• Corpus ID: 11131333

A Comparison of High-Level Full-System Power Models

@inproceedings{Rivoire2008ACO,
  title={A Comparison of High-Level Full-System Power Models},
  author={Suzanne Rivoire and Parthasarathy Ranganathan and Christoforos E. Kozyrakis},
  booktitle={HotPower},
  year={2008}
}
Dynamic power management in enterprise environments requires an understanding of the relationship between resource utilization and system-level power consumption. Power models based on resource utilization have been proposed in the context of enabling specific energy-efficiency optimizations on specific machines, but the accuracy and portability of different approaches to modeling have not been systematically compared. In this work, we use a common infrastructure to fit a family of high-level… 

Figures from this paper

Performance Events Based Full System Estimation on Application Power Consumption
  • Shu Yang, Zhongzhi Luan, Binyang Li, Ge Zhang, Tianming Huang, D. Qian
  • Computer Science, Engineering
    2016 IEEE 18th International Conference on High Performance Computing and Communications; IEEE 14th International Conference on Smart City; IEEE 2nd International Conference on Data Science and Systems (HPCC/SmartCity/DSS)
  • 2016
TLDR
The power models proposed in this paper can provide software developers or system designers with visible power behaviors for the applications and can make decisions or change code to develop more energy-efficient software.
A Novel Power Model and Completion Time Model for Virtualized Environments
TLDR
An empirically derived power model and a completion time model using linear regression with CPU utilization and operating frequency of the server as parameters are presented and are in the process of being employed to control VM provisioning to minimize power consumption.
Modeling System-Level Power Consumption Profiles Using RAPL
TLDR
This work presents a prototype lightweight software-based virtual power meter that offers comparable or superior performance to existing power models that are more complex and is viable for use in real-world applications such as power estimation for energy-aware scheduling.
CHAOS: Composable Highly Accurate OS-based power models
TLDR
This paper presents Composable, Highly Accurate, OS-based (CHAOS) full-system power models for machines and clusters, and defines a metric called Dynamic Range Error (DRE) to describe how well the model characterizes the dynamic system behavior.
Analysis of the Influences on Server Power Consumption and Energy Efficiency for CPU-Intensive Workloads
TLDR
It is shown that workloads targeting the same resource can differ significantly in their power draw and energy efficiency, as the power consumption of a given workload type varies depending on utilization, hardware and software configuration.
Low-cost estimation of sub-system power
TLDR
DiPART (Disaggregated Power Analysis in Real Time), a tool to estimate subsystem power consumption based on performance (event) counters and a single, system-wide power sensor, is presented.
A Simple Model for Estimating Power Consumption of a Multicore Server System
TLDR
This paper proposes a simple power model for a multicore server that is simple enough to gather only four parameters: operating frequency, the number of active cores, theNumber of cache accesses and thenumber of the last level cache misses.
Variations in CPU Power Consumption
TLDR
The results of this paper show that selection of a processor sample can have a statistically significant impact on power consumption, and show that these variations change over different architectures and processor types.
No Hardware Required: Building and Validating Composable Highly Accurate OS-based Power Models
TLDR
This paper presents an automatic framework for modeling nodeand cluster-level power consumption, using only portable OS-level performance counters, and defines a new metric called Dynamic Range Error (DRE) to describe how well the model characterizes the dynamic system behavior and facilitate interand intra-cluster model accuracy comparisons.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 28 REFERENCES
Run-time modeling and estimation of operating system power consumption
TLDR
The most striking observation is the strong correlation between power consumption and the instructions per cycle (IPC) during OS routine executions, and the proposed models can estimate OS power for run-time dynamic thermal and energy management.
Full-System Power Analysis and Modeling for Server Environments
TLDR
This work examines the validity of prior adhoc approaches to understanding power breakdown and quantify several interesting trends important for power modeling and management in the future, and introduces Mantis, a nonintrusive method for modeling full-system power consumption and providing real-time power prediction.
Models and metrics for energy-efficient computer systems
TLDR
This dissertation describes the benchmark design, highlighting the challenges and pitfalls of energy-efficiency benchmarking that distinguish it from benchmarking pure performance, and describes the design of the machine with the highest known JouleSort score.
Ensemble-level Power Management for Dense Blade Servers
TLDR
This paper proposes power efficiencies at a larger scale by leveraging statistical properties of concurrent resource usage across a collection of systems ("ensemble") by discussing an implementation of this approach at the blade enclosure level to monitor and manage the power across the individual blades in a chassis.
Power prediction for Intel XScale processors using performance monitoring unit events
TLDR
A first-order, linear power estimation model that uses performance counters to estimate run-time CPU and memory power consumption of the Intel PXA255 processor that can serve as a foundation for intelligent, poweraware embedded systems that dynamically adapt to the device’s power consumption is demonstrated.
Power prediction for Intel XScale/spl reg/ processors using performance monitoring unit events
  • Gilberto Contreras, M. Martonosi
  • Computer Science
    ISLPED '05. Proceedings of the 2005 International Symposium on Low Power Electronics and Design, 2005.
  • 2005
TLDR
A first-order, linear power estimation model that uses performance counters to estimate run-time CPU and memory power consumption of the Intel PXA255 processor that can serve as a foundation for intelligent, power-aware embedded systems that dynamically adapt to the device's power consumption is demonstrated.
Simulating Complex Enterprise Workloads using Utilization Traces
TLDR
This paper proposes an alternate approach to simulating such environments that uses resource utilization traces from real deployments in conjunction with high-level models that correlate resource utilization to system metrics like power and performance, to emulate the system behavior.
The benefits of event: driven energy accounting in power-sensitive systems
TLDR
This work evaluates the energy usage of each thread and throttles the system activity so that the scheduling goal is achieved, and shows that the correlation of events and energy values provides the necessary information for energy-aware scheduling policies.
Run-time power estimation in high performance microprocessors
TLDR
The Castle project is presented, which aims to deduce the actual runtime power dissipated by different processor units on the CPU chip by leveraging existing hardware.
Load balancing and unbalancing for power and performance in cluster-based systems
TLDR
The approach is to develop systems that dynamically turn cluster nodes on – to be able to handle the load imposed on the system efficiently – and off – to save power under lighter load.
...
1
2
3
...