Manila: Using a densely populated PMC-space for power modelling within large-scale systems

Abstract In this paper, we propose a new power modelling method, called Manila, that can largely reduce the effort of PMC-based power modelling using multi-dimensional k-nearest neighbour searching, without the use of model tuning and domain-specific knowledge. This method helps improve the accuracy of PMC-based power modelling and widen its scope of use. Specifically, Manila uses a densely populated PMC-space, generated from a large variety of computing workloads, which is essential for our improvement. This is in contrast to current PMC-based power models, that have a sparse PMC-space, due to using a predefined benchmark suite. A parameterised micro-benchmark is used to bootstrap the PMC-space, which is independent from any applications and can generate the generic computing workloads of many applications. Our method is more widely extendable and applicable than the existing methods. Manila can efficiently search the dense PMC-space for power estimates using a nearest neighbour search algorithm. Experimental results demonstrate that Manila is more accurate in power measurements for a wide range of parallel benchmarks, with an average mean absolute error of 2.8%.

[1]  Efraim Rotem,et al.  Power-Management Architecture of the Intel Microarchitecture Code-Named Sandy Bridge , 2012, IEEE Micro.

[2]  Lasse Natvig,et al.  Temperature effects on on-chip energy measurements , 2013, 2013 International Green Computing Conference Proceedings.

[3]  Wolf-Dietrich Weber,et al.  Power provisioning for a warehouse-sized computer , 2007, ISCA '07.

[4]  Sally A. McKee,et al.  Portable, scalable, per-core power estimation for intelligent resource management , 2010, International Conference on Green Computing.

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

[6]  Margaret Martonosi,et al.  Wattch: a framework for architectural-level power analysis and optimizations , 2000, Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat. No.RS00201).

[7]  Luiz André Barroso,et al.  The Case for Energy-Proportional Computing , 2007, Computer.

[8]  Margaret Martonosi,et al.  Power-Performance Modeling and Tradeoff Analysis for a High End Microprocessor , 2000, PACS.

[9]  David E. Culler,et al.  The ganglia distributed monitoring system: design, implementation, and experience , 2004, Parallel Comput..

[10]  David M. Eyers,et al.  PMC-Based Power Modelling with Workload Classification on Multicore Systems , 2014, 2014 43rd International Conference on Parallel Processing Workshops.

[11]  Stéphan Jourdan,et al.  Haswell: The Fourth-Generation Intel Core Processor , 2014, IEEE Micro.

[12]  David Eyers,et al.  Myths in power estimation with Performance Monitoring Counters , 2014, Sustain. Comput. Informatics Syst..

[13]  Franck Cappello,et al.  Distributed Monitoring and Management of Exascale Systems in the Argo Project , 2015, DAIS.

[14]  Robert J. Fowler,et al.  Application Runtime Variability and Power Optimization for Exascale Computers , 2015, ROSS@HPDC.

[15]  Wolfgang E. Nagel,et al.  Power measurement techniques on standard compute nodes: A quantitative comparison , 2013, 2013 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS).

[16]  Torbjörn Ekman,et al.  Sound and extensible renaming for java , 2008, OOPSLA.

[17]  Naehyuck Chang,et al.  Accurate modeling and calculation of delay and energy overheads of dynamic voltage scaling in modern high-performance microprocessors , 2010, 2010 ACM/IEEE International Symposium on Low-Power Electronics and Design (ISLPED).

[18]  David H. Bailey,et al.  The Nas Parallel Benchmarks , 1991, Int. J. High Perform. Comput. Appl..

[19]  Helmut Hlavacs,et al.  Methodology of measurement for energy consumption of applications , 2010, 2010 11th IEEE/ACM International Conference on Grid Computing.

[20]  Laurent Lefèvre,et al.  DNA-Inspired Scheme for Building the Energy Profile of HPC Systems , 2012, E2DC.

[21]  Martin Schulz,et al.  Beyond DVFS: A First Look at Performance under a Hardware-Enforced Power Bound , 2012, 2012 IEEE 26th International Parallel and Distributed Processing Symposium Workshops & PhD Forum.

[22]  Yale N. Patt,et al.  Feedback-driven threading: power-efficient and high-performance execution of multi-threaded workloads on CMPs , 2008, ASPLOS.

[23]  Xi Chen,et al.  Performance and power modeling in a multi-programmed multi-core environment , 2010, Design Automation Conference.

[24]  Xiao Qin,et al.  Energy-Efficient Scheduling for Parallel Applications Running on Heterogeneous Clusters , 2007, 2007 International Conference on Parallel Processing (ICPP 2007).

[25]  Rajesh Gupta,et al.  Evaluating the effectiveness of model-based power characterization , 2011 .

[26]  Jean-Marc Pierson,et al.  Characterizing Applications from Power Consumption: A Case Study for HPC Benchmarks , 2011, ICT-GLOW.

[27]  Minyi Guo,et al.  Scalable Multicore k-NN Search via Subspace Clustering for Filtering , 2015, IEEE Transactions on Parallel and Distributed Systems.

[28]  Margaret Martonosi,et al.  Run-time power estimation in high performance microprocessors , 2001, ISLPED '01.

[29]  Kresimir Mihic,et al.  A system for online power prediction in virtualized environments using gaussian mixture models , 2010, Design Automation Conference.

[30]  Weisong Shi,et al.  SPAN: A software power analyzer for multicore computer systems , 2011, Sustain. Comput. Informatics Syst..

[31]  J. Węglarz,et al.  Runtime power usage estimation of HPC servers for various classes of real-life applications , 2014, Future Gener. Comput. Syst..

[32]  Franck Cappello,et al.  Grid'5000: A Large Scale And Highly Reconfigurable Experimental Grid Testbed , 2006, Int. J. High Perform. Comput. Appl..

[33]  Lizy Kurian John,et al.  Complete System Power Estimation: A Trickle-Down Approach Based on Performance Events , 2007, 2007 IEEE International Symposium on Performance Analysis of Systems & Software.

[34]  Minyi Guo,et al.  Data filtering for scalable high-dimensional k-NN search on multicore systems , 2014, HPDC '14.

[35]  Sally A. McKee,et al.  Real time power estimation and thread scheduling via performance counters , 2009, CARN.

[36]  Margaret Martonosi,et al.  Power prediction for Intel XScale/spl reg/ processors using performance monitoring unit events , 2005, ISLPED '05. Proceedings of the 2005 International Symposium on Low Power Electronics and Design, 2005..

[37]  Luiz André Barroso,et al.  The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines , 2009, The Datacenter as a Computer: An Introduction to the Design of Warehouse-Scale Machines.

[38]  Yuichi Inadomi,et al.  Analyzing and mitigating the impact of manufacturing variability in power-constrained supercomputing , 2015, SC15: International Conference for High Performance Computing, Networking, Storage and Analysis.

[39]  Laurent Lefèvre,et al.  A Unified Monitoring Framework for Energy Consumption and Network Traffic , 2015, EAI Endorsed Trans. Energy Web.

[40]  Eduard Ayguadé,et al.  Decomposable and responsive power models for multicore processors using performance counters , 2010, ICS '10.

[41]  Yefu Wang,et al.  Electricity Bill Capping for Cloud-Scale Data Centers that Impact the Power Markets , 2012, 2012 41st International Conference on Parallel Processing.