Training courses

Want to get started with our systems but lack the necessary knowledge? We regularly organize hands-on systems training courses at our offices in Utrecht and Amsterdam or in situ at your education or research institution. Have a look at the overview and let us know which training course you are interested in by emailing us at training@surfsara.nl.

General

Introduction to Big Data and Hadoop

Duration: 2 half-days

Content: You'll get an introduction to Big Data, followed by information on the history of Hadoop and a general explanation of how it works. Without going into technical detail, we set out the benefits of and need for MapReduce, Pig, Apache Hive, HBase, YARN, CAP Theorem, Lambda Architecture and NoSQL. Examples of best and bad practices in terms of use provide a clearer understanding of applications.

Target group: Anyone who would like an overall, comprehensive overview of Big Data analysis and Hadoop but does not have a technical background.

Technical

Introduction to Unix

Duration: 2 hours

Content: You'll learn about the structure of Unix operating systems and the basic commands. You'll practice working with the command line and giving a number of commands.

Target group: Anyone who wants to have sufficient basic knowledge of Unix to be able to work with it on the national compute cluster Lisa or on the Cartesius supercomputer, for example. You are familiar with the Windows or OS X operating systems.

Introduction to MPI

Duration: 2 days

Content: You'll learn how Message Passing Interface (MPI) works. This is a standard which facilitates communication between processes, making it easier to program (large-scale) parallel computers. We explain both the basic principles (send, receive and broadcast) and more advanced topics. On both days you'll gain experience yourself through practical exercises.

Target group: Anyone who would like to find out how MPI works so that they can work with it themselves. You have experience of the programming languages C or Fortran.

Introduction to Intel Xeon Phi training

Duration: 1 half-day

Content: You'll learn to work with Intel Xeon Phi, coprocessors which significantly improve the performance of applications through parallel processing. The national compute cluster Lisa includes Intel Xeon Phi processors. You'll learn through practical tasks.

Target group: Anyone who would like to find out how Intel Xeon Phi coprocessors work so that they can work with them themselves. You are familiar with the Unix command line and have experience of the programming languages C or Fortran.

Introduction to GPU programming

Duration: 1 half-day

Content: You'll find out how NVIDIA GPUs and CUDA interact and you'll be introduced to a number of different parallel programming techniques. You'll learn to work with existing libraries which use GPU acceleration. You'll be given practical examples of most techniques, including GPU programming models such as OpenACC.

Target group: Anyone who would like to find out how GPUs work so that they can work with them themselves. You are familiar with the basics of programming and the Unix command line. You are familiar with the Unix command line and have experience of the programming languages C or Fortran.

Introduction to Visualisation

Duration: 1 half-day

Content: The concept of visualising scientific data will be explained. Visualisation gives you insights into remarkable phenomena in data and helps you check the accuracy of the results and present and communicate results in an understandable manner. You can, for example, display your research results using remote visualisation, where datasets are too big and complex to be visualised locally (on your own laptop). Different types of data require different visualisation methods, techniques and tools. You'll be given examples of 2D and 3D simulations, geographical data and networks. The visualisations comprise images and video materials and even interactive visualisations on the web. You'll practice with existing research data but you can also bring your own data with you.

Target group: Anyone who would like to find out how visualisation helps in understanding research data. You are familiar with scientific research.

Systems training

Getting started with HPC Cloud

Duration: 1 day

Content: You'll learn to work with SURFsara's HPC Cloud. The course includes everything from logging in to the virtual environment via OpenNebula to running a simple MPI program and the execution of distributed processes. You'll perform practical tasks on the HPC Cloud and set up a cluster yourself.

Target group: Anyone who would like to get started with HPC Cloud. You are familiar with the basics of programming and the Unix command line.

Getting started with the Hadoop cluster

Duration: 1 day

Content: You'll learn how to work with SURFsara's Hadoop cluster. And how to compute using MapReduce, Apache Spark, Hive, Pig and HBase. You'll practice on the Hadoop cluster yourself and locally on a virtual machine (VM).

Target group: Anyone who would like to get started with the Hadoop cluster so that they can perform Big Data analyses. You are familiar with the basics of programming and the Unix command line.

Getting started with Grid computing

Duration: 1 day

Content: You'll learn how to work with SURFsara's Grid computing clusters and the associated data storage systems. You'll gain an overview of the basic concepts of Grid computing such as parallelizing on the Grid, task distribution, monitoring and data management. This course is also available online and you can complete it in your own time.

Target group: Anyone who would like to get started with Grid computing. You are familiar with the basics of programming and the Unix command line.

Getting started with the Cartesius supercomputer and the national compute cluster Lisa

Duration: 1 half-day

Content: You'll learn how to work with the Cartesius supercomputer and the national compute cluster Lisa. We explain when you need the supercomputer and what applications feature on the Lisa cluster. This hands-on course includes both an interactive part on the login nodes and a batch part on the worker nodes. You will use capability and capacity cluster computers.

Target group: Anyone who would like to get started with Cartesius and Lisa. You are familiar with the basics of programming and the Unix command line.

Getting started with iRODS and EUDAT data management

Duration: 2 days

Content: You'll learn how to set up a data management infrastructure with applications such as iRODS (Integrated Rule-Oriented Data System) and PIDs (persistent identifiers). Through use cases you'll gain an understanding of how they work. You'll also practice with the applications yourself on virtual machines. We also present EUDAT (European Data Infrastructure)'s data management services.

Target group: Anyone who would like to get started with data management applications. You are familiar with the basics of programming and the Unix command line.