GPU-Accelerated Simulations of Isolated Black Holes
| Autor: | Adam G. M. Lewis, Harald P. Pfeiffer |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
Physics
Physics and Astronomy (miscellaneous) Syntax (programming languages) 010308 nuclear & particles physics FOS: Physical sciences Spec# General Relativity and Quantum Cosmology (gr-qc) Parallel computing Computational Physics (physics.comp-ph) 01 natural sciences Porting General Relativity and Quantum Cosmology CUDA Numerical relativity 0103 physical sciences Code (cryptography) Benchmark (computing) Cache 010306 general physics computer Physics - Computational Physics computer.programming_language ComputingMethodologies_COMPUTERGRAPHICS |
| Zdroj: | Classical and Quantum Gravity |
| Popis: | We present a port of the numerical relativity code SpEC which is capable of running on NVIDIA GPUs. Since this code must be maintained in parallel with SpEC itself, a primary design consideration is to perform as few explicit code changes as possible. We therefore rely on a hierarchy of automated porting strategies. At the highest level we use TLoops, a C++ library of our design, to automatically emit CUDA code equivalent to tensorial expressions written into C++ source using a syntax similar to analytic calculation. Next, we trace out and cache explicit matrix representations of the numerous linear transformations in the SpEC code, which allows these to be performed on the GPU using pre-existing matrix-multiplication libraries. We port the few remaining important modules by hand. In this paper we detail the specifics of our port, and present benchmarks of it simulating isolated black hole spacetimes on several generations of NVIDIA GPU. 42 pages, 11 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|