The research in High-Performance Computing focuses on different aspects
of optimizing (or "tuning") existing applications or applications under
development, such that results can be obtained faster. Typically those
applications are large-scale simulations, that can run for days and
weeks and that consume lots of computational resources, e.g. memory,
CPU cycles, disk space, etc.
| Serial tuning. This area focuses on finding the bottlenecks in sequential algorithms and applications, and to implement solutions that are optimized for modern cache-based computer systems. |
|
| Parallelization. This work involves design of parallel algorithms and/or the attempt to parallelize existing algorithms efficiently. The major part of work in this area is the development of parallel codes for SMP (Symmetric Multi-Processors) types of machines, using OpenMP. |
|
| Run-time optimization. Large applications can very often benefit from changing or optimizing the runtime environment, e.g. access to local disks, changing the memory page sizes, etc. The latter can be a good way to improve performance for applications that are not available in source code, and that suffer from many address cache (TLB) misses. |
