Markus Hohnerbach

Markus Hoehnerbach is a senior software engineer working on cuTENSOR and cuTENSORMg. He holds a doctorate in computer science from RWTH Aachen University. His areas of interest are high-performance computations on structured and unstructured tensors and their applications to machine learning and computational science.
Avatar photo

Posts by Markus Hohnerbach

Decorative image of matrices on a black background, with the text, "Part 2."
Simulation / Modeling / Design Mar 08, 2024

cuTENSOR 2.0: Applications and Performance

While part 1 focused on the usage of the new NVIDIA cuTENSOR 2.0 CUDA math library, this post introduces a variety of usage modes beyond that, specifically... 9 MIN READ
Decorative image of matrices on a black background, with the text "Part 1."
Simulation / Modeling / Design Mar 08, 2024

cuTENSOR 2.0: A Comprehensive Guide for Accelerating Tensor Computations

NVIDIA cuTENSOR is a CUDA math library that provides optimized implementations of tensor operations where tensors are dense, multi-dimensional arrays or array... 17 MIN READ
The cuTensor hero image with a floating grey block.
Simulation / Modeling / Design Apr 08, 2022

Extending Block-Cyclic Tensors for Multi-GPU with NVIDIA cuTENSORMg

Tensor contractions are at the core of many important workloads in machine learning, computational chemistry, and quantum computing. As scientists and engineers... 9 MIN READ