Wei Shi

Wei Shi

Auto-generated profile, based on publicly available information

Wei Shi

College of Computer Science and Technology, National University of Defense Technology, Changsha, China

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
22 August 2023 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
ZYZhijie Yang
Zhijie Yang
LWLei Wang
Lei Wang
WSWei Shi
Wei Shi
YWYao Wang
Yao Wang
JTJunbo Tie
Junbo Tie
WXWeixia Xu
Weixia Xu
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.

10 December 2021
Verified
Conference Paper
Open access
JDJunquan Deng
Junquan Deng
WSWei Shi
Wei Shi
JHJian Hu
Jian Hu
XJXianlong Jiao
Xianlong Jiao
We consider the mobile localization problem in future millimeter-wave wireless networks with distributed Base Stations (BSs) based on multi-antenna channel state information (CSI). For this problem, we propose a Semi-supervised t-distributed Stochastic Neighbor Embedding (St-SNE) algorithm to directly embed the high-dimensional CSI samples into the 2D geographical map. We evaluate the performance of St-SNE in a simulated urban outdoor millimeter-wave radio access network. Our results show that St-SNE achieves a mean localization error of 6.8 m with only 5% of labeled CSI samples in a 200×200 m 2 area with a ray-tracing channel model. St-SNE does not require accurate synchronization among multiple BSs, and is promising for future large-scale millimeter-wave localization.

30 September 2023 in Journal of Computer Science and Technology
Verified
Journal Article
Closed access
PDF file
ZKZiyang Kang
Ziyang Kang
SLShi-Ming Li
Shi-Ming Li
SWShi-Ying Wang
Shi-Ying Wang
LQLian-Hua Qu
Lian-Hua Qu
RGRui Gong
Rui Gong
LWLei Wang
Lei Wang

1 January 2008
Verified
Conference Paper
Closed access
LMLai Mingche
Lai Mingche
GLGao Lei
Gao Lei
SWShi Wei
Shi Wei
ZWZhi-Ying Wang
Zhi-Ying Wang
The virtual channel flow control approach provides an efficient way for the high throughput of the on-chip routers. However, allocating the virtual channels (VCs) statically results in a waste of the area and energy consumption. To remedy this drawback, we propose a novel dynamic virtual channel architecture (DVCA) in this paper. By inspecting the physical link state and speculating the packet transferring, it dispenses a variable number of VCs to escape the head-of line (HOL) blockings to maximize the throughput, and avoids the useless VC allocations to reduce the packet latencies. In its implementation, the VC allocation unit, the switch allocation unit as well as the VC control unit are modified to complete the DVCA router design. Then, under the 90nm CMOS process, the proposed routers using 50% buffers provide 6.2% throughput increase and 4.1% latency decrease averagely with the savings of 30.9% area and 31.3% power consumption compared to traditional routers.

31 March 2020 in arXiv
Verified
Preprint
Open access
PDF file
SLShiming Li
Shiming Li
SGShasha Guo
Shasha Guo
LZLimeng Zhang
Limeng Zhang
ZKZiyang Kang
Ziyang Kang
SWShiying Wang
Shiying Wang
WXWeixia Xu
Weixia Xu
Spiking neural network (SNN), as the third generation of artificial neural networks, has been widely adopted in vision and audio tasks. Nowadays, many neuromorphic platforms support SNN simulation and adopt Network-on-Chips (NoC) architecture for multi-cores interconnection. However, interconnection brings huge area overhead to the platform. Moreover, run-time communication on the interconnection has a significant effect on the total power consumption and performance of the platform. In this paper, we propose a toolchain called SNEAP for mapping SNNs to neuromorphic platforms with multi-cores, which aims to reduce the energy and latency brought by spike communication on the interconnection. SNEAP includes two key steps: partitioning the SNN to reduce the spikes communicated between partitions, and mapping the partitions of SNN to the NoC to reduce average hop of spikes under the constraint of hardware resources. SNEAP can reduce more spikes communicated on the interconnection of NoC and spend less time than other toolchains in the partitioning phase. Moreover, the average hop of spikes is reduced more by SNEAP within a time period, which effectively reduces the energy and latency on the NoC-based neuromorphic platform. The experimental results show that SNEAP can achieve 418x reduction in end-to-end execution time, and reduce energy consumption and spike latency, on average, by 23% and 51% respectively, compared with SpiNeMap.

1 October 2019
Verified
Conference Paper
Closed access
ZCZhang Chen
Zhang Chen
WSWei Shi
Wei Shi
QZQiang Zhou
Qiang Zhou
In this paper, a novel adaptive difference-coarray-based source enumeration (ADC-SE) method is introduced to address the number detection problem for general coherent signals. For decorrelation, the covariance matrix of the observed signals received by the uniform linear array (ULA) can be converted into the difference coarray domain with two different strategies. We find the distribution characteristic of the eigenvalue descending ratios (EDR), which are calculated from coarray data with different strategies, can be utilized to promote the detection accuracy and reliability performances of the eigenvalue-based source enumeration (EV-SE) method. In addition, the proposed method can also predict the correlation conditions of the signal sources. Numerical simulations verify that the proposed method exhibits better detection accuracy and reliability than the traditional methods under different signal conditions. Due to its demonstrated advantages, the ADC-SE method is a promising and competitive approach for practical source enumeration, especially for the coherent sources detection scenarios.