GPU Power Management: Comparative Analysis and Optimization Using Python and MATLAB Simulations
TL;DR
Simulation-based practice to improve the energy efficiency of Intel Arc GPUs and the Intel CPUs to overcome the issue of power inefficiency, workload imbalance, and thermal limitations indicates that the Intel Arc GPUs used less power compared to CPUs with similar tasks, which makes the argument of their energy efficiency advantage in environments with limited energy.
Abstract
The growing popularity of High-Performance Computing (HPC), artificial intelligence (AI) and sophisticated graphics display has rendered the management of GPS power as an important design factor. Proposed methodology presented in this paper, is a simulation-based practice to improve the energy efficiency of Intel Arc™ GPUs and the Intel CPUs to overcome the issue of power inefficiency, workload imbalance, and thermal limitations. The diagrammatic analysis of MATLAB/Simulink model is used to study the dynamic power behavior of system components under different load conditions. The Intel Arc A770, A750, and B580 GPUs, the Intel Core i7-14700K processor, and a high-voltage Switched-Mode Power Supply (SMPS) are implemented in the model and make it possible to simulate infrastructure realistically. Dynamic Voltage and Frequency Scaling (DVFS), idle power gating and workload-aware scheduling were all applied using the control systems and power electronics toolboxes in MATLAB. Validation of the experiment was conducted by real-time telemetry logging and Python based analysis of power, usage, temperature and frequency metrics of gaming, AI and compute workloads. Findings indicate that, in high-intensity tasks, the Intel Arc GPUs used less power compared to CPUs with similar tasks, which makes the argument of their energy efficiency advantage in environments with limited energy. The model also captures the thermal feedback and the voltage control in the SMPS and makes it stable under varying loads. Researchers and engineers can use this open-source and reproducible tool to obtain actionable insights for micro-architecture and system design of power-efficient high performance computing systems that are adaptable for innovation to concurrent hardware technologies and emerging, sustainability-driven demands.