Virtual Savant For The Heterogeneous Computing Scheduling Problem
PROCEEDINGS 2018 INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING & SIMULATION (HPCS)(2018)
摘要
A key issue when using distributed computing environments is finding a planning strategy to execute tasks in order to use the computational resources efficiently. This article presents the application of Virtual Savant to solve the heterogeneous computing scheduling problem, a widely-studied problem with several real-world applications. Virtual Savant is a novel method that uses machine learning techniques to automatically generate programs that can be executed in parallel to solve a given problem. Experimental analysis is performed on a set of problem instances generated following methodologies from the related literature. Results show that Virtual Savant is able to outperform MinMin, a well-known heuristic for the studied problem, by up to 15% while showing good scalability properties when increasing the number of computing resources and the dimension of the problem instances.
更多查看译文
关键词
virtual savant, scheduling, machine learning, optimization, automatic program generation
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要