Exploring Uncore Frequency Scaling for Heterogeneous Computing

2025-02-06

AI Summary

Traditional uncore frequency scaling in CPU-GPU heterogeneous systems—triggered solely when CPU power approaches its TDP—proves inefficient under GPU-bound workloads, causing substantial energy waste. Method: This paper first identifies a key phenomenon: under GPU-intensive workloads, uncore frequency need not scale down synchronously with CPU power. Leveraging this insight, we propose MAGUS—a phase-aware, memory-throughput-driven adaptive uncore frequency scaling framework. MAGUS integrates fine-grained execution-phase identification, real-time bandwidth monitoring and prediction, vendor-specific power interface support, and low-overhead runtime scheduling. Contribution/Results: Evaluated across multiple architectures, MAGUS achieves up to 27% energy reduction and 26% improvement in energy-delay product (EDP), with less than 5% performance degradation and sub-1% runtime overhead.

Technology Category

• Machine Learning: Hardware-aware ML
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems
• Multiagent Systems: Mechanism Design

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

High-performance computing (HPC) systems are essential for scientific discovery and engineering innovation. However, their growing power demands pose significant challenges, particularly as systems scale to the exascale level. Prior uncore frequency tuning studies have primarily focused on conventional HPC workloads running on homogeneous systems. As HPC advances toward heterogeneous computing, integrating diverse GPU workloads on heterogeneous CPU-GPU systems, it is crucial to revisit and enhance uncore scaling. Our investigation reveals that uncore frequency scales down only when CPU power approaches its TDP (Thermal Design Power), an uncommon scenario in GPU-dominant applications, resulting in unnecessary power waste in modern heterogeneous computing systems. To address this, we present MAGUS, a user-transparent uncore frequency scaling runtime for heterogeneous computing. Effective uncore tuning is inherently complex, requiring dynamic detection of application execution phases that affect uncore utilization. Moreover, any robust strategy must work across a diverse range of applications, each with unique behaviors and resource requirements. Finally, an efficient runtime should introduce minimal overhead. We incorporate several key techniques in the design of MAGUS, including monitoring and predicting memory throughput, managing frequent phase transitions, and leveraging vendor-supplied power management support. We evaluate MAGUS using a diverse set of GPU benchmarks and applications across multiple heterogeneous systems with different CPU and GPU architectures. The experimental results show that MAGUS achieves up to 27% energy savings and 26% energy-delay product (EDP) reduction compared to the default settings while maintaining a performance loss below 5% and an overhead under 1%.

Problem

• Optimizing energy in heterogeneous computing
• Dynamic uncore frequency scaling for GPUs
• Minimizing overhead in HPC systems

Innovation

• Uncore frequency scaling
• Dynamic phase detection
• Minimal overhead runtime