Hartwig Anzt

Chair for Computational Mathematics

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 author of the MAGMA-sparse open source software package and managing lead of the Ginkgo math 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 aiming at integrating low-precision functionality into high-accuracy simulation codes. He also is a PI in the EuroHPC project MICROCARD.

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 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

Tensor Cores for Matrix Multiplication Are on the Rise – Is There Any Hope for Sparse Operations?

SC'23 workshop: Future Is Sparse: Methods and Tools for Sparse Computations

Denver, USA, November 17, 2023

The Role of Software in HPC - Lessons Learnt in the US Exascale Computing Project

22d IEEE International Symposium on Parallel and Distributed Computing (ISPDC 2023)

Bucharest, Romania, July 10, 2023

Sustaining Simulation Performance in the US Exascale Computing Project - A tale from the trenches

35th Workshop on Sustained Simulation Performance

HLRS, Stuttgart, Germany, 2023

Batched Iterative Solvers in Plasma Fusion Simulations

15th JLESC workshop

Bordeaux, France, 2023

Ginkgo - a platform-portable math library responding to the needs of the US Exascale Computing Project

SIAM Conference on Computational Science and Engineering

Amsterdam, Netherlands, 2023

Then and Now – Growing as a child of ECP

US Exascale Computing Project, Annual Meeting

Houston, Texas, US, 2023

Mixed Precision Strategies for Memory-Bound Linear Algebra

LANS Seminars Series of the Los Alamos National Laboratory

Los Alamos National Laboratory, 2021

Pushing the Roofline: A Modular Precision Ecosystem Based on a Memory Accessor

FAU Perf Lab Seminar Series

Friedrich-Alexander-University Erlangen-Nuermberg, 2021

The Sparse Matrix Vector Product on High-End GPUs

SIAM Conference on Parallel Processing for Scientific Computing (PP20)

Seattle, Washington, U.S., 2020

ParILUT - A Parallel Threshold ILU for multicore and GPUs

SIAM Conference on Parallel Processing for Scientific Computing (PP20)

Seattle, Washington, U.S., 2020

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

Resources

Address
Innovative Computing Lab
University of Tennessee 1
1122 Volunteer Boulevard
Suite 203, Claxton
Knoxville, TN, 37996
USA
Phone Number
+1 865-974-8296
Publication List
GoogleScholar

CV
[PDF]

Special Note

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