pVOCL: Power-Aware Dynamic Placement and Migration in Virtualized GPU Environments

Palden Lama, Yan Li, Ashwin M. Aji, Pavan Balaji, James Dinan, Shucai Xiao, Yunquan Zhang, Wu-chun Feng, Rajeev Thakur, Xiaobo Zhou
Department of Computer Science, University of Colorado, Colorado Springs, USA
International Conference on Distributed Computing Systems (ICDCS), 2013


   title={pVOCL: Power-Aware Dynamic Placement and Migration in Virtualized GPU Environments},

   author={Lama, Palden and Li, Yan and Aji, Ashwin M and Balaji, Pavan and Dinan, James and Xiao, Shucai and Zhang, Yunquan and Feng, Wu-chun and Thakur, Rajeev and Zhou, Xiaobo},



Download Download (PDF)   View View   Source Source   



Power-hungry Graphics processing unit (GPU) accelerators are ubiquitous in high performance computing data centers today. GPU virtualization frameworks introduce new opportunities for effective management of GPU resources by decoupling them from application execution. However, power management of GPU-enabled server clusters faces significant challenges. The underlying system infrastructure shows complex power consumption characteristics depending on the placement of GPU workloads across various compute nodes, power-phases and cabinets in a datacenter. GPU resources need to be scheduled dynamically in the face of time-varying resource demand and peak power constraints. We propose and develop a power-aware virtual OpenCL (pVOCL) framework that controls the peak power consumption and improves the energy efficiency of the underlying server system through dynamic consolidation and power-phase topology aware placement of GPU workloads. Experimental results show that pVOCL achieves significant energy savings compared to existing power management techniques for GPU-enabled server clusters, while incurring negligible impact on performance. It drives the system towards energy-efficient configurations by taking an optimal sequence of adaptation actions in a virtualized GPU environment and meanwhile keeps the power consumption below the peak power budget.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: