Empirical performance modeling of GPU kernels using active learning
Empirical performance modeling of GPU kernels using active learning
复制标题
使用主动学习对 GPU 内核进行经验性能建模
DOI：
10.3233/978-1-61499-381-0-646
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Stefan M. Wild
中科院分区：
文献类型：
--
作者：
Prasanna Balaprakash;K. Rupp;A. Mametjanov;R. Gramacy;P. Hovland;Stefan M. Wild
我们专注于开发GPU内核经验性能模型的实验设计方法。最近，我们开发了一种迭代主动学习算法，该算法可以自适应地选择批次中的参数配置，以在CPU体系结构上同时评估，以便在参数空间上构建性能模型。在本文中，我们说明当无法进行并发评估时，该算法的采用是在没有GPU簇的情况下特别有用的。我们介绍了有关算法的实证研究，该算法对各种GPU内核和硬件。我们表明，即使无法进行并发评估，该算法的默认批处理模式也会产生更好的模型，并且迭代的主动学习算法也减少了获得GPU内核获得高质量经验性能模型所需的总体时间。
We focus on a design-of-experiments methodology for developing empirical performance models of GPU kernels. Recently, we developed an iterative active learning algorithm that adaptively selects parameter configurations in batches for concurrent evaluation on CPU architectures in order to build performance models over the parameter space. In this paper, we illustrate the adoption of the algorithm when concurrent evaluations are not possible, which is particularly useful in the absence of GPU clusters. We present an empirical study of the algorithm on a diverse set of GPU kernels and hardware. We show that even when concurrent evaluations are not possible, the default batch mode of the algorithm yields better models and the iterative active learning algorithm reduces the overall time required to obtain high-quality empirical performance models for GPU kernels.