Book ChapterDOI
Power consumption breakdown on a modern laptop
Aqeel Mahesri,Vibhore Vardhan +1 more
- pp 165-180
Reads0
Chats0
TLDR
The purpose of this work was to obtain a component-wise breakdown of the power consumption a modern laptop and found that reducing the backlight brightness can reduce the system power significantly, more than any other display power saving techniques.Abstract:
The purpose of this work was to obtain a component-wise breakdown of the power consumption a modern laptop. We measured the power usage of the key components in an IBM ThinkPad R40 laptop using an Agilent Oscilloscope and current probes. We obtained the power consumption for the CPU, optical drive, hard disk, display, graphics card, memory, and wireless card subsystems–either through direct measurement or subtractive measurement and calculation. Moreover, we measured the power consumption of each component for a variety of workloads. We found that total system power consumption varies a lot (8 W to 30 W) depending on the workload, and moreover that the distribution of power consumption among the components varies even more widely. We also found that though power saving techniques such as DVS can reduce CPU power considerably, the total system power is still dominated by CPU power in the case of CPU intensive workloads. The display is the other main source of power consumption in a laptop; it dominates when the CPU is idle. We also found that reducing the backlight brightness can reduce the system power significantly, more than any other display power saving techniques. Finally, we observed OS differences in the power consumption.read more
Citations
More filters
Proceedings Article
An analysis of power consumption in a smartphone
Aaron Carroll,Gernot Heiser +1 more
TL;DR: A detailed analysis of the power consumption of a recent mobile phone, the Openmoko Neo Freerunner, measuring not only overall system power, but the exact breakdown of power consumption by the device's main hardware components.
Journal ArticleDOI
EnerJ: approximate data types for safe and general low-power computation
TL;DR: EnerJ is developed, an extension to Java that adds approximate data types and a hardware architecture that offers explicit approximate storage and computation and allows a programmer to control explicitly how information flows from approximate data to precise data.
Proceedings ArticleDOI
Virtual machine power metering and provisioning
TL;DR: Joulemeter builds power models to infer power consumption from resource usage at runtime and identifies the challenges that arise when applying such models for VM power metering, and shows how existing instrumentation in server hardware and hypervisors can be used to build the required power models on real platforms with low error.
Proceedings ArticleDOI
Into the wild: studying real user activity patterns to guide power optimizations for mobile architectures
TL;DR: A regression-based power estimation model is presented that accurately estimates power consumption and provides insights about the power breakdown among hardware components, and it is shown that energy consumption widely varies depending upon the user.
Proceedings ArticleDOI
Fine-grained power modeling for smartphones using system call tracing
TL;DR: This work proposes a new, system-call-based power modeling approach which gracefully encompasses both utilization-based and non-utilization- based power behavior and presents the detailed design of such a power modeling scheme, its implementation on Android and Windows Mobile, and results confirm that the new model significantly improves the fine-grained as well as whole-application energy consumption accuracy.
References
More filters
Journal ArticleDOI
Power aware page allocation
TL;DR: This paper considers page allocation policies that can be employed by an informed operating system to complement the hardware power management strategies and makes a compelling case for a cooperative hardware/software approach for exploiting power-aware memory.
Journal ArticleDOI
Energy-efficient soft real-time CPU scheduling for mobile multimedia systems
Wanghong Yuan,Klara Nahrstedt +1 more
TL;DR: Compared to deterministic scheduling and voltage scaling, GRACE-OS saves energy by 7% to 72% while delivering statistical performance guarantees, and delivers soft performance guarantees by bounding the deadline miss ratio under application-specific requirements.
Journal ArticleDOI
Cooperative I/O: a novel I/O semantics for energy-aware applications
TL;DR: It is shown that Coop-I/O even outperforms the "oracle" shutdown policy which defines the lower bound in power consumption if the timing of requests can not be influenced, and the experimental results demonstrate the benefits of the concept.
Proceedings ArticleDOI
Low Power Control Techniques For TFT LCD Displays
TL;DR: This paper introduces several software-only techniques for LCD dynamic power management, which do not require any hardware changes on existing LCDs and their controllers.
Proceedings ArticleDOI
Energy estimation tools for the Palm
TL;DR: This paper describes an energy model and an execution-driven simulator incorporating this model for the PalmOS#8482; family of devices and suggests a higher-level view in which energy management becomes an explicit design goal of the software developer who can be more aware of the needs of applications.