当前位置: X-MOL 学术Computing › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Comparison of analytical and ML-based models for predicting CPU–GPU data transfer time
Computing ( IF 3.7 ) Pub Date : 2020-01-08 , DOI: 10.1007/s00607-019-00780-x
Ali Riahi , Abdorreza Savadi , Mahmoud Naghibzadeh

The overhead of data transfer to the GPU poses a bottleneck for the performance of CUDA programs. The accurate prediction of data transfer time is quite effective in improving the performance of GPU analytical modeling, the prediction accuracy of kernel performance, and the composition of the CPU with the GPU for solving computational problems. For estimating the data transfer time between the CPU and the GPU, the current study employs three machine learning-based models and a new analytical model called $$\lambda $$λ-Model. These models run on four GPUs from different NVIDIA architectures and their performance is compared. The practical results show that the $$\lambda $$λ-Model is able to anticipate the transmission of large-sized data with a maximum error of 1.643%, which offers better performance than that of machine learning methods. As for the transmission of small-sized data, machine learning-based methods provide better performance and a predicted data transfer time with a maximum error of 4.52%. Consequently, the current study recommends a hybrid model, that is, the $$\lambda $$λ-Model for large-sized data and machine learning tools for small-sized data.

中文翻译:

用于预测 CPU-GPU 数据传输时间的分析模型和基于 ML 的模型的比较

向 GPU 传输数据的开销对 CUDA 程序的性能构成了瓶颈。数据传输时间的准确预测对于提高GPU分析建模的性能、内核性能的预测精度以及CPU与GPU的组合解决计算问题等方面都非常有效。为了估计 CPU 和 GPU 之间的数据传输时间,当前的研究采用了三个基于机器学习的模型和一个名为 $$\lambda $$λ-Model 的新分析模型。这些模型在来自不同 NVIDIA 架构的四个 GPU 上运行,并比较了它们的性能。实际结果表明,$$\lambda $$λ-Model 能够以 1.643% 的最大误差预测大数据的传输,性能优于机器学习方法。对于小规模数据的传输,基于机器学习的方法提供更好的性能和预测的数据传输时间,最大误差为 4.52%。因此,目前的研究推荐了一种混合模型,即用于大数据的 $$\lambda $$λ-Model 和用于小数据的机器学习工具。
更新日期:2020-01-08
down
wechat
bug