Coordinated Power Management on Heterogeneous Systems

TL;DR

This paper introduces OPEN, a hybrid offline-online framework for accurate, low-cost performance prediction in heterogeneous CPU-GPU systems, facilitating power-aware computing decisions.

Contribution

The paper presents OPEN, a novel performance prediction framework combining offline modeling and online profiling with collaborative filtering for heterogeneous systems.

Findings

OPEN achieves up to 98.29% prediction accuracy.

The framework significantly reduces profiling costs.

It enables practical power-aware performance modeling.

Abstract

Performance prediction is essential for energy-efficient computing in heterogeneous computing systems that integrate CPUs and GPUs. However, traditional performance modeling methods often rely on exhaustive offline profiling, which becomes impractical due to the large setting space and the high cost of profiling large-scale applications. In this paper, we present OPEN, a framework consists of offline and online phases. The offline phase involves building a performance predictor and constructing an initial dense matrix. In the online phase, OPEN performs lightweight online profiling, and leverages the performance predictor with collaborative filtering to make performance prediction. We evaluate OPEN on multiple heterogeneous systems, including those equipped with A100 and A30 GPUs. Results show that OPEN achieves prediction accuracy up to 98.29\%. This demonstrates that OPEN effectively reduces profiling cost while maintaining high accuracy, making it practical for power-aware performance modeling in modern HPC environments. Overall, OPEN provides a lightweight solution for performance prediction under power constraints, enabling better runtime decisions in power-aware computing environments.