MAGUS: Memory-Throughput-Based Uncore Frequency Scaling on Heterogeneous Systems (poster)

Created on May 08, 2025

2025   ·   paper   ·   papers   Supercomputing   Data Science   High Performance Computing

MAGUS: Memory-Throughput-Based Uncore Frequency Scaling on Heterogeneous Systems (poster)

Zheng, Z.,Sultanov, S.,Papka, M. E.,Lan, Z.

image

Prior uncore frequency tuning studies have primarily focused on conventional HPC workloads running on CPU-only systems. As HPC advances toward heterogeneous computing, integrating diverse GPU workloads on heterogeneous CPU-GPU systems, it becomes imperative to revisit and enhance uncore scaling. Our investigation reveals that uncore frequency scales down only when CPU power approaches its TDP (Thermal Design Power) – a rare scenario in GPU-dominant applications – resulting in unnecessary power waste in modern computing systems.

Citation: Zheng, Z., Sultanov, S., Papka, M. E., Lan, Z., MAGUS: Memory-Throughput-Based Uncore Frequency Scaling on Heterogeneous Systems (poster), The 12th Greater Chicago Area Systems Research Workshop (GCASR), Chicago, IL, 2025-05-08. https://gcasr.org/2025/posters