Accuracy-Aware Mixed-Precision GPU Auto-Tuning

Reduced-precision floating-point arithmetic has become increasingly important in GPU applications for AI and HPC, as it can deliver substantial speedups while reducing energy consumption and memory footprint. However, choosing the appropriate data formats brings a challenging tuning problem: precision parameters must be chosen to maximize performance while preserving numerical accuracy. At the same time, GPU kernels typically expose additional tunable optimization parameters, such as block size, tiling strategy, and vector width. The combination of these two kinds of parameters results in a complex trade-off between accuracy and performance, making manual exploration of the resulting design space time-consuming. In this work, we present an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">accuracy-aware</i> extension to the open-source <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Kernel Tuner</i> framework, enabling automatic tuning of floating-point precision parameters alongside conventional code-optimization parameters. We evaluate our accuracy-aware tuning solution on both Nvidia and AMD GPUs using a variety of kernels. Our results show speedups of up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$12{\times }$</tex-math></inline-formula> over double precision, demonstrate how Kernel Tuner's built-in search strategies are effective for accuracy-aware tuning, and show that our approach can be extended to other optimization objectives, such as memory footprint or energy efficiency. Moreover, we highlight that jointly tuning accuracy- and performance-affecting parameters outperforms isolated approaches in finding the best-performing configurations, despite significantly expanding the optimization space. This unified approach enables developers to trade accuracy for throughput systematically, enabling broader adoption of mixed-precision computing in scientific and industrial applications.