Yingcheng Xu

Yingcheng Xu

Auto-generated profile, based on publicly available information

Yingcheng Xu

China National Institute of Standardization, Beijing 100191, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
28 February 2025
Verified
Conference Paper
Open access
JSJinliang Shi
Jinliang Shi
SLSHIGANG LI
SHIGANG LI
YXYouxuan Xu
Youxuan Xu
RFRongtian Fu
Rongtian Fu
XWXueying Wang
Xueying Wang
TWTong Wu
Tong Wu
Sparse Matrix-matrix Multiplication (SpMM) and Sampled Dense-dense Matrix Multiplication (SDDMM) are important sparse operators in scientific computing and deep learning. Tensor Core Units (TCUs) enhance modern accelerators with superior computing power, which is promising to boost the performance of matrix operators to a higher level. However, due to the irregularity of unstructured sparse data, it is difficult to deliver practical speedups on TCUs. To this end, we propose FlashSparse, a novel approach to bridge the gap between sparse workloads and the TCU architecture. Specifically, FlashSparse minimizes the sparse granularity for SpMM and SDDMM on TCUs through a novel swap-and-transpose matrix multiplication strategy. Benefiting from the minimum sparse granularity, the computation redundancy is remarkably reduced while the computing power of TCUs is fully utilized. Besides, FlashSparse is equipped with a memory-efficient thread mapping strategy for coalesced data access and a sparse matrix storage format to save memory footprint. Extensive experimental results on H100 and RTX 4090 GPUs show that FlashSparse sets a new state-of-the-art for sparse matrix multiplications (geometric mean 5.5x speedup over DTC-SpMM and 3.22x speedup over RoDe).

1 July 2020 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
Ying LiYing Li
Ying Li
LHLei Han
Lei Han
XNXiuli Ning
Xiuli Ning
YXYingcheng Xu
Yingcheng Xu
Frequent fire incidents on electric bicycles; have brought great harm to consumers’ personal and property safety. This article sort and analyze the data, combine the collected accident reports of electric bicycles. Due to the incompleteness of the data, this article use Bayesian Network to construct the Bayesian network topology model of electric bicycles fire risk, use fuzzy set theory to solve Fuzzy computing the language discussed by experts. Finally, the fuzzy Bayesian theory is used to calculate the example, and the fire risk of the electric bicycle in the example is low. This method provides a reference for the accident investigation and analysis of electric bicycles.

1 November 2019 in IOP Conference Series: Materials Science and Engineering
Verified
Conference Paper
Open access
PDF file
WQWu Qian
Wu Qian
Chaowei WangChaowei Wang
Chaowei Wang
FPFei Pei
Fei Pei
XYXu Yingcheng
Xu Yingcheng
LXLu Xiaowei
Lu Xiaowei
On the basis of factors influencing the evaluation of equipment transportation efficiency, such as safety, timeliness, universality and economy of system analysis, and in combination with the basic theory of Analytic Hierarchy Process (AHP), this paper sorted out the main steps for evaluation of equipment transportation efficiency, established the hierarchical chart for evaluation index of equipment transportation efficiency, proposed a comprehensive evaluation model of equipment transportation efficiency based on AHP, and verified the feasibility of this model through the specific cases. The comprehensive evaluation model of equipment transportation efficiency based on AHP proposed by this paper provides a method for the decision makers to select the optimal design scheme for equipment transportability, and lays a foundation for related studies of equipment transportability.

4 February 2020
Verified
Book Chapter
Closed access
PDF file
YLYing Li
Ying Li
XLXiaowei Lu
Xiaowei Lu
LHLei Han
Lei Han
YXYingcheng Xu
Yingcheng Xu
XNXiuli Ning
Xiuli Ning

1 July 2020 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
LYLi Ya
Li Ya
SHSong Heliang
Song Heliang
XYXu Yingcheng
Xu Yingcheng
In this paper, research and analysis have been carried out on the theories related to Internet + government service data quality. Based on the principles of scientificity, systematicness, development, and operability, an Internet + government service data quality assessment index system suitable for China’s big data era has been proposed, this index system is proposed from five aspects: inherent quality of data, quality of data expression, system-related scenario quality, utility quality of data, and user experience quality of data. The analytic hierarchy process method has been used to analyze the relationship between indexes at the criterion layer, the sub-criterion layer and the objective layer, and the weights of the data quality assessment indexes at each layer were determined. The method proposed in this paper provides an idea for the assessment of government service data quality and has certain practical significance, laying a theoretical foundation for the related work of Internet + government service data quality assessment.

12 January 2020
Verified
Book Chapter
Closed access
PDF file
YXYingcheng Xu
Yingcheng Xu
FPFei Pei
Fei Pei
QWQian Wu
Qian Wu
BLBisong Liu
Bisong Liu