2015 Ontario Summer School for High Performance Computing Central

From oldwiki.scinet.utoronto.ca
Jump to navigation Jump to search

Summerschool hpc 2015.gif


About

The 2015 Ontario Summer School on High Performance Computing, whose second installment of the year will be hosted by SciNet, provides attendees with opportunities to learn and share knowledge and experience in high performance and technical computing. The format: a five-day workshop with mixed lectures and hands-on sessions on a number of selected subjects, including shared memory programming, distributed memory programming, parallel data processing, and general purpose graphics processing unit programming.

Below are descriptions and course material for the Central version, given from July 13th to July 17th, 2015, in Toronto.


Introduction to the Linux Shell

Abstract

Working with many of the HPC systems in Ontario involves using the linux/unix command line. This provides a very powerful interface, but it can be quite daunting for the uninitiated. Become initiated with this course. This hands on session will cover basic commands and scripting, as well as touching on some powerful constructs like regular expressions. It could be a great boon for your productivity!

Details

Time/date

Monday July 13, 9:30 - 12:30

Location

Galbraith Building, Room 404

35 St. George Street

Toronto, ON M5S 1A4

Instructor

Dr. Mike Nolta (SciNet)

Prerequisites

A laptop with a linux-like environment.

Slides and other material

Introduction to High Performance Computing

Abstract

This session will provide an introduction to basic concepts of high performance computing. It is intended to be a high level primer for those largely new to HPC, and serve as a foundation upon which to build over the coming days. Topics will include motivation for HPC, essential issues, problem characteristics as they apply to parallelism and a high level overview of parallel programming models. Strategies of running large sets of serial processes using e.g. GNU parallel, will also be presented.

Details

Time/date

Monday July 13, 13:30 - 16:30

Location

Galbraith Building, Room 404

35 St. George Street

Toronto, ON M5S 1A4

Instructor

Dr. Marcelo Ponce (SciNet)

Prerequisites

Basic Linux shell skills Registration for all summer school sessions will become available at https://www.sharcnet.ca/events/ss2015.

Slides and other material

file http://www.scinethpc.ca/~mponce/HPC_intro.pdf

Data Analysis with R

Abstract

This session offers a brief introduction to R, with a focus on data analysis and statistics.

Details

Date/time

Monday July 13, 9:30 - 12:30

Location

Galbraith Building, Room 405

35 St. George Street

Toronto, ON M5S 1A4

Instructor

Dr. Erik Spence (SciNet)

Prerequisites

Some programming experience in any language. You should have used and written functions. Bring a laptop with a R and Rstudio installed.

Slides and other material

Slides.

Parallel R

Abstract

This session will cover parallel programming R, with a focus on parallel data analysis. Topics covered include snow, parallel, and foreach/doparallel.

Details

Time/date

Monday July 13, 13:30 - 16:30

Location

Galbraith Building, Room 405

35 St. George Street

Toronto, ON M5S 1A4

Instructor

Dr. Erik Spence (SciNet)

Prerequisites

Experience with programming in R and a rudimentary understanding of parallel computing.

Slides and other material

Slides.

Programming Shared Memory Systems with OpenMP

Abstract

In this session, in which lectures and hands-on labs are interspersed, the students will learn the basics of shared memory programming with OpenMP. In particular, we will discuss the OpenMP's threads, memory, and performance, reductions and load balancing. We will also discuss extensions to heterogeneous systems such as offered by the OpenMP 4.0 and OpenACC standards.

Details

Time/date

Tuesday July 14, 9:30 - 16:30

Location

Galbraith Building, Room 404

35 St. George Street

Toronto, ON M5S 1A4

Instructor

Dr. Ramses van Zon (SciNet)

Prerequisites

C/C++ and/or Fortran scientific programming; Experience editing and compiling code in a Linux environment.

Slides and other material

To come


Scientific Computing with Python

Abstract

In this session, you will be taught how to use python for research computing purposes. Topics include: the basics of python, automation, numpy, scipy, file i/o, and visualization.

Details

Time/date'

Tuesday July 14, 9:30 - 12:30

Location

Galbraith Building, Room 405

35 St. George Street

Toronto, ON M5S 1A4

Instructor

Dr. Erik Spence (SciNet)

Prerequisites

A bit of coding experience in any programming or scripting language. Command-line experience in Linux is a plus.

Slides and other material

To come


Python for High Performance Computing

Abstract

This session will cover parallel programming in python, with a focus on parallel data analysis. We will cover subprocess, multiprocessing, pypar and other parallel-enabling python packages.

Details

Time/date

Tuesday July 14, 13:30 - 16:30

Location

Galbraith Building, Room 405

35 St. George Street

Toronto, ON M5S 1A4

Instructor

Dr. Erik Spence (SciNet)

Prerequisites

Python programming experience and a rudimentary understanding of parallel computing.

Slides and other material

To come


Programming Clusters with MPI

Abstract

In this two-day session, through lectures interspersed with hands-on labs, the students will learn the basics of MPI programming. Examples and exercises will be based on parallelization of common scientific computing problems.

Details

Time/date

Wednesday July 15, 9:30 - 16:30

Thursday July 16, 9:30 - 16:30

Location

Galbraith Building, Room 404

35 St. George Street

Toronto, ON M5S 1A4

Instructor

Dr. Scott Northrup (SciNet)

Prerequisites

Programming experience with Fortran or C/C++.

Slides and other material

To come


Programming GPUs with CUDA

Abstract

This is an introductory course covering programming and computing on GPUs---graphics processing units---which are an increasingly common presence in massively parallel computing architectures. This session will cover both of the available C-like programming frameworks: NVIDIA’s CUDA-C. The basics of GPU programming will be covered, and students will work through a number of hands on examples. Demonstrations of profiling and debugging applications running on the GPU will also be included. The structuring of data and computations that makes full use of the GPU will be discussed in detail. Students should be able to leave the course with the knowledge necessary to begin developing their own GPU applications.

Details

Time/date

Wednesday July 15, 9:30 - 16:30

Thursday July 16, 9:30 - 16:30

Location

Galbraith Building, Room 405

35 St. George Street

Toronto, ON M5S 1A4

Instructors Dr. Pawel Pomorski and Dr. Sergey Mashchenko (SHARCNET)

Prerequisites

C/C++ scientific programming, experience editing and compiling code in a Linux environment. Some experience with CUDA and/or OpenMP a plus.

Slides and other materials

To come


Visualization

Abstract

The first part of this session will be a basic introduction to general-purpose scientific visualization tools such as gnuplot, grace(xmgr), remote tools (tunneling, VNC), python's matplotlib, and examples from other. The second part will be a mix of lecture and hands-on to introduce more specialized scientific visualization software such as vmd, paraview, and visit.

Details

Time/date

Friday July 17, 9:30 - 16:30

Location

Galbraith Building, Room 404

35 St. George Street

Toronto, ON M5S 1A4

Instructor Dr. Marcelo Ponce (SciNet)

Prerequisites

Software installed, for the morning session: gnuplot, ssh (graphic client), vnc client, python and matplotlib; afternoon session: paraview.

Slides and other material

To come


Debugging, Optimization, and Best Practices

Abstract

Debugging is an important step in developing a new code, or porting an old one to a new machine. We will discuss the debugging of frequently encountered bugs in serial code with gdb and the debugging of parallel (MPI and threaded) codes with DDT on live systems. Next, we will present general issues, common pitfalls and optimization strategies that are application to HPC systems. By using profiling tools available for parallel programs, we can see when the bottlenecks are. We can try to alleviate them by following common best practices, allowing one to obtain their results more quickly and at the same time minimize their burden on shared system resources. Walk-through examples and case studies will be presented during the session to illustrate the concepts.

Details

Date/time

Friday July 17, 9:30 - 16:30

Location

Galbraith Building, Room 405

35 St. George Street

Toronto, ON M5S 1A4

Instructors

Dr. Ramses van Zon and Dr. Mike Nolta (SciNet)

Prerequisites

Basic familiarity with a high-level language (C/C++/Fortran) as well as compiling and running programs via the command line environment on a HPC system.

Slides and other material

To come