-
Welcome
-
Subscribe to
packing, spreading and scheduling latency
This proposal has been accepted as a session.
One Line Summary
When packing tasks can improve power efficiency and scheduling latency
Abstract
Spreading tasks on CPUs is the default policy to improve performance by minimizing resources sharing and scheduling latency but the final behavior doesn’t always follow the rule. This talk will describe how some information like the power domain topology or the wakeup latency can be used in the scheduler to improve power efficiency and scheduling latency. Based on the results of an implementation, the talk will explain when it’s worth to pack tasks but also why it can sometimes deserve the power efficiency of the system.
Presentation Materials
slidesSpeakers
-
Vincent Guittot
STMicroelectronics- Favorites: View Vincent's favorites
Biography
Vincent Guittot is an embedded Linux engineer at STMicroelectronics.
Since 2005, he has focused on mobile phone running Linux and Android. In 2010, he has joined the power management working group of Linaro and starts to work on all part of the kernel that could improve the power consumption.Sessions
-
- Title: packing, spreading and scheduling latency
- Microconference: Power-efficient Scheduling
-
One Line Summary:
When packing tasks can improve power efficiency and scheduling latency
- slides
- Speakers: Vincent Guittot, Tuukka Tikkanen
-
Tuukka Tikkanen
Linaro Limited, Huawei- Website: http://www.linaro.org/
Biography
Tuukka Tikkanen is a senior kernel engineer at Huawei, assigned to Linaro collaboration. He has been contributing to Linux kernel power management working with Elektrobit, Nokia and Huawei. He wrote the original clock framework in 2004 for OMAP platform. Currently he is working on improving power management and scheduling for multicore SoC systems, focusing on ARM big.LITTLE platforms.
Sessions
-
- Title: packing, spreading and scheduling latency
- Microconference: Power-efficient Scheduling
-
One Line Summary:
When packing tasks can improve power efficiency and scheduling latency
- slides
- Speakers: Vincent Guittot, Tuukka Tikkanen