Feb 2022 / Introduction to HPC (Winter Kickstart)

Winter Kickstart is a two × half day course for researchers to get started with high-performance computing (HPC) clusters. We will take you from being a new user to being competent to run your code at a larger scale than you could before. (However, we don’t cover application-specific matters beyond some Python/R/Matlab basics or focus on the high-performance part: but this is an easy next step after this course).

This course is good for any researcher who thinks they may need to scale up to larger resources in the next six months, in any field. Even if you don’t use computing clusters, you will be better prepared to understand how computing works on other systems. If you are a student, this is an investment in your skills. By the end of the course you get the hints, ready solutions and copy/paste examples on how to find, run and monitor your applications, and manage your data. In addition to how to optimize your workflow in terms of filesystem traffic, memory usage etc.

If you are at Aalto University: the course is obligatory for all new Triton users and recommended to all interested in the field.

This course is part of Scientific Computing in Practice lecture series at Aalto University.

Other universities

This course is hosted at Aalto University but put on in cooperation with many other universities. Anyone (even not at a partner site) could get something out of this course.

If you are not at Aalto University, you can follow along with the course and will learn many things anyway. The course is designed to be as useful to people outside of Aalto, but many of the examples won’t directly work on your cluster and you will need to adapt (we will mention these points where we know of them). Known sites hosting:

If you want to get your site listed here and/or help out, contact us via the CodeRefinery chat (#workshops stream). Our hints for other sites’ support staff are available.

Schedule

All times are EET (Europe/Helsinki time)!

THU-FRI 3-4.February, 12:00-16:00.

  • Wed, 2 February 2022 (mandatory for new Triton users)

    We strongly recommend that you join this day as well. This is a bigger-picture introduction.

  • Thu, 3 February 2022

    All times approximate, breaks every hour.

  • Fri, 4 February 2022

    All times approximate, breaks every hour.

    • 11:50 – 13:00: Simple parallelization with array jobs

    • 13:00 – 14:00: Using more than one CPU at the same time

    • 14:00 – 14:30: Laptops to Lumi, Jussi Enkovaara, CSC

      You now know of basics of using a computing cluster. What if you need more than what a university can provide? CSC (and other national computing centers) have even more resources, and this is a tour of them. Slides here.

    • 14:40 – 15:30: Running jobs that can utilize GPU hardware

    • 15:30 – 16:00: Questions to presenters

Practical information

The course is also streamed via Twitch (the CodeRefinery channel) so that anyone may follow along without registration. There are also Zoom breakout rooms/help sessions for those at partner universities. There is a HackMD link (collaborative edited notes) which is used for asking questions during the course.

Registration: Please register at this link

Instructors, organizers, contact: For additional info, email scip@aalto.fi

  • Richard Darst

  • Enrico Glerean

  • Simo Tuomisto

  • Jussi Enkovaara

  • … and you?

Preparation / prerequisites

Software installation

  • SSH client to connect to the cluster (+ be able to connect, see next point)

  • Zoom (if attending breakout rooms)

Cluster account and connection verification:

  • Access to your computer cluster.

  • Then, connect and get it working

    • Aalto (and possibly useful to others): try to connect to Triton to be ready. Come to the Wednesday session for help connecting (required).

Background knowledge: “A HPC cluster is easy to use if you know the Linux command line well”. A lot of this course is actually about getting comfortable with Linux so that you can use the cluster well.

Mental preparation: Online workshops can be a productive format, but it takes some effort to get ready. Browse these resources:

Community standards

We hope to make a good learning environment for everyone, and expect everyone to do their part for this. If there is anything we can do to support that, let us know.

If there is anything wrong, tell us right away - if you need to contact us privately, you can message the host on Zoom or contact us outside the course. This could be as simple as “speak louder / text on screen is unreadable / go slower” or as complex as “someone is distracting our group by discussing too advanced things”.

Material

See the schedule