Performance Monitor Based Power Management for big.LITTLE Platforms

Simon Holmbacka, Sebastien Lafond, Johan Lilius

Research output: Chapter in Book/Conference proceedingConference contributionScientificpeer-review


Recently new heterogeneous computing architectures, coupling low-power low-end cores with powerful, power-hungry cores, appeared on the market. From a power management point of view, and compared to traditional homogeneous multi-core architectures, such architectures provide one more variable: the core type to map applications on. At the same time conventional power managers drives theDVFS mechanism based on the notion of workload. This means that as long as the CPU is capable of executing work, a workload increase will result in a frequency increase. In practice this results in a Race-to-Idle execution which mostlyuses high clock frequencies. In this work we propose a performance monitor based power manager for cluster switched ARM big.LITTLE architectures. The proposed power manager allocates resources based on application performancerather than workload levels, which allows the hardware to adapt closer to software requirements. The presented power manager is capable of saving up to 57% of energy with the addition of one line of c-code in legacy applications.
Original languageUndefined/Unknown
Title of host publicationN/A
PublisherInternational conference on high-performance and embedded architectures and compilers
Publication statusPublished - 2015
MoE publication typeA4 Article in a conference publication
Eventconference; 2015-01-19; 2015-01-21 - International conference on high-performance and embedded architectures and compilers HiPEAC 2015
Duration: 19 Jan 201521 Jan 2015


Conferenceconference; 2015-01-19; 2015-01-21

Cite this