《2016 New Challenges of Parallel Job Scheduling》.pdf

New Challenges of Parallel Job Scheduling Eitan Frachtenberg1 and Uwe Schwiegelshohn2 1 Powerset, Inc. eitan@ 2 Robotics Research Institute, University Dortmund, Otto-Hahn-Strasse 8, 44221 Dortmund, Germany uwe.schwiegelshohn@ Abstract. The workshop on job scheduling strategies for parallel pro- cessing (JSSPP) studies the myriad aspects of managing resources on parallel and distributed computers. These studies typically focus on large-scale computing environments, where allocation and management of computing resources present numerous challenges. Traditionally, such systems consisted of massively parallel supercomputers, or more recently, large clusters of commodity processor nodes. These systems are charac- terized by architectures that are largely homogeneous and workloads that are dominated by both computation and communication-intensive appli- cations. Indeed, the large majority of the articles in the first ten JSSPP workshops dealt with such systems and addressed issues such as queuing systems and supercomputer workloads. In this paper, we discuss some of the recent developments in parallel computing technologies that depart from this traditional domain of prob- lems. In particular, we identify several recent and influential technologies that could have a significant impact on the future of research on parallel scheduling. We discuss some of the more specific research challenges that these technologies introduce to the JSSPP community, and propose to enhance the scope of future JSSPP workshops to include these topics.