Xueming Li

Xueming Li

Auto-generated profile, based on publicly available information

Xueming Li

School of Integrated Circuits, Guangdong University of Technology, Guangzhou, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
3 February 2022 in IET Circuits, Devices & Systems
Verified
Journal Article
Open access
PDF file
XHXianghong Hu
Xianghong Hu
XLXueming Li
Xueming Li
XZXin Zheng
Xin Zheng
YLYuan Liu
Yuan Liu
XXXiaoming Xiong
Xiaoming Xiong
Elliptic curve cryptography (ECC), as one of the public key cryptography systems, has been widely applied to many security applications. It is challenging to implement a scalar multiplication (SM) operation which has the highest computational complexity in ECC. In this study, we propose a hardware processor which achieves high speed and high security for ECC. We first present a three‐clock cycle, divide‐and‐conquer multiplication algorithm which greatly reduces the number of execution cycles of multiplication. We then propose a dedicated multiplication hardware structure which reuses the multiplier and optimizes data path delay. To keep multiplication running in non‐idle status and executing in parallel with other modular operations, the operation scheduling of point addition and point doubling has been re‐designed and optimized based on an effective segmentation and pipeline strategy. Finally, under the premise of similar computing and hardware overhead, we propose an improved high‐security SM algorithm which involves random points to resist side‐channel attacks. On a 55 nm complementary metal oxide semiconductor application specific integrated circuit platform, the processor costs 463k gates and requires 0.028 ms for one SM. Our results indicate that the ECC processor is superior to other state‐of‐the‐art designs reported in the literature in terms of speed and area‐time product metrics.

11 February 2022 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
XHXianghong Hu
Xianghong Hu
XLXueming Li
Xueming Li
HHHongmin Huang
Hongmin Huang
XZXin Zheng
Xin Zheng
XXXiaoming Xiong
Xiaoming Xiong
Accelerators for convolutional neural networks (CNNs) based on field-programmable gate arrays (FPGAs) have drawn much attention in recent years. Two INT-8 multiplications are often implemented on a single digital signal processor (DSP) to improve DSP efficiency and performance. However, most of these works only use DSPs to implement multiplications and do not involve accumulations, which requires a lot of look-up tables (LUTs) and consequently leads to greater energy consumption. Furthermore, these works do not detail how to obtain two signed INT-8 multiplications with a DSP. This brief thus proposes a tiny accelerator for CNNs and a DSP-based processing element (PE) that is designed to implement two signed INT-8 multiply-and-accumulate (MAC) operations to reduce the overhead of LUTs. To allow the DSP to support two signed INT-8 MAC operations and avoid the large loss of accuracy caused by data overflow of partial sums (psum), we apply an efficient DSP optimization approach and a dynamic-precision quantization method. The accelerator is implemented on a Xilinx ZC706 FPGA device and achieves a DSP utilization efficiency $1.7\times $ to $7.3\times $ greater than state-of-the-art accelerators implemented on the same device. Furthermore, our accelerator offers $3.56\times $ greater energy efficiency than other FPGA-based accelerators.

26 August 2022 in Microelectronics Journal
Verified
Journal Article
Closed access
XLXueming Li
Xueming Li
HHHongmin Huang
Hongmin Huang
TCTaosheng Chen
Taosheng Chen
HGHuaien Gao
Huaien Gao
XHXianghong Hu
Xianghong Hu
XXXiaoming Xiong
Xiaoming Xiong

9 November 2023 in ACM Transactions on Embedded Computing Systems
Verified
Journal Article
Open access
XHXianghong Hu
Xianghong Hu
hongmin huanghongmin huang
hongmin huang
XLXueming Li
Xueming Li
XZXin Zheng
Xin Zheng
QRQinyuan Ren
Qinyuan Ren
XXXiaoming Xiong
Xiaoming Xiong
Deep convolutional neural networks (DNNs) have been widely used in many applications, particularly in machine vision. It is challenging to accelerate DNNs on embedded systems because real-world machine vision applications should reserve a lot of external memory bandwidth for other tasks, such as video capture and display, while leaving little bandwidth for accelerating DNNs. In order to solve this issue, in this study, we propose a high-throughput accelerator, called reconfigurable tiny neural network accelerator (ReTiNNA), for the bandwidth-limited system and present a real-time object detection system for the high-resolution video image. We first present a dedicated computation engine that takes different data mapping methods for various filter types to improve data reuse and reduce hardware resources. We then propose an adaptive layer-wise tiling strategy that tiles the feature maps into strips to reduce the control complexity of data transmission dramatically and to improve the efficiency of data transmission. Finally, a design space exploration (DSE) approach is presented to explore design space more accurately in the case of insufficient bandwidth to improve the performance of the low-bandwidth accelerator. With a low bandwidth of 2.23 GB/s and a low hardware consumption of 90.261K LUTs and 448 DSPs, ReTiNNA can still achieve a high performance of 155.86 GOPS on VGG16 and 68.20 GOPS on ResNet50, which is better than other state-of-the-art designs implemented on FPGA devices. Furthermore, the real-time object detection system can achieve a high object detection speed of 19 fps for high-resolution video.

20 November 2025 in Journal of Systems Architecture
Verified
Journal Article
Closed access
XLXueming Li
Xueming Li
JPJinhui Pan
Jinhui Pan
HHHongmin Huang
Hongmin Huang
YLYuanmiao Lin
Yuanmiao Lin
XHXianghong Hu
Xianghong Hu
XXXiaoming Xiong
Xiaoming Xiong

12 January 2026 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
YLYuanmiao Lin
Yuanmiao Lin
KLKelong Liang
Kelong Liang
PZPeng Zhang
Peng Zhang
ZZZijian Zhang
Zijian Zhang
XLXueming Li
Xueming Li
XXXiaoming Xiong
Xiaoming Xiong
Quantization and sparsity are key techniques for CNN compression and acceleration. Independent exploration of value-based sparsity (VBS) or bit-level sparsity (BLS) in 8b weights yield limited gains. We analyze weight distributions of VGG16 and ResNet50 after 4b quantization and find over 80% zero-values with strong near-structured sparsity. On VGG16, 98.11% of 16-weight groups contain at least 8 zero-values. Based on this analysis, we propose a two-stage sparse compression (TSSC) method that integrates VBS and BLS to efficiently compress weights. In stage 1, we apply post-quantization pruning to enforce structured sparsity with at least 8 zero-values per 16 weights and utilize value-based structured sparsity (VBSS) to compress these 8 zero-values per group. In stage 2, among the remaining weights, we apply column-based BLS (CBBLS) to further compress remaining weights. Finally, a two-stage sparse accelerator, which integrates the TSSC method and corresponding hardware optimization (hardware-efficient activation selection unit and bit-serial multiply-accumulate), is implemented to accelerate the CNN models. Experimental results demonstrate that our proposed TSSC method can reduce the weights of VGG16 and ResNet50 to 0.99b and 0.95b while maintaining an acceptable accuracy drop. When deployed on FPGA, our accelerator achieves an 8.08× weight compression and 7.13× performance improvement compared with 8b non-sparse VGG16 model. Compared with state-of-the-art accelerators, we achieve 1.95×-7.97×, 2.00×-32.8× and 1.13×-6.53× improvement in LUT efficiency, equivalent LUT efficiency and energy efficiency, respectively.