Introduction to High-Performance and Parallel Computing

This module provides a comprehensive overview of high-performance computing (HPC) for non-computer scientists. Participants will gain practical skills in Linux environments, bash scripting, and accessing remote systems. They will also learn about the components of a high-performance distributed computing system and receive support for academic credit.

This module delves into the nuts and bolts of HPC, covering HPC architecture, software, allocations, node types, and job submission using Slurm. Participants will gain practical experience in submitting jobs and understanding the intricacies of HPC architecture and job submission.

Participants will explore basic parallelism in this module, including simple application timing, serial vs. parallel processing, parallel memory models, and high throughput computing. They will gain insights into the differences between serial and parallel processing and understand the concepts of data vs. task parallelism.

This module focuses on evaluating parallel program performance by covering topics such as parallelizing code, speedup, efficiency, scalability, and limits to scaling. Participants will engage in strong and weak scaling studies to quantify the performance of parallel programs.