Regional Centre for Accelerator based Particle Physics - RECAPP

Harish-Chandra Research Institute,

An Aided Institute of The Department of Atomic Energy, Govt. of India

BACK

How to use Recapp’s HPC Cluster

Using a High Performance Computing Cluster such as the RECAPP’s HPC Cluster requires at a minimum some basic understanding of the Linux Operating System.

It is outside the scope of this manual to explain Linux commands and/or how parallel programs work. This manual simply explains how to run jobs on the HPC cluster.

When you login you are connected to what is called a Master/ Head node. The HPC Cluster has several major components:

  • Login/ Head Node
  • Compute Nodes

Login/ Head Node: This is the first  node you get when you first log into HPC. This node is meant for simple tasks such as submitting jobs, checking on job status, editing (emacs, vi). This runs all of the critical cluster  services.

Compute nodes: These are the workhorse of the cluster. For computational work both Serial or Parallel, in Batch mode or Interactive mode, you will be using the compute nodes.