Alessio ScloccoLast week we released version 1.1 of Kernel Tuner, out Python tool for performance, and energy-efficiency, tuning of GPU applications.
https://github.com/KernelTuner/kernel_tuner/releases/tag/1.1.0
The university of Leiden published a news item about the imminent release of version 1.0 of Kernel Tuner.
Optimisation software 'Kernel Tuner' ready for serious use
LIACS assistant professor Ben van Werkhoven leads the development of software for optimising graphics processing units. By now, version 1.0 of 'Kernel Tuner' is just around the corner. This milestone shows that the software is ready for serious use.
Alessio ScloccoIf you are interested in the slides of our SC23 tutorial on "Energy-efficient GPU computing" you can download them at the following link! You can also run the hands-on exercises on Google Colab for free if you want :)
https://github.com/KernelTuner/kernel_tuner_tutorial/blob/master/slides/2023_Supercomputing/SC23.pdf
Netherlands eScience CenterWe are at the United Kingdom Research Software Engineer (#RSEs) Conference (#RSECon23) today hosting 2 sessions:
👉 Our RSE Alessio and PhD Candidates Floris-Jan and Stijn are teaching RSEs how to improve the performance of their #GPU applications using #KernelTuner
👉Our Training Programme Lead, Mateusz, is providing an update on RSE activities @eScienceCenter & in the NL!
👉 Our RSE Alessio and PhD Candidates Floris-Jan and Stijn are teaching RSEs how to improve the performance of their #GPU applications using #KernelTuner
👉Our Training Programme Lead, Mateusz, is providing an update on RSE activities @eScienceCenter & in the NL!
My colleagues presented an interesting paper on autotuning GPUs for energy efficiency titled "Going green: optimizing GPUs for energy efficiency through model-steered auto-tuning".
Preprint is already available https://arxiv.org/abs/2211.07260
Going green: optimizing GPUs for energy efficiency through model-steered auto-tuning
Graphics Processing Units (GPUs) have revolutionized the computing landscape over the past decade. However, the growing energy demands of data centres and computing facilities equipped with GPUs come with significant capital and environmental costs. The energy consumption of GPU applications greatly depend on how well they are optimized. Auto-tuning is an effective and commonly applied technique of finding the optimal combination of algorithm, application, and hardware parameters to optimize performance of a GPU application. In this paper, we introduce new energy monitoring and optimization capabilities in Kernel Tuner, a generic auto-tuning tool for GPU applications. These capabilities enable us to investigate the difference between tuning for execution time and various approaches to improve energy efficiency, and investigate the differences in tuning difficulty. Additionally, our model for GPU power consumption greatly reduces the large tuning search space by providing clock frequencies for which a GPU is likely most energy efficient.