首页|New Findings from Beijing Institute of Technology in the Area of Machine Learning Described (Revisiting Thread Configuration of Spmv Kernels On Gpu: a Machine Learning Based Approach)
New Findings from Beijing Institute of Technology in the Area of Machine Learning Described (Revisiting Thread Configuration of Spmv Kernels On Gpu: a Machine Learning Based Approach)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Elsevier
Investigators discuss new findings in Machine Learning. According to news reporting out of Beijing, People’s Republic of China, by NewsRx editors, research stated, “Sparse matrix-vector multiplication (SpMV) optimization on GPUs has been challenging due to irregular memory accesses and unbalanced workloads. The majority of existing solutions assign a fixed number of threads to one or more rows of sparse matrices according to empirical formulas.” Financial support for this research came from National Natural Science Foundation of China (NSFC). Our news journalists obtained a quote from the research from the Beijing Institute of Technology, 99 “However, this method does not give the optimal thread configuration and results in a significant performance loss. This paper proposes a new machine learning-based thread assignment strategy for SpMV on GPU, predicting the near-optimal thread configuration for matrices. Further, we partition irregular sparse matrices into blocks according to the distribution of non-zero elements and predict the optimal thread configuration for each block. A new SpMV kernel is designed to accelerate the execution of different blocks. Experimental results show that our machine learning-based approach can select the near-optimal thread configuration for most matrices. The efficiency of SpMV for irregular matrices is also improved by matrix partitioning and blockwise prediction.”
BeijingPeople’s Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine LearningBeijing Institute of Technology
NETL
NSTL
Elsevier
