Security FOA Algorithm
In order to improve the efficiency of accounting information management and realize the local sharing of accounting information, this paper proposes a local sharing method of accounting information based on optimized fruit fly optimization algorithm (FOA). On the basis of constructing the accounting information sharing model by using the optimized FOA algorithm, the importance evaluation index of local accounting information sharing is set up. Then, in the value identification process of accounting information sharing, FOA information sharing management process is improved according to the needs of different levels of information users, and then the local sharing of accounting information is realized in a modular manner. Experiments show that this method has high practicability, its sharing process is less time-consuming, and the basic carrier capacity of the sharing platform is improved.
- 13 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 14, 1-8
Local Sharing Method of Accounting Information Based on Optimized Security FOA Algorithm
In order to improve the efficiency of accounting information management and realize the local sharing of accounting information, this paper proposes a local sharing method of accounting information based on optimized fruit fly optimization algorithm (FOA). On the basis of constructing the accounting information sharing model by using the optimized FOA algorithm, the importance evaluation index of local accounting information sharing is set up. Then, in the value identification process of accounting information sharing, FOA information sharing management process is improved according to the needs of different levels of information users, and then the local sharing of accounting information is realized in a modular manner. Experiments show that this method has high practicability, its sharing process is less time-consuming, and the basic carrier capacity of the sharing platform is improved.
- 3 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6, 1217-1221
Research on teaching quality evaluation model of online courses in Colleges and Universities
Through the research on the classification of knowledge points of online courses, the current online teaching quality evaluation has some problems, such as unscientific evaluation index weight, imperfect evaluation system and so on, The deep learning model is applied to the research of text and image classification and recognition of online course evaluation indicators. By collecting the latest research results of big data analysis model for teaching quality evaluation of relevant online courses, By mapping big data models to research objectives, Using the analytic hierarchy process to preliminarily determine the weight index. At last, The big data analysis model is proposed to be applied to the online course evaluation system structure and the online course evaluation index system.
- 3 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 6, 1217-1221
Research on teaching quality evaluation model of online courses in Colleges and Universities
Through the research on the classification of knowledge points of online courses, the current online teaching quality evaluation has some problems, such as unscientific evaluation index weight, imperfect evaluation system and so on, The deep learning model is applied to the research of text and image classification and recognition of online course evaluation indicators. By collecting the latest research results of big data analysis model for teaching quality evaluation of relevant online courses, By mapping big data models to research objectives, Using the analytic hierarchy process to preliminarily determine the weight index. At last, The big data analysis model is proposed to be applied to the online course evaluation system structure and the online course evaluation index system.
- 1 March 2017
- Published by American Scientific Publishers in Nanoscience and Nanotechnology Letters
- Vol. 9 (3) , 310-315
Hyperbranched Polyamine as Nano-Plugging Agent Used in Water-Based Drilling Fluid
According to self-condensing vinyl polymerization, a hyperbranched polyamine can be synthesized by divinyl sulfone, piperazine, diethylenetriamine, following the approach of A2 + B2 + BB'4. It has been characterized by FT-IR, TGA and phase analysis light scanning. The average particle size of hyperbranched polyamine (HBPA) was 45.9 nm. HBPA has an excellent thermal stability, which can be used to high temperature deep well drilling proccess. HBPA as a nano-plugging agent has been applied successfully in water-based drilling fluid system to plug nanopores in shale formation. HBPA has little effect on water-based drilling fluid rheological properties. With the increase in HBPA amount, the FLAPI and FLHTHP decreased dramatically. When the HBPA is greater than 1.0 wt%, plugging rate of water-based drilling fluid for artificial core is close to 100% and the permeability recovery value can reach 99.5%, proving that HBPA has an excellent plugging performance.
- 1 March 2017
- Published by American Scientific Publishers in Nanoscience and Nanotechnology Letters
- Vol. 9 (3) , 310-315
Hyperbranched Polyamine as Nano-Plugging Agent Used in Water-Based Drilling Fluid
According to self-condensing vinyl polymerization, a hyperbranched polyamine can be synthesized by divinyl sulfone, piperazine, diethylenetriamine, following the approach of A2 + B2 + BB'4. It has been characterized by FT-IR, TGA and phase analysis light scanning. The average particle size of hyperbranched polyamine (HBPA) was 45.9 nm. HBPA has an excellent thermal stability, which can be used to high temperature deep well drilling proccess. HBPA as a nano-plugging agent has been applied successfully in water-based drilling fluid system to plug nanopores in shale formation. HBPA has little effect on water-based drilling fluid rheological properties. With the increase in HBPA amount, the FLAPI and FLHTHP decreased dramatically. When the HBPA is greater than 1.0 wt%, plugging rate of water-based drilling fluid for artificial core is close to 100% and the permeability recovery value can reach 99.5%, proving that HBPA has an excellent plugging performance.
- 5 January 2008
- Published by Springer Nature in Journal of Electronic Testing
- Vol. 24 (1) , 57-65
A New Approach to Single Event Effect Tolerance Based on Asynchronous Circuit Technique
- 5 January 2008
- Published by Springer Nature in Journal of Electronic Testing
- Vol. 24 (1) , 57-65
A New Approach to Single Event Effect Tolerance Based on Asynchronous Circuit Technique