Developing Advanced Computing Course Materials for Distributed Audiences

1
Developing Advanced Computing Course Materials
for Distributed Audiences

• Texas Advanced Computing Center (TACC)
• The University of Texas at Austin

2
TACC Advanced ComputingTechnology Areas

• High Performance Computing (HPC)
• numerically intensive computing produces data
• Visualization Data Analysis (VDA)
• rendering data into information knowledge
• Data Information Systems (DIS)
• managing and analyzing data for information
  knowledge
• Distributed and Grid Computing (DGC)
• Integrating diverse resources, data, and people
  to produce and share knowledge requires
  networks!

3
Why are these courses important?

• Classes that prepare students to use advanced
  computing resources as they are used in
  computational, applications-driven research and
  development are relatively rare in university
  curricula.
• With the emergence of grid computing technologies
  and the development of integrated
  cyberinfrastructure promising new capabilities
  for knowledge discovery, classes that provide a
  solid, practical foundation for using
  cyberinfrastructure in research and development
  are even more important for both academic and
  industry careers.

4
Courses

• Introduction to Scientific/Technical Computing
• Parallel Computing for Science Engineering
• Visualization Data Analysis for Science
  Engineering
• Distributed Grid Computing for Science and
  Engineering

5
Introduction to Scientific/Technical Computing

• This course will cover a wide variety of
  techniques and methods applicable to many
  scientific disciplines. The course will begin
  with an introduction to the traditional mainstays
  of scientific and technical computing basics of
  computer architecture the UNIX environment
  floating-point arithmetic numerical methods
  including integration, interpolation, linear
  algebra, ordinary and partial differential
  equations, and optimization, and non-linear
  solution algorithms. Basic visualization and data
  analysis tools will be presented as well.

6
Parallel Computing For Science Engineering

• The course beings with a comprehensive
  introduction to parallel computing theory, and
  discuss hardware features and software components
  essential for parallel computing. Next, OpenMP
  and MPI programming paradigms are introduced and
  prepare students for a study of key algorithms
  and provides an explanation of applications in
  various fields. The course will focus on
  application development, performance, and
  scalability throughout. In addition, it will
  prepare students to formulate and develop
  parallel algorithms to implement them as
  effective applications for parallel computing
  systems.

7
Visualization Data Analysis for Science
Engineering

• The course begins with a comprehensive
  introduction to the theory behind visualization
  and data analysis. The applied nature of this
  class will focus on application development and
  achieving performance. The class provides not
  only an introduction to the theory of scientific
  visualization but also the context to test and
  develop understanding of these theoretical
  principals.

8
Distributed Grid Computing for Science
Engineering

• This class begins with an introduction to the
  principles and characteristics of grid computing
  in addition to technologies that facilitate
  deploying and using grid resources. The course
  will also review current international, national
  and campus grid building activities and leverage
  the lessons learned from the deployment of these
  state-of-the-art grids. Finally, the course will
  present the future plans and trends in grid
  computing, so students will have information and
  insight on what to track as they complete this
  class and use grid computing in research or
  commercial environments.

9
Delivery Mechanisms

• In person
• Delivered at UT Austin, eventually in smart
  classrooms with videoconferencing technologies
• Classes will become part of the UT CS Dept course
  catalog and cross-listed in other departments for
  maximum exposure
• Remote usage
• Course slides and assigments packaged in common
  formats (MS Office / OpenOffice, PDF, etc.) for
  download
• Course lectures recorded to capture spoken
  lectures and QA from class (common formats)
• Lectures also recorded with video (common
  formats)
• Eventually, also broadcast in real-time (AG,
  Conference XP)

10
EPIC Engaging People in CyberinfrastructureCurri
culum Development Project

• EPIC www.eotepic.org
• Multi-institution EOT project (ends Summer 06)
• Goal is to build human capacity by creating
  awareness of the opportunities offered through
  cyberinfrastructure (CI) and by educating and
  training a diverse group of people.
• TACC will deliver these classes using EPIC
  funding and collaborations to additional
  institutions

11
Questions?

• Contact us
• Jay Boisseau boisseau_at_tacc.utexas.edu
• Karl Schulz karl_at_tacc.utexas.edu
• Kelly Gaither kelly_at_tacc.utexas.edu