Authors: Ruda, Dustin
Turek, Stefan
Ribbrock, Dirk
Zajac, Peter
Title: Very fast finite element Poisson solvers on lower precision accelerator hardware: A proof of concept study for Nvidia Tesla V100
Language (ISO): en
Abstract: Recently, accelerator hardware in the form of graphics cards including Tensor Cores, specialized for AI, has significantly gained importance in the domain of high-performance computing. For example, NVIDIA’s Tesla V100 promises a computing power of up to 125 TFLOP/s achieved by Tensor Cores, but only if half precision floating point format is used. We describe the difficulties and discrepancy between theoretical and actual computing power if one seeks to use such hardware for numerical simulations, that is, solving partial differential equations with a matrix-based finite element method, with numerical examples. If certain requirements, namely low condition numbers and many dense matrix operations, are met, the indicated high performance can be reached without an excessive loss of accuracy. A new method to solve linear systems arising from Poisson’s equation in 2D that meets these requirements, based on “prehandling” by means of hier-archical finite elements and an additional Schur complement approach, is presented and analyzed. We provide numerical results illustrating the computational performance of this method and compare it to a commonly used (geometric) multigrid solver on standard hardware. It turns out that we can exploit nearly the full computational power of Tensor Cores and achieve a significant speed-up compared to the standard methodology without losing accuracy.
Subject Headings: Accelerator hardware
Tensor core GPUs
NVIDIA V100
Prehandling
Hierarchical finite elements
Poisson's equation
URI: http://hdl.handle.net/2003/41313
http://dx.doi.org/10.17877/DE290R-23156
Issue Date: 2022-05-06
Rights link: https://creativecommons.org/licenses/by/4.0/
Appears in Collections:Lehrstuhl III Angewandte Mathematik und Numerik

Files in This Item:
File Description SizeFormat 
10943420221084657.pdf1.99 MBAdobe PDFView/Open


This item is protected by original copyright



This item is licensed under a Creative Commons License Creative Commons