A benchmark set of highly-efficient CUDA and OpenCL kernels and its dynamic autotuning with Kernel Tuning Toolkit

Open Webpage

Filip Petrovic, David Strelák, Jana Hozzová, Jaroslav Olha, Richard Trembecký, Siegfried Benkner, Jiri Filipovic

Published: 01 Jan 2020, Last Modified: 15 May 2024Future Gener. Comput. Syst. 2020EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Introduces dynamic autotuning of OpenCL or CUDA kernels with KTT framework.•Introduces a set of ten highly-efficient tunable benchmarks.•Evaluates benchmarks’ performance portability using various GPUs, CPU, and Xeon Phi.•Demonstrates dynamic autotuning with a real-world application.