Developing → Developer Guide

The SUPReMM architecture comprises three major components.

• Software that runs directly on HPC compute nodes and periodically collects performance information.
• Software that uses the node-level performance data to generate job-level data.
• An Open XDMoD module that enables the job-level information to be viewed and analysed.

The Open XDMoD module is designed to support the ingestion and display of job-level performance data from a variety of sources including PCP, Prometheus, Cray RUR, and tacc_stats. The recommended data collection software is either PCP or Prometheus. The supported job summarization software is listed below.

Open XDMoD

The Open XDMoD core software and the Open XDMoD SUPReMM module source code are hosted on github.

• Open XDMoD core
• Open XDMoD SUPReMM module

Summarization Software

The job-level summarization software is available on GitHub.

• Job Summarization

PCP Software

• PCP community page

Prometheus

• Prometheus community page