Auto-tuning GPU code for energy efficiency

Graphics Processing Units (GPUs) have revolutionized the computing landscape over the past decades. 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 depends on how well the software is optimized to utilize the underlying hardware. Auto-tuning is an effective and commonly applied technique of finding the optimal combination of algorithm, application, and hardware parameters to optimize the performance of GPU applications. In this talk, I will highlight some of the key challenges, latest developments, and future plans in the field of GPU energy tuning.