Running Jobs#
Running jobs efficiently is at the heart of a successful experience with our High-Performance Computing (HPC) cluster. This section outlines the essential aspects of executing various types of jobs, understanding the queuing system, and troubleshooting.
Understanding the Queuing System#
Learn how our job scheduler manages the distribution of computational tasks.
Job Queues: Overview of different job queues.
Job Status: Monitoring and understanding job states.
See also
Job Scheduling Policies and Priorities#
Gain insights into how jobs are prioritized and scheduled within the system.
Policies: The rules governing job scheduling.
Priorities: How job priority is determined.
See also
Interactive and Batch Mode#
Run jobs interactively or submit batch scripts for later execution.
Interactive Jobs: Immediate execution and feedback.
Batch Jobs: Using scripts to manage longer-running jobs.
Working with GPUs#
Harness the power of GPUs for computation-intensive tasks.
GPU Job Submission: Submitting jobs to GPU-enabled nodes.
Monitoring GPU Usage: Tools and commands to monitor GPU resources.
See also
Recurring Jobs#
Set up and manage recurring jobs that run on a schedule.
Creating Recurring Jobs: How to define and manage repeating tasks.
Modifying Recurring Jobs: Adjusting existing recurring jobs.
See also
Debugging and Troubleshooting Jobs#
Find solutions and get help with common job-related issues.
Common Errors: Solutions to typical problems.
Advanced Debugging Tools: Utilizing professional debugging techniques.
Running jobs smoothly is key to productive research and development. Explore these topics to understand and make the most of our robust computing infrastructure. If you need assistance, our support team is available at rchelp@northeastern.edu or consult our Frequently Asked Questions (FAQs).
Happy computing!