CBC Talk Heterogeneous CPU-GPU high-performance computing by Johannes Langguth
Total number of participants: 8
Total number of guests outside of CBC: 0
Number of different nationalities represented: 4
Total number of speakers: 1
Total number of talks: 1
The performance of modern supercomputers is to a large extent due to
the addition of hardware accelerators such as GPUs and Xeon Phis.
Accelerators potentially provide higher performance at lower system
and energy cost, but their usage results in higher system complexity,
which makes designing efficient simulation codes more difficult. In
this talk, we give an overview of the current HPC landscape and show
how large scale simulations on irregular meshes can be implemented in
order to make full use of heterogeneous computational resources.
Glenn T. Lines
Center for Biomedical Computing (CBC) aims to develop and apply novel simulation technologies to reach new understanding of complex physical processes affecting human health. We target selected medical problems where insight from mathematical modeling can contribute to changing clinical practice.