Xiang Fei

Xiang Fei

Auto-generated profile, based on publicly available information

Xiang Fei

Department of Computer Science and Technology, Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
20 February 2024
Verified
Conference Paper
Open access
MPMeng Pang
Meng Pang
XFXiang Fei
Xiang Fei
PQPeng Qu
Peng Qu
YZYouhui Zhang
Youhui Zhang
ZLZhaolin Li
Zhaolin Li
Sparse-Matrix Dense-Matrix Multiplication (SpMM) and Sampled Dense Dense Matrix Multiplication (SDDMM) are important sparse kernels in various computation domains. The uneven distribution of nonzeros in the sparse matrix and the tight data dependence between sparse and dense matrices make it a challenge to run sparse matrix multiplication efficiently on GPUs. By analyzing the aforementioned problems, we propose a row decomposition (RoDe)-based approach to optimize the two kernels on GPUs, using the standard Compressed Sparse Row (CSR) format. Specifically, RoDe divides the sparse matrix rows into regular parts and residual parts, to fully optimize their computations separately. We also devise the corresponding load balancing and finegrained pipelining technologies. Profiling results show that RoDe can achieve more efficient memory access and reduce warp stall cycles significantly. Compared to the state-of-the-art (SOTA) alternatives, RoDe achieves a speedup of up to 7.86× with a geometric mean of 1.45× for SpMM, and a speedup of up to 8.99× with a geometric mean of 1.49× for SDDMM; the dataset is SuiteSparse. RoDe also outperforms its counterpart in the deep learning dataset. Furthermore, its preprocessing overhead is significantly smaller, averaging only 16% of the SOTA.

11 May 2020 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
PQPeng Qu
Peng Qu
YZYouhui Zhang
Youhui Zhang
XFXiang Fei
Xiang Fei
WZWeimin Zheng
Weimin Zheng
Spiking neural network (SNN) is the most commonly used computational model for neuroscience and neuromorphic computing communities. It provides more biological reality and possesses the potential to achieve high computational power and energy efficiency. However, prior simulation frameworks of SNN on GPGPUs suffer from insufficient parallelism exploration, irregular memory access, and load imbalance because of the special properties of SNN. In this paper, we propose specific optimization methods to speed up the SNN simulation on GPGPU. Firstly, we propose a fine-grained network representation as a flexible and compact intermediate representation (IR) for SNNs. Secondly, we propose the cross-population/-projection parallelism exploration to make full use of GPGPU resources. Thirdly, sparsity aware load balance is proposed to deal with the activity sparsity, which is one of the main behavioral characteristics of SNN. Finally, we further provide dedicated optimization to support multiple GPGPUs. Accordingly, BSim, a code generation framework for high-performance simulation of SNN on GPGPUs is also proposed. Tests show that, compared to a state-of-the-art SNN simulator GeNN on GPGPU, BSim achieves 1.41∼9.33× speedup for SNNs with different configurations; it outperforms other simulators much more.

14 December 2021 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
JHjianqiang huang
jianqiang huang
HWHaojie Wang
Haojie Wang
XFXiang Fei
Xiang Fei
XWXiaoying Wang
Xiaoying Wang
WCWenguang Chen
Wenguang Chen
In this paper, we build a $TC$ - $Stream$ , a high-performance graph processing system specific for a triangle counting algorithm on graph data with up to tens of billions of edges, which significantly exceeds the device memory capacity of Graphics Processing Units (GPUs). The triangle counting problem is a broad research topic in data mining and social network analysis in the graph processing field. As the scale of the graph data grows, a portion of the graph data must be loaded iteratively. In the existing literature, graphs with billions of edges need to be done distributively, which is cost-intensive. Also, many disk-based triangle counting systems are proposed for CPU architectures, but their tackling performances are inefficient. To solve the above problem, we propose $TC$ - $Stream$ , and it focuses on three issues: 1) For power-law graphs, because the amount of tasks of each vertex or edge is inconsistent, it is bound to cause different demands of computing and memory resources for different task types. We propose a parallel vertex approach and the reordering of vertices for graph data that can be placed in the GPU device memory to ensure the maximum workload balancing; 2) A binary-search-based set intersection method is designed to achieve the maximum parallelism in GPU; 3) For the graph data that exceeds the GPU device memory capacity, we develop a novel vertical partition algorithm to guarantee the independent computing on each partition so that the three computation processes, i.e., the computation on GPU, the data transmission between main memory of CPU and SSD, and the communication between the CPU and the GPU can be perfectly overlapped. Moreover, the $TC$ - $Stream$ optimizes edge-iterator models and benefits from multi-thread parallelism. Extensive experiments conducted on large-scale datasets showed that the $TC$ - $stream$ running on a single Tesla V100 GPU performs $2.4-6\times$ and $1.8-4.4\times$ faster than the state-of-the-art single-machine in-memory triangle counting system and GPU-based triangle counting system, respectively, and achieves $2.4\times$ faster than the state-of-the-art out-of-core distributed system PDTL running on an 8-node cluster when processing the graph data with 42.5 billion edges, which demonstrates the high performance and cost-effectiveness of the $TC$ - $Stream$ .

1 June 2021 in Tsinghua Science and Technology
Verified
Journal Article
Closed access
XFXiang Fei
Xiang Fei
YZYouhui Zhang
Youhui Zhang
WZWeimin Zheng
Weimin Zheng

1 January 2007 in Acta Physica Sinica
Verified
Journal Article
Open access
PDF file
ZYZhang Yonghui
Zhang Yonghui
CAChang An-Bi
Chang An-Bi
XFXiang Fei
Xiang Fei
FSFalun Song
Falun Song
QKQiang Kang
Qiang Kang
GSGong Sheng-Gang
Gong Sheng-Gang
采用静电场模拟对二极管结构及导引磁场位形分布进行了优化设计,并在20GW脉冲功率源上进行了重复频率运行实验研究,二极管输出电子束电压超过1MV,电流达20kA,脉冲宽度45ns,重复频率100Hz,达到了设计指标.

28 January 2026
Verified
Conference Paper
Open access
HBHaodong Bian
Haodong Bian
YZYouhui Zhang
Youhui Zhang
XFXiang Fei
Xiang Fei
JHjianqiang huang
jianqiang huang
XWXiaoying Wang
Xiaoying Wang