arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.14409cs.DCcs.AI
收藏

LS-CAT:一个大规模的CUDA AutoTuning数据集

LS-CAT: A Large-Scale CUDA AutoTuning Dataset

Norwegian University of Science and Technology (NTNU)(挪威科技大学)

Lars Bjertnes, Jacob O. Tørring, Anne C. Elster

摘要:

机器学习(ML)方法的有效性取决于对大型合适数据集的访问。在本文中,我们将介绍如何构建来自GitHub的LS-CAT(大规模CUDA自动调整)数据集,以训练基于NLP的ML模型。我们的数据集包括19683个专注于线性代数的CUDA内核。除了CUDA代码,我们的LS-CAT数据集包含5028536个相关的运行时,具有不同的内核,块大小和矩阵大小的组合。运行时是Nvidia GTX 980和Nvidia T4系统上的GPU基准。这些信息为基于NLP的模型找到源代码特性和线程块大小的最佳选择之间的相关性奠定了基础。从我们的LS-CAT数据库中可以得出几个结果。例如,在一个示例中,我们的实验结果表明,在平均情况下,线程块大小的最佳选择可以获得平均6%的增益。因此,我们还分析了一般情况下可以实现多大的性能提升,发现在10%的情况下,通过使用最佳块可以实现超过20%的性能提升。还包括对当前和未来工作的描述。

英文摘要:

The effectiveness of Machine Learning (ML) methods depend on access to large suitable datasets. In this article, we present how we build the LS-CAT (Large-Scale CUDA AutoTuning) dataset sourced from GitHub for the purpose of training NLP-based ML models. Our dataset includes 19 683 CUDA kernels focused on linear algebra. In addition to the CUDA codes, our LS-CAT dataset contains 5 028 536 associated runtimes, with different combinations of kernels, block sizes and matrix sizes. The runtime are GPU benchmarks on both Nvidia GTX 980 and Nvidia T4 systems. This information creates a foundation upon which NLP-based models can find correlations between source-code features and optimal choice of thread block sizes. There are several results that can be drawn out of our LS-CAT database. E.g., our experimental results show that an optimal choice in thread block size can gain an average of 6% for the average case. We thus also analyze how much performance increase can be achieved in general, finding that in 10% of the cases more than 20% performance increase can be achieved by using the optimal block. A description of current and future work is also included.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑