Training

This is an introductory session to using the new national systems, Graham and Cedar. Participants will learn about their capabilities, file systems, available software, the Slurm scheduler, and how to get up and running with them. This session provides an overview and quick-start guidance. (1 hour) (Slides) (Video)

What is high performance computing (HPC) and what can it do for me? How can ACENET help? Used by researchers across many disciplines to tackle analyses too large or complex for a desktop, or to achieve improved efficiency over a desktop, this session takes participants through the preliminary stages of learning about HPC and computing clusters, and how to get started with this type of computing. It then reviews software packages available for applications, data analysis, software development and compiling code. Finally, participants will be introduced to the concept of parallel computing to achieve much faster results in analysis. This session is designed for those with no prior experience in HPC, and are looking for an introduction and overview. (1 hour) (Slides) (Video)

Linux is the terminal interface used to enable you to use the ACENET and Compute Canada HPC clusters from your desktop. It’s the tool to get your data on the clusters, run your programs, and get your data back. In this session, learn how to get started with Linux, how to create and navigate directories for your data, load files, manage your storage, run programs on the computing clusters, and set file permissions. This workshop is designed for those with no prior experience in working with a terminal interface. Participants are encouraged to bring a laptop. (1 hour) (Slides) (Video)

Participants will learn how to use shell scripting to exercise the power of the command line. Shell scripting helps you save time, automate file management tasks, and better use Linux. This session teaches you how to name, locate and set permissions for executable files, taking input and producing output. Learn about job scripts, shell variables and looping commands. This workshop is designed for either new HPC users who are familiar with working in a Linux environment, but have not had experience with shell scripting, or for experienced users seeking to get more out of shell scripting. In order to get the most from the session, participants are strongly encouraged to have a Compute Canada/ACENET account and to bring a laptop to do the exercises.  (1 hour) (Slides) (Video)

This session teaches participants how to use Compute Canada’s queuing environment on the new national systems (Cedar and Graham), using the job scheduler Slurm. Learn how the scheduler works, how it allocates jobs, what are reasonable requests to minimize wait time, how to make the best use of the resources to be more efficient, how to get more throughput, how to get more jobs running at the same time, and how to troubleshoot and deal with crashes. This workshop is designed for either new HPC users familiar with Linux and Shell Scripting, but who have not had experience with using Slurm, or, for experienced users transitioning to Slurm or seeking to improve efficiency with the scheduler. In order to get the most from the session, participants are strongly encouraged to have a Compute Canada/ACENET account and to bring a laptop to do the exercises. (1 hour) (Slides)

This session teaches job scheduling on ACENET systems that use the Grid Engine scheduler. Learn how the scheduler works, how it allocates jobs, what are reasonable requests to minimize wait time, how to make the best use of the resources to be more efficient, how to get more throughput, how to get more jobs running at the same time, and how to troubleshoot and deal with crashes. This workshop is designed for either new HPC users familiar with Linux and Shell Scripting, but who have not had experience using Grid Engine, or, for experienced users seeking to improve efficiency with the scheduler. In order to get the most from the session, participants are strongly encouraged to have a Compute Canada/ACENET account and to bring a laptop to do the exercises. (1 hour) (Slides) (Video)

Data analysis and processing has been around for a long time – what is new is the variety, volume, and velocity at which things can now be quantified. Today, data is available form a myriad of sources such as, tweets, GPS coordinates, images, and videos from mobile devices, and massive on-line archives of digitized manuscripts to name a few. The amount and variety of data make it difficult to analyze and we as a society are still working out the best ways to use this data to improve our understanding and make better decisions. This seminar will appeal to people from humanities to natural sciences and in-between, and will help you determine how your data fits into the big data ecosystem and introduce some tools to help you manage and analyze your data. (1 hour)

This session provides an introduction to the Compute Canada cloud which is used to create and manage virtual machines. Virtual machines allow great flexibility but require knowledge and effort to configure them for your specific needs. Virtual machines can be used for diverse work flows, from processing particle physics data to running humanities and social sciences websites. Learn how to create a virtual machine and how to start using it. (1 hour) (Slides)

Version control has been a key concept in software engineering for decades, but it’s now becoming known and used by more than just hard-core programmers. The most popular tool is currently Git, but it’s part of a large “ecosystem” of web services (GitHub, BitBucket, GitLab, …) and competing tools (Subversion, Mercurial, Perforce…). What do these all mean? How do you choose a combination of version control tools and services for your work? (1 hour) (Slides)

Software Carpentry teaches basic computational research skills. Sessions include program design, version control, data management and task automation. This is a hands-on workshop, where collaboration is encouraged and participants are asked to apply their learning to individual research problems. This workshop is of interest to: current computational researchers and their teams; anyone considering a research project that requires computational research; or students who want to gain these skills to enhance their career choices. A laptop is required. (2 days)

Data Carpentry trains researchers in the core data skills for efficient, shareable, and reproducible research practices covering the full lifecycle of data-driven research. Through a two-day hands-on approach, the focus is on the introductory computational skills needed for data management and analysis. The workshops are domain-specific, and include life and physical sciences, and humanities and social sciences. Sessions build on the existing knowledge of participants to enable them to quickly apply the skills learned to their own research. This workshop is of interest to: current researchers and their teams using large data sets; anyone considering a research project that involves large data sets; or students who want to gain these skills to enhance their career choices. A laptop is required. (2 days)

This workshop provides a brief overview of Research Data Management, with a focus on the development of Data Management Plans (DMPs). DMPs are a key component of the data management process that touch on all aspects of RDM, describing how data are collected, formatted, preserved, and shared. Importantly, DMPs also promote the consideration of the costs and challenges associated with managing research data. Participants will learn about RDM in the context of the research data lifecycle, gain an understanding of the basic components of a DMP, create a DMP for their research project using the Portage Network’s DMP Assistant tool, and think critically about data management challenges and how to evaluate DMPs. No software or prior data management training required. Before the workshop, participants should create an account on the Portage Network DMP Assistant tool and come prepared with information about a specific project for which the DMP can be written (e.g., a project workplan or research abstract). Participants must also bring their own laptop. (1.5 hours)

Learn how to handle dozens or hundreds of jobs without typing “qsub” every time, using templates, loops, and task arrays. This workshop is most useful for those who already have an ACENET account and have completed one of the Basics workshops on job scheduling. Bring a laptop to participate in the exercises. (2 hours)

This workshop introduces the terminology and concepts of parallel programming. This includes types of parallel programs, design methodologies, and performance measures. Appropriate for those with programming experience and who have taken the ACENET Basics workshops. (1 hour) (Slides)

This is a one-hour crash course in the primary tool for writing message-passing parallel programs. It covers the basic concepts of MPI, including sending and receiving messages, coordination, and data synchronization. This workshop assumes that you have some programming experience with one or more languages and have take the ACENET Basics sessions. (1 hour) (Slides)

Participants will learn about the primary tool for writing shared-memory parallel programs. The session covers OpenMP and provides a short introduction to POSIX threads. You will learn about the most common techniques, such as parallel for loops, barriers and critical sections. This workshop assumes that you have programming experience with one or more languages and have taken the ACENET Basics sessions. (1 hour) (Slides)

This workshop assumes that you have some experience with OpenMP or some other shared-memory programming paradigm. It covers more advanced topics like controlling work distributions, creating and using task pools and several other areas. (2 hours)

Many programs come as source code and a mysterious Makefile, with instructions like “make all; make install”. Here’s how it works, what can go wrong, how to fix it, and maybe even how to write your own. Participants must have some programming experience and have taken the ACENET Basics sessions. (1 hour) (Slides)

This workshop assumes that you have some experience with one or more programming languages. It covers some basic optimization techniques that are general in nature, as well as several tips for specific languages. (1 hour)

For those with some experience using the ACENET systems, this session is an informal opportunity to address individual difficulties, areas of concern, or questions. (1 hour)

This workshop introduces researchers to the theory, key ideas, and techniques of Molecular Dynamics. A practical application targeted at biosimulations is introduced using the GROMACS package. (full day)

This workshop introduces researchers to using the Compute Canada cloud to handle projects involving big data.(2 hours) (Slides)

This session is designed for those who have no experience in coding, who want to understand the general principles of coding and have taken the ACENET Basics series. (1 hour)

This is a more in-depth hands-on coding workshop for those who are interested in coding in C++. Designed for 8-10 participants who have ACENET accounts. Participants must have some rudimentary programming experience and have taken the ACENET Introduction to Coding and the ACENET Basics seminars. The workshop’s format is two 45-minute lectures, two 30-minute breaks, and two 45-minute student programming sessions. (4 hours)

This workshop will cover an introduction to the C programming language, including syntax, variables and data structures. While not necessary, some experience with programming concepts would be helpful. By the end of the workshop, you should be able to read C programs and be able to write and compile simple ones of your own. (1 hour)

This workshop assumes that you already know the basics of the C programming language. We will move on to deeper topics like memory management, pointer arithmetic and file I/O. (1 hour)

This is a hands-on coding workshop for those who are interested in coding in Fortran 77/90. Designed for 8-10 participants who have ACENET accounts. Participants must have some rudimentary programming experience and have taken the ACENET introduction to Coding and the ACENET Basics seminars. The workshop’s format is two 45-minute lectures, two 30-minute breaks, and two 45-minute student programming sessions. (4 hours)

This workshop will cover an introduction to the Python programming language, including syntax, variables and data structures. While not necessary, some experience with programming concepts would be helpful. By the end of the workshop, you should be able to read Python programs and be able to write simple ones of your own. (2 hours) (Slides)

This workshop assumes that you have some experience with the Python programming language. It will cover several packages, including numpy and scipy, that are useful in doing scientific computations. Several different examples will be discussed, including solving PDEs, solving systems of equations, and even doing symbolic computations. (2 hours) (Slides)

This workshop assumes that you have some previous Python experience. You will learn many of the tools available to profile your code and find the trouble spots. Once located, the second half of the workshop presents a series of tips and tricks that may be able to help you speed up the execution of your program. (1.5 hours) (Slides)

This workshop assumes that you have some experience with the Python language. It will cover the external packages that are useful in doing image processing. This includes techniques that may be helpful in biomedical imaging, space based earth imaging, or anything else image related. (1 hour)

This workshop will cover the basics of R, how to do basic statistics and plotting. It will cover how to install and use extra packages, but not how to write your own. By the end of the workshop, you will be able to do basic statistical analysis, and know how to access the tools to do more advanced analysis. (2 hours)

This workshop provides a hands-on session where attendees are taken through several tasks in order to become familiar with how R works. (2 hours)

This workshop assumes that you have some experience with R. It will cover some of the packages that can help when dealing with very large data sets. It will also cover some of the packages and techniques that are useful when trying to do parallel programming in R, including issues in trying to do parallel work on Windows machines. (2 hours)

This workshop assumes that you have some experience with R. It will cover using R as a full programming language, allowing you to write your own code. It will also cover the basics of creating your own packages for when you are ready to share your code with other users. (2 hours)