All Tutorials

  • Tue Jul 9, 1:00 pm - 3:00 pm
    575
    Walter Library

    This tutorial will introduce users to MSI systems, outlining the hardware available, and introducing the module and queueing systems, as well as methods for remote access and file transfer. Users will be shown how to construct queue scripts and submit their calculation jobs on MSI’s high-performance systems. The features of different systems will be compared so that users may determine which might best suit their research needs. Software options and availability will be discussed.


  • Mon Jul 1, 9:00 am - 4:00 pm
    575
    Walter Library

    Due to overwhelming demand, this tutorial initially held on June 25, 2013, is being presented a second time. Here is a brief description:


    Python is a general purpose programming language with a rich syntax and structure. You can learn to use Python and see almost immediate gains in productivity relative to programming with other languages. Python has many modules specializing in various topics of interest to the scientific community and is used as an interface for numerous scientific packages.


    The morning section will provide an introduction to Python. Simple and advanced data types, variable assignment, control structures, mathematical and logical operators, program input and output, and functional programming will be discussed.


    The afternoon section will cover advanced features of Python relevant to high performance computing. Topics will include efficient data processing with NumPy, integrating compiled routines into python programs, and techniques for using python to drive parallel supercomputing tasks.


  • Thu Jun 27, 1:00 pm - 3:00 pm
    575
    Walter Library

    Every experienced developer has a preferred method and toolchain for writing code. This tutorial will help users choose the right tools and improve habits for a better experience with custom and third-party source codes. We begin with a look at build systems (e.g., Make, CMake) and version control (e.g., SVN, Git) for project management. Through examples we will demonstrate: a) generating code documentation for the web, b) unit testing, c) debugging, and d) profiling and optimization. This tutorial pulls examples from multiple languages (C/C++, FORTRAN, Java and Python) to demonstrate that best practices are language agnostic.


    Prerequisites: Experience with at least one programming language and the Unix shell environment.


  • Tue Jun 25, 9:00 am - 4:00 pm
    575
    Walter Library

    Python is a general purpose programming language with a rich syntax and structure. You can learn to use Python and see almost immediate gains in productivity relative to programming with other languages. Python has many modules specializing in various topics of interest to the scientific community and is used as an interface for numerous scientific packages.


    The morning section will provide an introduction to Python. Simple and advanced data types, variable assignment, control structures, mathematical and logical operators, program input and output, and functional programming will be discussed.


    The afternoon section will cover advanced features of Python relevant to high performance computing. Topics will include efficient data processing with NumPy, integrating compiled routines into python programs, and techniques for using python to drive parallel supercomputing tasks.


  • Mon Jun 24, 12:00 am - Fri Jun 28, 4:00 pm
    575
    Walter Library

    This class focuses on how to use computers to make discoveries from large amount of scientific data, in particular high-throughput biological data. The topics include 1) the computational methods for analyzing the scientific data such as decision trees, k-nearest neighbors, neural networks, SVMs, k-means, hierarchical clustering and etc; 2) analysis and visualization of large scale networks such as protein-protein interaction networks, disease networks and social networks. There were in-class exercises and mini group projects for hands-on experiences with tools for data analysis. A tour to visit the supercomputer room and the visualization lab was also organized.


  • Thu Jun 20, 1:00 pm - 3:00 pm
    575
    Walter Library

    Koronis features an SGI® Altix® UV 1000 – a large global shared memory (GSM) system. Its availability has offered unprecedented opportunities for NIH researchers to conduct memory-intensive calculations. At the same time, it poses great computational challenges from the system-memory complexity that, combined with the flexibility in the selection of the number of computing cores, can severely degrade the performance.


    This tutorial will help users make efficient use of Koronis and improve the application performance. Topics to be discussed include:

    1. The tactics for better use of CPUSET hierarchy.

    2. How the queues are structured and how to reduce the queuing time of your jobs.

    3. The available file systems and how they can be used for improving the I/O performance of your applications.


  • Tue Jun 18, 1:00 pm - 3:00 pm
    575
    Walter Library

    This tutorial is geared to new MSI users and will provide an introduction to the facilities and computational resources at MSI. The quick start portion of the tutorial will provide instructions for accessing these resources such as setting up accounts, submitting jobs on the various machines, etc. We will conclude with a brief introduction of the MSI UNIX environment, including hands-on examples. The UNIX operating system is a fundamental part of the MSI experience for people using the MSI Linux workstations and core systems. Many of MSI’s scientific codes require that the user understand basic UNIX operating commands and functionality. This tutorial will give the novice user an introduction to using the UNIX operating environment to navigate around and use MSI resources.


  • Wed Apr 24, 1:30 pm - 4:30 pm
    575
    Walter Library

    The workshop provides an overview of COMSOL Multiphysics:

    its capabilities, new features, enhanced functionality, and revamped graphical user interface. We will examine the model-builder-based interface which, in addition to heightened efficiency, provides new functionality to modify and quickly adapt models. A live example will be shown exemplifying both the speed and ease of the new work flow. New modules will also be looked at.


    The second half of the workshop is a hands-on tutorial in COMSOL

    Multiphysics Version. A hands-on tutorial lets you set up a first model using fast-results application interfaces. Please consider contacting Mia Johansson at miaj@comsol.com with a short description of your application/interests in advance of the workshop.


    Attendees will receive a 2-week free trial to use COMSOL Multiphysics. If you bring your own laptop, you can use this trial for the hands-on session. Alternatively you can use the lab computers provided by MSI.


    Please register on the COMSOL website: http://www.comsol.com/events/cmw/24959/.


  • Tue Apr 16, 2:00 pm - 3:15 pm
    138
    Cargill Building

    Supercomputing in Plain English: A High Performance Computing Workshop Series

    Session 11: Grab Bag: Scientific Libraries, I/O, Visualization


    This is a videoconference of a workshop being presented by OSCER.


    The OU Supercomputing Center for Education & Research (OSCER) is presenting a workshop series on Supercomputing in Plain English (SiPE). MSI is videoconferencing these sessions live. While attendance at all sessions is not required, the sessions build on each other, so we recommend that you attend as many as possible to get the most value from them. Information about the complete series can be found here: http://www.oscer.ou.edu/education.php.


    Please register with MSI for each session you plan to attend. We also encourage you to register with OSCER by sending an email to hneeman@ou.edu. Knowing how many people are participating may enable them to present more workshops in the future.


  • Tue Apr 16, 10:00 am - 4:00 pm
    575
    Walter Library

    This one-day, hands-on workshop provides an introduction on how to write a parallel program using MPI and will help researchers write better and portable parallel codes for distributed-memory Linux clusters. The tutorial will focus on basic point-to-point communication and collective communications, which are the most commonly used MPI routines in high-performance scientific computation. In addition, the advantage of using MPI non-blocking communication will be introduced. Each session of the workshop will combine a lecture with hands-on practice. The lecture will introduce basic principles, and the hands-on portion will focus on the use of MPI principles via examples.


    Session 1: Introduction to basic concepts of MPI, centering on point-to-point communication.


    Session 2: MPI collective communications including broadcast, gather, scatter, and All-to-All. Programming will be done in Fortran and C, so any background in these two languages will be helpful.


Pages