2016 16th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) 2016
DOI: 10.1109/ccgrid.2016.25
|View full text |Cite
|
Sign up to set email alerts
|

Demand-Aware Power Management for Power-Constrained HPC Systems

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
14
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
4
1
1

Relationship

1
5

Authors

Journals

citations
Cited by 22 publications
(14 citation statements)
references
References 16 publications
0
14
0
Order By: Relevance
“…Sarood et al [48] use performance modeling to increase job throughput in power constrained systems. A power management of overprovisioned systems has also been studied by Patki et al [12,43]. Unlike our work, all sockets are viewed as homogeneous in terms of power consumption, which can lead to suboptimal scheduling decisions.…”
Section: Power-aware Budgeting and Schedulingmentioning
confidence: 93%
See 2 more Smart Citations
“…Sarood et al [48] use performance modeling to increase job throughput in power constrained systems. A power management of overprovisioned systems has also been studied by Patki et al [12,43]. Unlike our work, all sockets are viewed as homogeneous in terms of power consumption, which can lead to suboptimal scheduling decisions.…”
Section: Power-aware Budgeting and Schedulingmentioning
confidence: 93%
“…SLURM extended policy implements SLURM's logic in our simulator, with the addition of power-awareness and power backfilling. SLURM+PE and SLURM+PEVA employ state-of-the-art features of proposed power-aware policies [12,22,43], while SLURM+IVP demonstrates the ideal scenario, where prediction is 100% accurate. The evaluation is done based on a simulator, as described in Section 4.1, by feeding it performance and power traces from actual executions on the Quartz cluster.…”
Section: Variability-aware Scheduling Evaluationmentioning
confidence: 99%
See 1 more Smart Citation
“…Power-performance optimization methodologies typically aim at maximizing application performance while satisfying given constraints (power budget, energy consumption, application execution deadline, etc.). Most of them are mainly based on "power-shifting" among hardware components [9,13,19] or among applications/jobs [3,17,20,24,26]. Usually we have a large number of jobs running on a HPC system, and hence optimizing power-performance in both intraand inter-application cases is important.…”
Section: Power-performance Optimizationmentioning
confidence: 99%
“…Cao et al developed a demand-aware power management approach [24]. With this approach, job scheduler allocates power budget and hardware resources to run jobs considering their demands and the total system power consumption.…”
Section: Power-performance Optimizationmentioning
confidence: 99%