Scientific Computing in Practice: Summer Kickstart 2017

Part of Scientific Computing in Practice lecture series at Aalto University.

Audience: Aalto employees and students looking for an extensive intro into computational resources available to Aalto people.

About the course: three days kickstart for Aalto researchers to get started with the available HPC computational resources at Aalto and CSC. The course is modular, we cover one by one several aspects. First day dedicated to the HPC in principle: one will get whole picture what computational resources are available in particular what is HTCondor, what CSC has to offer and for sure a Triton cluster at Aalto. The day two is focused on Triton usage practicalities, given in the hands-on style tutorial, there will be lot of practical things that you end up trying on your own on Triton. The third day, the last one, is more advanced, with the practical examples in Matlab, R, software installation and development, debugging and profiling tools.

Overall we give you hints, ready solutions and copy/paste examples on how to compile, run and monitor your applications. In addition to how to optimize your workflow in terms of filesystem traffic, memory usage etc.

The course is obligatory for all new Triton users and recommended to all interested in the field.

Time, date: Mon 5.6 — Wed 7.6.2017, from 10:00 – 15:30 all days

Place (MIND THE CHANGE): Otaniemi

  • Mon and Tue: T1 (T-building, Konemiehentie 2)
  • Wed: NOKIA (main building, Otakaari 1)

Days’ time schedule is flexible, here is the tentative plan. 30 minutes break around 12:00, plus short 10 minutes breaks in between. You will be given time to try and ask, it’s more like an informal help session to get you started with computing resources.

BTW, HPC stands for High Performance Computing

Day #1:

  • Module #1.1 (1.5h): HPC crash course: what is behind the front-end // lecture

HPC fundamentals: terminology, architectures, interconnects, infrastructure behind, as well as MPI vs shared memory // Ivan Degtyarenko

HPC fundamentals (PDF)

  • Module #1.2 (0.5h): Triton — the cluster at Aalto // lecture with demos

About Science IT, accessing the cluster, getting help, cluster hardware and networking // Ivan Degtyarenko

Triton overview (PDF)

  • Module #1.3 (1h): CSC resources overview // lecture with demos

An overview of CSC computing environment // Atte Sillanpää

CSC Kickoff 2017 (PDF)

  • Module #1.4 (1h): Cloud computing at CSC // lecture with demos

Cloud computing services, cPouta and ePouta, at  CSC // Kalle Happonen

CSC IaaS Cloud Platforms (PDF)

  • Module #1.5 (1h): HTCondor setup at Aalto // lecture with demos

Did you know that department workstations around could be accessible for computing? It is were HTCondor comes in game // Jari Varje

HTCondor kickstart (PDF), HTCondor examples (.zip)

Day #2:

  • Module #2.1 (2h): Getting started on Triton, SLURM basics // tutorial

Triton’s workflow, running and monitoring serial jobs on Triton. Interactively and in batch mode. // Richard Darst

Getting started, Slurm basics (PDF)

  • Module #2.2 (1h): “module load …” // tutorial

Cluster software, toolchains with “module” // Simo Tuomisto

Environment Modules (PDF)

  • Module #2.3 (0.5h): $WRKDIR and other work spaces // tutorial

IO issues, type of storages on Triton, best practices  // Richard Darst

Storage (PDF), Data management (PDF)

  • Module #2.4 (1.5h): SLURM advances // tutorial

Running in parallel with MPI and OpenMP, array jobs, gres resources including GPU // Janne Blomqvist

SLURM advanced (HTML link)

Day #3:

  • Module #3.0 (0.5h): Troubleshooting: solving running jobs issues.

Possible issues on Triton and how to resolve them. The session will include hands-on tutorial from the “SLURM advances” // Janne Blomqvist

Troubleshooting on Triton (HTML link)

  • Module #3.1 (1.5h): Code building on Triton // tutorial

Building your software on Triton // Janne Blomqvist

Bulding a code on Triton

  • Module #3.2 (1h): Matlab case // live demos

Matlab as a use case. Live examples from the real project running on Triton // Enrico Glerean

Matlab demo by Enrico (link to GitLab)

  • Module #3.3 (0.5h): R case  // live demos

R as a tool for data analysis // Simo Tuomisto

R slides (PDF, external link)

  • Module #3.4 (0.5h): Deep Learning case // live demos

Several Deep Learning tools examples // Simo Tuomisto

Deep Learning slides (PDF, external link)

Other material (included only if we have time):

  • Version Control

Short intro into why Git is important for all your work  // Richard Darst

  • Profiling and debugging tools on Triton // live demos

Several tools for code profiling and debugging [see link for reference] // Janne Blomqvist

Lectures:

Aalto: Janne Blomqvist (D. Sc.),  Ivan Degtyarenko (D. Sc.), Simo Tuomisto, Richard Darst (D. Sc.), Jari Varje (doctoral candidate), Enrico Glerean (D.Sc.)

CSC: Atte Sillanpää (D. Sc.), Kalle Happonen (M. Sc.)

Cost: Free of charge for Aalto employees and students.

Registration: The course is over.

Credits (opintopisteet): Full course hours correspond roughly to 1 ECTS. Requires all three days attendance plus homework. Homework to be returned by Fri 16.6, SCIP2017 Kickstart homework (PDF).

Other comments: Day 2 and 3 parts will include live examples, demos and hands-on tutorials. Participants will be provided with access to Triton for running examples. Participants are expected to bring their laptops with the pre-installed SSH client, configured for using WiFi (preferably Eduroam, otherwise Aalto or Aalto Open).

Additional course info at: Ivan Degtyarenko, ivan.degtyarenko at aalto.fi