@article{ZHOU2024, 
author = {Tianyang ZHOU and Qinglin WANG and Rongchun LI and Songzhu MEI and Shangfei YIN and Ruochen HAO and Jie LIU},
title = {Optimizing Yinyang K-means algorithm on many-core CPUs},
year = {2024},
journal = {Journal of National University of Defense Technology},
volume = {46},
number = {1},
pages = {93-102},
keywords = {K-means, NUMA, vectorization, many-core CPU, performance optimization},
url = {https://www.sciopen.com/article/10.11887/j.cn.202401010},
doi = {10.11887/j.cn.202401010},
abstract = {Traditional Yinyang K-means algorithm is computationally expensive when dealing with large-scale clustering problems. An efficient parallel acceleration implementation of Yinyang K-means algorithm was proposed on the basis of the architectural characteristics of typical many-core CPUs. This implementation was based on a new memory data layout, used vector units in many-core CPUs to accelerate distance calculation in Yinyang K-means, and targeted memory access optimization for NUMA (non-uniform memory access) characteristics. Compared with the open source multi-threaded version of Yinyang K-means algorithm, this implementation can achieve the speedup of up to 5.6 and 8.7 approximately on ARMv8 and x86 many-core CPUs, respectively. Experiments show that the optimization successfully accelerate Yinyang K-means algorithm in many-core CPUs.}
}