Model-Based Performance Analysis of the HyTeG Finite Element Framework

Thönnes D, Rüde U (2023)

Publication Type: Conference contribution

Publication year: 2023

Abstract

In this work, we present how code generation techniques significantly improve the performance of the computational kernels in the HyTeG software framework. This HPC framework combines the performance and memory advantages of matrix-free multigrid solvers with the flexibility of unstructured meshes. The pystencils code generation toolbox is used to replace the original abstract C++ kernels with highly optimized loop nests. The performance of one of those kernels (the matrix-vector multiplication) is thoroughly analyzed using the Execution-Cache-Memory (ECM) performance model. We validate these predictions by measurements on the SuperMUC-NG supercomputer. The experiments show that the performance mostly matches the predictions. In cases where the prediction does not match, we discuss the discrepancies. Additionally, we conduct a node-level scaling study which shows the expected behavior for a memory-bound compute kernel.

Authors with CRIS profile

Dominik Thönnes Lehrstuhl für Informatik 10 (Systemsimulation) Ulrich Rüde Lehrstuhl für Informatik 10 (Systemsimulation)

How to cite

APA:

Thönnes, D., & Rüde, U. (2023). Model-Based Performance Analysis of the HyTeG Finite Element Framework.

MLA:

Thönnes, Dominik, and Ulrich Rüde. "Model-Based Performance Analysis of the HyTeG Finite Element Framework." 2023.

BibTeX: Download