Framework for Parallel Kernels Auto-tuning
Masaryk University, Faculty of Informatics
Masaryk University, 2018
@article{petrovivc2018framework,
title={Framework for Parallel Kernels Auto-tuning},
author={Petrovi{v{c}}, Bc Filip},
year={2018}
}
The result of this thesis is a framework for auto-tuning of parallel kernels which are written in either OpenCL or CUDA language. The framework includes advanced functionality such as support for composite kernels and online auto-tuning. The thesis describes API and internal structure of the framework and presents several examples of its utilization for kernel optimization.
November 10, 2019 by hgpu
