DCApr 19

EcoShift: Performance-Aware Power Management for Power-Constrained Heterogeneous Systems

arXiv:2604.1763513.8h-index: 2
Predicted impact top 78% in DC · last 90 daysOriginality Incremental advance
AI Analysis

For HPC system administrators, EcoShift improves power allocation efficiency in heterogeneous clusters, leading to better application performance under strict power caps.

EcoShift is a performance-aware power management framework for power-constrained heterogeneous HPC systems that uses online performance prediction and dynamic programming to distribute reclaimed power across CPU-GPU applications, achieving up to 6% average performance improvement over state-of-the-art policies while maintaining power constraints.

Power-constrained HPC systems increasingly run heterogeneous CPU--GPU applications under strict cluster-wide power limits. Existing cluster-wide power management policies rely on fair-share or utilization heuristics and do not capture application-specific sensitivity to CPU and GPU power caps, leading to inefficient use of reclaimed power. We present EcoShift, a performance-aware cluster-wide power management framework. EcoShift combines online performance prediction with a dynamic-programming-based allocator to distribute reclaimed power across CPU--GPU applications for maximum average performance improvement. Through emulation-based evaluation on two heterogeneous Intel CPU and NVIDIA A100/H100 GPU platforms with diverse CPU--GPU workloads, EcoShift consistently outperforms state-of-the-art policies, achieving up to 6% average performance improvement while preserving the cluster-wide power constraint.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes