Gain insights into using HPC systems and supercomputers to solve large computational problems. Explore HPC components, software stacks, job schedulers, and parallel programming, including Open MP, MPI, and GPU coding.

Learn to use High Performance Computing (HPC) Systems  and solve large computational problems.  This course assumes basic familiarity with the Bash command line environment found on GNU/Linux and other Unix-like environments. This course is of the first of its kind, should be your second step from my previous Educative course "Learn to Analyze Text Data in Bash Shell and Linux"

You'll learn:
- Intro to HPC Systems and Supercomputers
- HPC system's basic components
- HPC software stack
- HPC job schedulers and batch systems (PBS and Slurm with demos)
- Introduction to parallel programming (Open MP, MPI and GPU coding)

Video demos are included, I think it is a must have course for students, researchers, big data analysts, and developers. It will help you to utilize High Performance Computing systems at your institution. Non-interactive course. More details at:  www.scientificprogramming.io/learn-hpc

Ajay Shenoy

This course demystifies HPC and introduces you to the essential tools required to schedule and run parallel programs. Easy to understand.

India

Learn to Use HPC Systems and Supercomputers

A MPI job can considered as a cross-node and multi-process job. Sample Slurm MPI job script would look like below:

#!/bin/bash
#SBATCH --job-name=MyJob
#SBATCH --account=username
#SBATCH --ntasks=32
#SBATCH --ntasks-per-node=16
#SBATCH --cpus-per-tasks=1

module load openmpi
mpiexec <program>

The script above tells Slurm that this is a **multi-processing** job. It requests a total of 32 MPI processes (`ntasks=32`). It will launch 16 MPI processess (`ntasks-per-node=16`) on each node (it implicitly requested 2 nodes). For each MPI process, it needs 1 cpu core to handle (`cpus-per-task=1`).

Supercomputers and HPC clusters

Components of a HPC system

HPC software stack

PBS - Portable Batch System

SLURM -Workload Manager

Parallel programming - OpenMP

Parallel programming - MPI

Parallel programming - GPU and CUDA

Conclusions and references

Slurm distrbuted MPI and GPU jobs