Zhikuang Xin

Zhikuang Xin

Auto-generated profile, based on publicly available information

Zhikuang Xin

Computer Network Information Center, Chinese Academy of Sciences, Beijing, China

Research Focus & Metrics

Academic Career Length

4Years (2023-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
HZHaisha Zhao
Haisha Zhao
SLSan Li
San Li
JWJiaheng Wang
Jiaheng Wang
CZChunbao Zhou
Chunbao Zhou
Jue WangJue Wang
Jue Wang
Xuebin CHIXuebin CHI
Xuebin CHI
General-purpose Sparse Matrix-Matrix Multiplication (SpMM) is a fundamental kernel in scientific computing and deep learning. The emergence of new matrix computation units such as Tensor Cores (TCs) brings more opportunities for SpMM acceleration. However, in order to fully unleash the power of hardware performance, systematic optimization is required. In this paper, we propose Acc-SpMM, a high-performance SpMM library on TCs, with multiple optimizations, including data-affinity-based reordering, memory efficient compressed format, high-throughput pipeline, and adaptive sparsity-aware load balancing. In contrast to the state-of-the-art SpMM kernels on various NVIDIA GPU architectures with a diverse range of benchmark matrices, Acc-SpMM achieves significant performance improvements, on average 2.52x (up to 5.11x) speedup on RTX 4090, on average 1.91x (up to 4.68x) speedup on A800, and on average 1.58x (up to 3.60x) speedup on H100 over cuSPARSE.

11 November 2023
Verified
Conference Paper
Open access
SLShunde Li
Shunde Li
ZWZongguo Wang
Zongguo Wang
LBLingkun Bu
Lingkun Bu
Jue WangJue Wang
Jue Wang
ZXZhikuang Xin
Zhikuang Xin
Xuebin CHIXuebin CHI
Xuebin CHI
The Method Of Characteristic (MOC) to solve the Neutron Transport Equation (NTE) is the core of full-core simulation for reactors. High resolution is enabled by discretizing the NTE through massive tracks to traverse the 3D reactor geometry. However, the 3D full-core simulation is prohibitively expensive because of the high memory consumption and the severe load imbalance. To deal with these challenges, we develop ANT-MOC1. Specifically, we build a performance model for memory footprint, computation and communication, based on which a track management strategy is proposed to overcome the resolution bottlenecks caused by limited GPU memory. Furthermore, we implement a novel multi-level load mapping strategy to ensure load balancing among nodes, GPUs, and CUs. ANT-MOC enables a 3D full-core reactor simulation with 100 billion tracks on 16,000 GPUs, with 70.69% and 89.38% parallel efficiency for strong scalability and weak scalability, respectively.

27 July 2024
Verified
Book Chapter
Closed access
PDF file
ZXZhikuang Xin
Zhikuang Xin
ZWZhenghong Wu
Zhenghong Wu
DZDong Zhu
Dong Zhu
XWXiaoguang Wang
Xiaoguang Wang
Jue WangJue Wang
Jue Wang
YWYangang Wang
Yangang Wang

26 July 2026
Verified
Conference Paper
Open access
JGJunyu Gu
Junyu Gu
Jue WangJue Wang
Jue Wang
ZXZhikuang Xin
Zhikuang Xin
ZLZhiqiang Liang
Zhiqiang Liang
ZWZongguo Wang
Zongguo Wang
YWYangang Wang
Yangang Wang


25 September 2026 in ACM Transactions on Architecture and Code Optimization
Verified
Journal Article
Open access
JGJunyu Gu
Junyu Gu
Jue WangJue Wang
Jue Wang
ZXZhikuang Xin
Zhikuang Xin
CZChunbao Zhou
Chunbao Zhou
ZLZhiqiang Liang
Zhiqiang Liang
YWYangang Wang
Yangang Wang
Sparse matrix-dense matrix multiplication (SpMM) is a core operation in scientific computing and deep learning. On multi-GPU platforms, its scalability is limited by communication bottlenecks. To address this, we propose DistSpMM, a co-design framework integrating data layout, pipelining, and communication strategies. DistSpMM introduces HSDMA, a lightweight algorithm that reduces communication by optimizing the dense matrix allocation. DistSpMM features a topology-aware two-stage pipeline that manages the IB/NVLink bandwidth disparity to maximize the overlap of computation and communication. Finally, DistSpMM employs an adaptive selector that uses a performance model to dynamically choose the optimal communication granularity (coarse vs. fine-grained) based on data sparsity and network tier. Experiments on diverse real-world datasets demonstrate the superior performance of our method. It achieves average speedups of 1.6× to 2.6× in single-node multi-GPU environments and 4.0× to 5.1× in multi-node multi-GPU environments over the baseline. Compared to the best state-of-the-art implementations, our method delivers up to 2.0× speedup.