Hartwig Anzt

Research Scientist in High Performance Computing

Hartwig Anzt is a Helmholtz-Young-Investigator Group leader at the Steinbuch Centre for Computing at the Karlsruhe Institute of Technology (KIT). He obtained his PhD in Mathematics at the Karlsruhe Institute of Technology. Afterwards, he joined Jack Dongarra's Innovative Computing Lab at the University of Tennessee in 2013 until he started his own research group in 2017. He still contributed to the Innovative Computing Lab as a Research Consultant. Hartwig Anzt has a strong background in numerical mathematics, specializes in iterative methods and preconditioning techniques for the next generation hardware architectures. His Helmholtz group on Fixed-point methods for numerics at Exascale (FiNE) is granted funding until 2022. Hartwig Anzt has a long track record of high-quality software development. He is author of the MAGMA-sparse open source software package and managing lead of the Ginkgo numerical linear algebra library. Hartwig Anzt is a co-PI of the PEEKS project and the xSDK project inside the software technology effort of the US Exascale Computing Project (ECP). He is also the technical PI of the multiprecision effort in the xSDK project, a coordinated effort aiming at integrating low-precision functionality into high-accuracy simulation codes.

Position

Group Leader at Karlsruhe Institute of Technology (KIT)

Research Group Leader of the Helmholtz-Young-Investigator-Group "Fixed-point methods for numerics at Exascale" (FiNE) at the Steinbuch Centre for Computing.

Research Consultant at the University of Tennessee (UTK)

Research Consultant at the Innovative Computing Laboratory (ICL) contributing as part of the PEEKS project to the US Exascale Computing project.

Research

My research focus is on developing and optimizing numerical methods for efficient high-performance computing. In particular, I am interested in sparse linear algebra, iterative and asynchronous methods, Krylov solvers, preconditioning. The approach I take is based on the idea of re-formulating the problems in terms of fixed-point problems to allow for higher parallelization levels. The implementation of the fixed-point methods typically make heavy use of (data-parallel) batched routines, and possess relaxed synchronization requirements. I also work on fault tolerance, energy efficiency, as well as Multi- and Manycore (GPU) computing. The algorithm research is complemented with efforts aiming at sustainable software development in an academic setting, and a healthy software lifecycle.

Software Projects

Ginkgo

Ginkgo is a high-performance linear algebra library for manycore systems, with a focus on sparse solution of linear systems. It is implemented using modern C++, with GPU kernels implemented in CUDA and HIP. Ginkgo is part of the Extreme-scale Scientific Software Development Kit (xSDK)

MAGMA-sparse

MAGMA-sparse is an integrated component of the MAGMA open source linear algebra library for multi- and manycore architectures. It is based on the C programming language and part of the Extreme-scale Scientific Software Development Kit (xSDK).

Recent Talks & Presentations

Podcast: Developing Multiprecision Algorithms with the Ginkgo Library Project

Let's Talk Exascale

US Exascale Computing Project, 2019

The Ginkgo Sparse Linear Algebra Package

Supercomputing 2019, Booth Talk

Denver, November 2019

Accepting High-Quality Software Contributions as Scientific Publications

Blog Article of the Better Scientific Software (BSSw) initiative

Published October 2019

Algorithm Design in the Advent of Exascale Computing

4th International Symposium on Research and Education of Computational Science (RECS)

Tokyo, October 2019

Sustainable Software Development in an Academic Setting

4th International Symposium on Research and Education of Computational Science (RECS)

Tokyo, October 2019

Addressing the Communication Bottleneck: Towards a Modular Precision Ecosystem for HPC

Focus Session at the ISC High Performance 2019: New Approaches, Algorithms Towards Exascale Computing

Frankfurt, June 2019

ParILUT - A Parallel Threshold ILU for GPUs

33rd IEEE International Parallel and Distributed Computing Symposium

Rio de Janeiro, May 2019

Approximate and Exact Selection on GPUs

9th International Workshop on Accelerators and Hybrid Exascale Systems (AsHES)

Rio de Janeiro, May 2019

Are we doing the right thing? - A Critical Analysis of the Academic HPC Community

20th IEEE International Workshop on Parallel and Distributed Computing (PDSEC)

Rio de Janeiro, May 2019

Adaptive-Precision Preconditioning

9th Joint Laboratory for Extreme Scale Computing (JLESC) workshop

Knoxville, April 2019

ParILUT - A new Parallel Threshold ILU

9th Joint Laboratory for Extreme Scale Computing (JLESC) workshop

Knoxville, April 2019

Towards Continuous Benchmarking (CB)

9th Joint Laboratory for Extreme Scale Computing (JLESC) workshop

Knoxville, April 2019

The Art of Writing Scientific Software in an Academic Environment

Blog Article of the Better Scientific Software (BSSw) initiative

Published February 2019

Exploiting Node-level Performance in Sparse Linear Algebra

SIAM Conference on Computational Science and Engineering (SIAM CSE 2019)

Spokane, February 2019

An Automated Performance Evaluation Framework for the Ginkgo Software Ecosystem

90th Annual Meeting of the International Associaten of Applied Mathematics and Mechanics (GAMM 2019)

Vienna, February 2019

Towards a Modular Precision Ecosystem

Erlangen Computing Seminar

Erlangen, December 2018

Fixed-Point and Adaptive Precision Methods for Numerics at Exascale

GridKa School 2018 - Computing and Science Fair

Karlsruhe, August 2018

Numerical Linear Algebra for High Performance Computing

SBD Workshop: Transfer of HPC and Data Knowledge to Scientific Communities

Juelich, June 2018

ParILUT - A New Parallel Threshold ILU

SIAM Meeting on Parallel Processing (SIAM PP 2018)

Tokyo, March 2018

Resources

Address
Steinbuch Centre for Computing
Herrmann-von-Helmholtz-Platz 1
76344 Eggenstein-Leopoldshafen
Germany
Phone Number
+49 721 608 22756
Publication List
GoogleScholar

CV
[PDF]

Special Note

Anyone misspelling my last name in an official document or presentation slides owes me a bottle of vine.