Description: This hands-on course is designed for researchers who want to take their high-performance computing (HPC) workflows to the next level. Whether you're new to large-scale computing or looking to optimize your current practices, this course will guide you through the key steps to efficiently scale your applications on HPC systems.
Participants will begin by identifying their specific applications and learn how to properly compile their code for HPC environments. The course covers essential topics including running interactive sessions, performance tuning, and efficient batch job submission—complete with practical script examples. You’ll also explore strategies for checkpointing, monitoring job progress, and effective debugging techniques.
Through a combination of lectures and hands-on exercises, this course offers real-world insights into improving performance, reducing run times, and making the most of shared computing resources. By the end, you'll be equipped with the tools and knowledge needed to run scalable, reliable, and efficient HPC workflows.
Teachers: Sergey Maschenko (SHARCNET, McMaster University) and Jaime Pinto (SciNet, University of Toronto)
Level: Introductory
Format: Lecture + Hands-on
Certificate: Attendance
Prerequisites: None