Webinars
- The PowerStack Initiative (A Community-driven Effort), EEHPC-WG Webinar Series, October 2018
News Articles
- “PowerStack: A global response to the power management problem for exascale”, HIPEAC 2019 Blog Article
- Power and Performance Optimization at Exascale, InsideHPC, March 2018
- Energy efficiency and the software stack, InsideHPC, December 2017
- A global survey of HPC center energy and power-aware job scheduling and resource management, InsideHPC, November 2017
Publications on System/Site-Level Efficiency Studies
- Ryuichi Sakamoto et al., “Analyzing Resource Trade-offs in Hardware Overprovisioned Supercomputers”, IPDPS 2018
- Matthias Maiterth et al., “Energy and Power-Aware Job Scheduling and Resource Management: Global Survey - Initial Analysis”, HPPAC 2018
Publications on Application-Level Efficiency Studies
- Eastep et al., “Global Extensible Open Power Manager: A vehicle for HPC Community Collaboration on Co-Designed Energy Management Solutions”, ISC 2017
Strawman Docs
- “A Strawman for an HPC PowerStack”, OSTI Technical Report, August 2018
The PowerStack team intends to leverage existing well-engineered solutions when designing and implementing interfaces that work through various layers of the stack. Here, we list state-of-the-art software for power management that we are exploring and intending to extend as a part of this approach. Links to software/repositories to be added shortly.
Resource Managers/Schedulers
- SLURM
- PBSPro
- Cobalt
- Flux
Runtime Systems
Node-Level Interfaces
Existing Standardization Efforts
- PowerAPI (specifications with focus on node-level design)
- EEHPCWG JSRM (focus on site-level job scheduling policies)