Efficient DVFS to Prevent Hard Faults for Many-Core Architectures

Dynamic Voltage and Frequency Scaling (DVFS) is a widely-used and efficient technology for Dynamic Power management (DPM). To avoid hard faults caused by voltage and frequency scaling, some overhead always be imposed on the performance of applications due to the latency of DVFS. Besides, on many-core architectures, the design of multiple voltage domains has made the latency of DVFS a much more significant issue. In this paper, we propose an efficient DVFS scheme to prevent hard faults, meanwhile eliminating the impact of latency of DVFS as possible. The main idea is applying Retroactive Frequency Scaling (RFS) where the latency of DVFS might be introduced. Based on the analysis, our approach is expected to achieve noticeable performance improvement on many-core architectures.

[1]  Giovanni De Micheli,et al.  Power and Reliability Management of SoCs , 2007, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[2]  Philip Levis,et al.  Policies for dynamic clock scheduling , 2000, OSDI.

[3]  Kai Ma,et al.  Scalable power control for many-core architectures running multi-threaded applications , 2011, 2011 38th Annual International Symposium on Computer Architecture (ISCA).

[4]  Scott Shenker,et al.  Scheduling for reduced CPU energy , 1994, OSDI '94.

[5]  Thomas F. Wenisch,et al.  CoScale: Coordinating CPU and Memory System DVFS in Server Systems , 2012, 2012 45th Annual IEEE/ACM International Symposium on Microarchitecture.

[6]  Yifeng Guo,et al.  Reliability-aware power management for parallel real-time applications with precedence constraints , 2011, 2011 International Green Computing Conference and Workshops.

[7]  Shekhar Y. Borkar,et al.  Thousand Core ChipsA Technology Perspective , 2007, 2007 44th ACM/IEEE Design Automation Conference.

[8]  Cho-Li Wang,et al.  Latency-Aware Dynamic Voltage and Frequency Scaling on Many-Core Architectures for Data-Intensive Applications , 2013, 2013 International Conference on Cloud Computing and Big Data.

[9]  Manish Parashar,et al.  Exploring cross-layer power management for PGAS applications on the SCC platform , 2012, HPDC '12.

[10]  Klaus Waldschmidt,et al.  Reliability-Aware Power Management of Multi-Core Processors , 2006, DIPES.

[11]  Saurabh Dighe,et al.  A 48-Core IA-32 Processor in 45 nm CMOS Using On-Die Message-Passing and DVFS for Performance and Power Scaling , 2011, IEEE Journal of Solid-State Circuits.