Articles and Resources:
Processors and Performance
After the LCD display, the processor is one of the largest consumers of battery life in a notebook PC. A high performance processor in a notebook PC can consume upwards of 30 Watts, which is a large percentage of the entire energy budget of a portable or desktop. Thankfully, newer processors have mechanisms (such as Intel Speedstep) that allow them to run at lower frequencies - either when the applications do not demand a higher frequency, or when the user has selected an energy-conserving power policy. This section has content that addresses the energy-saving features of CPUs, and how applications developers can create software that works in harmony with these features, that allow the CPU to operate in its most energy-efficient manner.
- CPU Power Utilization on Intel® Architecture: Many applications use timer based interrupts for periodic execution of a code section before or at a particular timeline. The granularity of the interrupt frequency has an impact on the platform power. Timers that are too granular (such as every millisecond) degrade CPU C-state residency and therefore use more energy.
- How to Reduce Power Consumption in a Real-Time Threaded Application: This document describes at a high level how Hyper-Threading technology can decrease the total power consumed in a threaded multimedia application.
- Power Optimization: Furthering the Mobile Vision: In this series of Power Optimization whitepapers, we provide developers insight on Intel mobile platform power profiles, and software techniques for optimizing power in specific component s (along with the impact on the overall platform).
Hard disk drives and optical drives also contribute to limiting PC battery life. The longer a disk spins and the amount and frequency of data transfers have a substantial impact on power consumption. SW can significantly influence the impact of disk I/O on battery life. Both the Operating System and applications can reduce power usage with the intelligent organization of data on the hard drive, smart disk caching, and by following a strategy of powering down the drive when not in use.
- DVD Playback Power Consumption Analysis: This paper analyzes the power consumption of different DVD playback software, and provides recommendations for reducing power consumption. For this study, various DVD playback software was analyzed and run with the multiple configurations available. We provide our recommendation on an optimal strategy for reducing power consumption while playing content from a DVD-ROM.
- DVD/CD Rendering: Optimizing for Power on Mobile Platforms: This paper introduces a technique of optimizing a multimedia application when it accesses content from a DVD/CD such that the playback of the DVD/CD comsumes much less power.
- Power Analysis of Disk I/O Methodologies: This paper analyzes the power characteristics of the hard disk during sequential/random reads and native command queuing, and provides an analysis on file fragmentation and disk thrashing. This paper also provides guidelines on optimizing the power during disk I/O in various usage models along with the power impact.
Networking is an important part of the power equation in to day's increasingly mobile environment. Fully mobile users, operating in battery only environments, surf the web in coffee shops, write documents in meetings, and play massive multi-player online games when relaxing in a common area between classes. Strategies and methodologies for combining networking needs and minimizing power usage are a must.
- Data Transfer over Wireless LAN Power Consumption Analysis: As industry moves towards mobile computing, resources like battery life become significantly important for system usability. This paper analyzes power consumption of a laptop while transmitting compressed and non-compressed data over wireless network to determine the most power efficient method. The study focuses on how the compression ratio or size of the file affects power consumption and not on the performance of a particular compression algorithm. Recommendations for transmitting data over wireless network are presented. This study can provide guidelines to developers for writing applications that involves data transmission.