Research Computing Services Course Week
Twice a year, the USIT Research Computing Services (RCS) group (gruppe for Vitenskapelig Databehandling (VD)) conduct an intensive training week for all Notur and local users. The event is free of charge, and unless otherwise noted there is no registration.
Topics rage from beginner level programming and system usage, Titan workshops, to advanced topics. We are happy to welcome two external speakers, Xing Cai from Simula who will be lecturing on parallel programming and Johan Simon Seland from Sintef who will hold a workshop on GPU programming.
The courses are held between November 14 and 17, 2011 in Ole-Johan Dahls hus and Kristen Nygaards hus.
| time | title | lecturer | description |
|---|---|---|---|
|
Monday November 14 - beginners day- Ole-Johan Dahls hus, Prolog |
|||
| 9:15-10:15 | Programming with Perl | Katerina Michalickova |
Description: This course is suitable for complete beginners as an introduction to programming with Perl examples. Target audience: Scientists who do not program but would like to learn |
| 10:30-11:30 | Introduction to Python | Dmytro Karpenko |
Description: Introduction to the Python programming language. Target audience: Scientists who do not program but would like to learn |
| 12:30-14:00 | Introduction to R | Bjørn-Helge Mevik |
Description: Introduction to the R system,reading and saving data, plotting and analysing data, running R scripts. Target audience: R novices |
| 14:15-15:45 | Programming with R | Bjørn-Helge Mevik |
Description: Manipulating data, writing functions and scripts in R, dos and don'ts. Target audience: People who have used R or programmed a little, or that have taken the Introduction to R lecture. |
|
Tuesday November 15 - Titan day - Ole-Johan Dahls hus, Prolog |
|||
| 9:15-10:15 | Introduction to Titan | Katerina Michalickova |
Description: Introduction to the computer cluster Titan that is the principal scientific computational resource at the University of Oslo. The course is aimed at people with a modest (to none) background in UNIX and parallel computing and includes very simple examples. However, by the end of the lecture you will have a basic working knowledge of Titan and will be able to submit simple jobs. Target audience: Users with a modest (to none) background in UNIX and parallel computing |
| 10:30-11:30 | Titan job submission system | Simen Gaure |
Description: In-depth explanation of the Titan job submission system SLURM. Good knowledge of SLURM parameters enables users to write more efficient job scripts. Target audience: Scientists who already use Titan. |
| 12:30-13:30 | Intermediate bash shell scripting | Andreas Buzh Skau |
Description:Intermediate to advanced concepts in bash shell scripting. In Titan context, better knowledge of bash scripting will enable users to write more flexible job scripts. Target audience: Scientists with some knowledge of bash scripting |
| 13:45-14:30 | Titan job scripts | Katerina Michalickova |
Description: Simple to complicated examples of Titan job scipts with explanation. Target audience: Titan users |
| 14:45-15:45 | Titan IO | Ole Widar Saastad |
Description: Introduction of the data transfer aspects of using Titan. The lecture helps scientists with managing their data on Titan in the most efficient manner. Target audience: Titan users |
|
Wednesday November 16 - advanced day - Kristen Nygaards hus, small auditorium |
|||
| 9:30-11:30 | GPU programming | Johan Simon Seland (Sintef) |
Description: Modern GPUs (Graphics Processing Units) are now fully programmable many-core processors that offer unprecedented levels of floating point performance. They brings terascale computing to the laptop, and petascale computing to clusters. This lecture will consist of two parts, for the first half we will motivate why GPU computing is worthwhile for high-performance computing, and briefly look at various approaches to program GPUs, including the well-known CUDA and OpenCL libraries. The second half will detail algorithmic design for GPUs and best practices for benchmarking, validating and profiling GPU programs. Target audience: Scientists with interest in GPU computing. |
| 12:30-14:00 | Programming with OpenMP og mixed MPI-OpenMP | Xing Cai (Simula) |
Description: Introduction to parallel programming using OpenMP og mixed MPI-OpenMP (hybrid) computing. Target audience: Intermediate to advanced programmers. |
| 14:15-15:30 | User profiling and program behavior | Ole Widar Saastad |
Description: Learn to understand and monitor the resource use of your applications. Target audience: This training is intended for users who have little experience or knowledge about the behavior of their application. |
|
Thursday November 17 - RCS services day - Ole-Johan Dahls hus, Python |
|||
| 12:30-13:00 | Local, national, and international computational resources for researchers | Nikolai Vazov |
Description: This lecture introduces the activities of the Research Computing Services group in local, national and international context. Learn about various means of computational support for scientists. Target audience: All |
| 13:15-13:45 | Statistics resources and services for researchers | Pål Fugelli |
Description:An introduction to the statistical services and tools provided by UiO/USIT including information about available software for data-management and statistical analysis. Access and use the new windows-based servers. Target audience:Researchers with little or no experience in using software-tools for statistical analysis. |
| 13:45-14:15 | Storage services for researchers | Thierry Toutain |
Description:Introduction to the Norstore storage service at UiO. You will learn how to access and use the data storage. We also describe the tools and services available to store and transfer scientific data to Norstore. Target audience:All |
| 14:30-15:00 | Meet the RCS (VD) staff - open forum | VD staff |
Description: Do you have questions/suggestions regarding Titan or other RCS services? Please come to this open session. Target audience: All |
The exact program and schedule is subject to (minor) change. Any changes will be announced.