High Performance Visualization for Large-Scale Scientific Data Analytics (Spring 2015)

As the size of data generated from numerical simulations continues to increase, visualization is now playing an increasingly more important role in assisting the scientists to obtain insight into the simulation output. To equip students with the ability to analyze very large-scale data sets, this course will provide an in-depth discussion of the state-of-the-art in large scale scientific visualization algorithms and systems. In addition to the fundamental visualization techniques, we will cover parallel implementation of selected algorithms for high-performance architectures such as the Blue Waters supercomputer. Students will get hands-on experience visualizing large-scale scientific data sets.

This semester-long online course will include video lectures, quizzes, and homework assignments and will provide students with free access to the Blue Waters supercomputer. The course is intended for graduate students in computer science or areas related to computational sciences who are interested in learning how to use visualization to analyze large-scale scientific data sets and also will be of interest to students who are considering scientific visualization as a research topic for their advanced studies.

The instructor is Dr. Han-Wei Shen, professor of Computer Science and Engineering at the Ohio State University. Participating institutions will need to provide a local instructor who will be responsible for advising the local students and officially assigning grades. Students will complete the online course exams and exercises as part of their grade.

Prerequisites for participating graduate students include:

  • Experience working in a Unix environment
  • Experience developing and running codes written in C or C++
  • Knowledge in 3D computer graphics and OpenGL/GPU programming is recommended
  • Knowledge in parallel programming tools such as MPI is recommended

Tentative Weekly Schedule

I. Visualization Foundation (3 weeks)
    Scientific data representation and file format
    Overview of visualization software (VTK and ParaView) 
    Overview of visualization Pipeline and parallelization strategies
II. Visualization Algorithms (6 weeks) 
    Scalar field visualization (volume rendering, isosurface, and topological methods)
    Vector and tensor field visualization (streamline, pathline, stream surfaces)
III. Large Scale Data Visualization and Analysis (6 weeks)
    Multivariate visualization 
    Time-Varying data visualization 
    Statistics and query driven visualization 
    Uncertainty visualization 
    Feature extraction and tracking 
    In situ visualization 


  • Visualization Toolkit: An Object-Oriented Approach to 3D Graphics, 4th Edition, Schroeder, Martin, Lorensen
  • The Visualization Handbook: Hansen, Johnson
  • High Performance Visualization: Enabling Extreme-Scale Scientific Insight, Bethel, Childs, Hansen


  • Lab 1: 10%
  • Lab 2: 10%
  • Lab 3: 10%
  • Lab 4: 10%
  • Midterm: 20%
  • Term paper: 10%
  • Final Project: 30%

About the Instructor

Han-Wei Shen is a full professor in the Department of Computer Science and Engineering at the Ohio State University. He has worked in the area of scientific visualization for more than two decades. His research is primarily focused on parallel visualization, flow visualization, time-varying visualization, and isosurface and volume rendering. His research has been supported by many federal HPC and Data Analytics programs, including DOE's SciDAC II, SciDAC III, Exascale Computing, and NSF's Big Data research initiatives. He has won NSF's CAREER award and DOE's Early Career Principle Investigator award for his visualization research. He has also won the Outstanding Teaching Award twice from the Department of Computer Science and Engineering at the Ohio State University. He is a paper chair for IEEE Scientific Visualization conference 2013 and 2014.