云上深度学习作业弹性训练的最优资源分配器
An Optimal Resource Allocator of Elastic Training for Deep Learning Jobs on Cloud
摘要：
云培训平台，如亚马逊网络服务和华为云，为用户提供计算资源，以训练他们的深度学习工作。弹性培训是一种嵌入在云培训平台中的服务，可以动态地增加或减少分配给作业的资源。弹性训练系统的核心技术是在异构作业之间最佳分配有限的资源，以缩短作业延迟和提高训练效率。本文提出了一种用于弹性训练系统的最优资源分配器，该资源分配器利用混合整数规划（MIP）模型来最大化深度学习任务的训练进度。我们利用华为云深度学习训练平台ModelArts获得的真实作业数据，进行仿真实验，将最优资源分配器与贪婪资源分配器作为基准进行比较。数值实验结果表明，相对于贪婪资源分配器，该分配器可以将排队时间减少32%，训练效率提高24%，从而极大地改善了用户使用华为ModelArts的体验，并有可能实现更高的产品利润。此外，最优资源分配器的决策速度很快，平均只需0.4秒。
英文摘要：
Cloud training platforms, such as Amazon Web Services and Huawei Cloud provide users with computational resources to train their deep learning jobs. Elastic training is a service embedded in cloud training platforms that dynamically scales up or down the resources allocated to a job. The core technique of an elastic training system is to best allocate limited resources among heterogeneous jobs in terms of shorter queueing delay and higher training efficiency. This paper presents an optimal resource allocator for elastic training system that leverages a mixed-integer programming (MIP) model to maximize the training progress of deep learning jobs. We take advantage of the real-world job data obtained from ModelArts, the deep learning training platform of Huawei Cloud and conduct simulation experiments to compare the optimal resource allocator with a greedy one as benchmark. Numerical results show that the proposed allocator can reduce queuing time by up to 32% and accelerate training efficiency by up to 24% relative to the greedy resource allocator, thereby greatly improving user experience with Huawei ModelArts and potentially enabling the realization of higher profits for the product. Also, the optimal resource allocator is fast in decision-making, taking merely 0.4 seconds on average.
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。
