| Popis: |
As many scientific computation tasks focus on solving large-scale and computationally intensive problems, a wide range of problems involving High-Throughput Computing (HTC) paradigms and data-oriented algorithms emerge. To solve these problems, we review and recommend some simple workflows for users to bundle their serial or parallel jobs in this paper, including the native way with the Linux scheduler, the numactl method for processes or shared memory management, and the job array feature of job scheduler. We also introduce several convenient job bundling tools that TACC develops, such as ibrun, Launcher, Pylauncher, and Launcher-GPU. Some basic practice guidelines are added for users to choose appropriate workflows and tools when job bundling is required. |
