Energy use and performance vary with GPU number precision levels
Energy-Aware Performance Characterization of Kokkos Kernels Across Precision Levels
Performance
Summary
Computers doing heavy calculations on GPUs can use different number types that affect how fast and energy-efficient they run. The authors looked at three ways of using these number types and measured how much work the GPUs did, their speed, and how much energy they used. They made new models to show the relationship between energy, performance, and temperature. Their findings show that using 64-bit numbers generally uses more energy, while mixing 32-bit and 64-bit numbers balances speed and energy better depending on the task.
What this means in practice
- •For hpc application developers: Adjusting number precision in GPU kernels to balance energy usage and performance for complex scientific computing.
- •For gpu power management teams: Improving energy and thermal management policies using new models that link GPU temperature, energy use, and kernel execution behavior.
Authors
Maria Patrou, Andrey Prokopenko, Aditya Kashi, Oscar Hernandez, Jean-Luc Fattebert
Abstract
Kokkos is a performance-portable programming model used in GPU-accelerated HPC applications comprising kernels with diverse computational and memory behaviors. We characterize kernels from two applications to evaluate how FP32, FP64, and mixed FP32/FP64 affect arithmetic intensity, performance throughput, and GPU energy consumption. We introduce an Energy-Aware Roofline Model that incorporates energy into performance analysis and a Thermal-Aware Inter-Kernel Energy Model that visualizes energy consumption alongside duration, GPU temperature, and execution order. We study both applications with: (1) fine-grained, application-level instrumentation through the Kokkos Performance Tools PAPI Connector and (2) coarse-grained PAPI instrumentation applied to a dedicated-kernel benchmark using vendor-specific power management components. Our analysis shows that precision effects vary by application, kernel, and workload. Mixed FP32/FP64 kernels generally achieve arithmetic intensity comparable to FP32, with modestly lower throughput and, in most cases, a modest increase in energy consumption. FP64 kernels generally exhibit the highest energy consumption among the evaluated precision configurations.