Investigating the potential of application-centric aggressive power management for HPC workloads

Energy efficiency of large-scale data centers is becoming a major concern not only for reasons of energy conservation, failures, and cost reduction, but also because such sys tems are soon reaching the limits of power available to them. Like High Performance Computing (HPC) systems, large-scale clu ster-based data centers can consume power in megawatts, and of all the power consumed by such a system, only a fraction is used for actual computations. In this paper, we study the potential of application-centric aggressive power management of data center's resources for HPC workloads. Specifically, we consider power management mechanisms and controls (currently or soon to be) available at different levels and for different subsystems, and leverage several innovative approaches that have been taken to tackle this problem in the last few years, can be effectively used in a application-aware manner for HPC workloads. To do this, we first profile sta ndard HPC benchmarks with respect to behaviors, resource usage and power impact on individual computing nodes. Based on a power and latency model and the workload profiles, we develop an algorithm that can improve energy efficiency with little or no performance loss. We then evaluate our proposed algorithm through simulations using empirical power characterization and quantification. Finally, we validate the simulation results with actual executions on real hardware. The obtained results show that by using application aware power management, we can re-du ce the average energy consumption without significant penalty in performance. This motivates us to investigate autonomic approaches for application-aware aggressive power management and cross layer and cross function predictive subsystem level power management for large-scale data centers.

[1]  Kevin Skadron,et al.  Multi-mode energy management for multi-tier server clusters , 2008, 2008 International Conference on Parallel Architectures and Compilation Techniques (PACT).

[2]  Mary Jane Irwin,et al.  Phase-aware adaptive hardware selection for power-efficient scientific computations , 2007, Proceedings of the 2007 international symposium on Low power electronics and design (ISLPED '07).

[3]  Doron Rotem,et al.  Analysis of trade-off between power saving and response time in disk storage systems , 2009, 2009 IEEE International Symposium on Parallel & Distributed Processing.

[4]  Naehyuck Chang,et al.  Memory-aware energy-optimal frequency assignment for dynamic supply voltage scaling , 2004, Proceedings of the 2004 International Symposium on Low Power Electronics and Design (IEEE Cat. No.04TH8758).

[5]  Xiaodong Li,et al.  Cross-component energy management: Joint adaptation of processor and memory , 2007, TACO.

[6]  Feng Pan,et al.  Exploring the energy-time tradeoff in MPI programs on a power-scalable cluster , 2005, 19th IEEE International Parallel and Distributed Processing Symposium.

[7]  Ricardo Bianchini,et al.  Energy conservation in heterogeneous server clusters , 2005, PPoPP.

[8]  Dirk Grunwald,et al.  Massive Arrays of Idle Disks For Storage Archives , 2002, ACM/IEEE SC 2002 Conference (SC'02).

[9]  Alon Naveh,et al.  Power and Thermal Management in the Intel Core Duo Processor , 2006 .

[10]  J. Mugler,et al.  Proceedings Formatting Team , 2002 .

[11]  Mahmut T. Kandemir,et al.  Energy-oriented compiler optimizations for partitioned memory architectures , 2000, CASES '00.

[12]  Ricardo Bianchini,et al.  Limiting the power consumption of main memory , 2007, ISCA '07.

[13]  Wu-chun Feng,et al.  A Power-Aware Run-Time System for High-Performance Computing , 2005, ACM/IEEE SC 2005 Conference (SC'05).

[14]  Hong Zhu,et al.  A survey of practical algorithms for suffix tree construction in external memory , 2010 .

[15]  Mahmut T. Kandemir,et al.  Automatic data migration for reducing energy consumption in multi-bank memory systems , 2002, DAC '02.

[16]  Hakim Weatherspoon,et al.  Summary of the 3rd ACM SIGOPS workshop on large-scale distributed systems and middleware (LADIS 2009) , 2010, OPSR.

[17]  Frank Bellosa,et al.  Process cruise control: event-driven clock scaling for dynamic power management , 2002, CASES '02.

[18]  David E. Irwin,et al.  Ensemble-level Power Management for Dense Blade Servers , 2006, 33rd International Symposium on Computer Architecture (ISCA'06).

[19]  Xiaodong Li,et al.  Performance directed energy management for main memory and disks , 2004, ASPLOS XI.

[20]  Karsten Schwan,et al.  VirtualPower: coordinated power management in virtualized enterprise systems , 2007, SOSP.

[21]  Hanene Ben Fradj,et al.  System Level Multi-bank Main Memory Configuration for Energy Reduction , 2006, PATMOS.

[22]  Bronis R. de Supinski,et al.  Adagio: making DVS practical for complex HPC applications , 2009, ICS.

[23]  Hyo J. Lee.  Augmenting RAID with an SSD for Energy Relief , 2008 .

[24]  Rong Ge,et al.  High-performance, power-aware distributed computing for scientific applications , 2005, Computer.

[25]  Ricardo Bianchini,et al.  Exploiting redundancy to conserve energy in storage systems , 2006, SIGMETRICS '06/Performance '06.

[26]  Euiseong Seo,et al.  Empirical Analysis on Energy Efficiency of Flash-based SSDs , 2008, HotPower.

[27]  Martin Schulz,et al.  Bounding energy consumption in large-scale MPI programs , 2007, Proceedings of the 2007 ACM/IEEE Conference on Supercomputing (SC '07).

[28]  Akshat Verma,et al.  pMapper: Power and Migration Cost Aware Application Placement in Virtualized Systems , 2008, Middleware.

[29]  Xiao Qin,et al.  An Energy-Efficient Reliability Model for Parallel Disk Systems , 2009, 2009 Sixth International Conference on Information Technology: New Generations.

[30]  Hanene Ben Fradj,et al.  Multi-Bank Main Memory Architecture with Dynamic Voltage Frequency Scaling for System Energy Optimization , 2006, 9th EUROMICRO Conference on Digital System Design (DSD'06).

[31]  David K. Lowenthal,et al.  Using multiple energy gears in MPI programs on a power-scalable cluster , 2005, PPoPP.

[32]  David K. Lowenthal,et al.  Just In Time Dynamic Voltage Scaling: Exploiting Inter-Node Slack to Save Energy in MPI Programs , 2005, ACM/IEEE SC 2005 Conference (SC'05).

[33]  Xi He,et al.  Power-aware scheduling of virtual machines in DVFS-enabled clusters , 2009, 2009 IEEE International Conference on Cluster Computing and Workshops.

[34]  Mahmut T. Kandemir,et al.  Scheduler-based DRAM energy management , 2002, DAC '02.

[35]  Michael C. Huang,et al.  Positional adaptation of processors: application to energy reduction , 2003, ISCA '03.

[36]  Xiaorui Wang,et al.  Cluster-level feedback power control for performance optimization , 2008, 2008 IEEE 14th International Symposium on High Performance Computer Architecture.

[37]  Calvin Lin,et al.  A comprehensive approach to DRAM power management , 2008, 2008 IEEE 14th International Symposium on High Performance Computer Architecture.

[38]  D.K. Lowenthal,et al.  Adaptive, Transparent Frequency and Voltage Scaling of Communication Phases in MPI Programs , 2006, ACM/IEEE SC 2006 Conference (SC'06).

[39]  Mahmut T. Kandemir,et al.  Hardware and Software Techniques for Controlling DRAM Power Modes , 2001, IEEE Trans. Computers.