Everything Everywhere All at Once

The US Exascale Computing Project (ECP) aims to deliver a capable exascale computing ecosystem to provide breakthrough modelling and simulation solutions to address the most critical challenges in scientific discovery, energy assurance, economic competitiveness, and national security. This requires providing scientific computing applications with a software stack that allows them to perform on the leading supercomputers. In this talk, Hartwig discusses the impact of the changing hardware landscape on software design and the requirements in terms of flexibility and productivity. Instead of giving a high-level project overview, the talk is a tale from the trenches and elaborates on how the Ginkgo open-source mathematics library responds to high-performance computing application requirements and helps to achieve simulation performance goals.

Biography

Hartwig Anzt is the Chair of Computational Mathematics at the TUM School of Computation, Information, and Technology of the Technical University of Munich (TUM) Campus Heilbronn. He also holds a Research Associate Professor position at the Innovative Computing Lab (ICL) at the University of Tennessee (UTK). Hartwig Anzt holds a PhD in applied mathematics from the Karlsruhe Institute of Technology (KIT) and specializes in iterative methods and preconditioning techniques for the next generation hardware architectures. He also has a long track record of high-quality development. He is the author of the MAGMA-sparse open-source software package and the managing lead of the Ginkgo mathematics software library. Hartwig Anzt had served as a PI in the Software Technology (ST) pillar of the US Exascale Computing Project (ECP), including a coordinated effort to integrate low-precision functionality into high-accuracy simulation codes. He is also a PI for the EuroHPC project MICROCARD. Hartwig Anzt serves as editor for ACM TOPC and SIAM SISC. He was also elected program manager of the SIAM Activity Group on Supercomputing.