About HPAC

Left to right: Paul Springer, Daniel Tameling, Diego Fabregat, Elmar Peise, Matthias Petschow, Paolo Bientinesi, Viola Wierschem, and Edoardo Di Napoli.

The High-Performance and Automatic Computing group is concerned with the development and analysis of accurate and efficient numerical algorithms, with focus on numerical linear algebra. We target applications from materials science, molecular dynamics and computational biology, and the whole range of high-performance architectures.

Topics

• Numerical linear algebra
  • Sequences of problems
  • Small scale operations
  • Tensor operations
  • Error analysis
  • Parallel eigensolvers
• Parallelism
  • Vectorization
  • Multicore
  • Distributed-memory
  • Coprocessors: GPU, Xeon Phi, ...
  • Hybrid
• Automation
  • Algorithm and code generation
  • Performance modeling and prediction
  • Algorithm ranking
• Applications
  • Genome analysis
  • Molecular dynamics simulations
  • Symbolic algorithmic differentiation for matrix operations
  • Electronic structure calculations

Projects for Bachelor and Master theses

Check list of available projects.