论文信息 - Bayesian Optimization of HPC Systems for Energy Efficiency

Bayesian Optimization of HPC Systems for Energy Efficiency

Energy efficiency is a crucial factor in developing large supercomputers and cost-effective datacenters. However, tuning a system for energy efficiency is difficult because the power and performance are conflicting demands. We applied Bayesian optimization (BO) to tune a graphics processing unit (GPU) cluster system for the benchmark used in the Green500 list, a popular energy-efficiency ranking of supercomputers. The resulting benchmark score enabled our system, named “kukai”, to earn second place in the Green500 list in June 2017, showing that BO is a useful tool. By determining the search space with minimal knowledge and preliminary experiments beforehand, BO could automatically find a sufficiently good configuration. Thus, BO could eliminate laborious manual tuning work and reduce the occupancy time of the system for benchmarking. Because BO is a general-purpose method, it may also be useful for tuning any practical applications in addition to Green500 benchmarks.

[1] Shoaib Kamil,et al. OpenTuner: An extensible framework for program autotuning , 2014, 2014 23rd International Conference on Parallel Architecture and Compilation (PACT).

[2] M. Stein. Large sample properties of simulations using latin hypercube sampling , 1987 .

[3] Valentin Dalibard,et al. BOAT: Building Auto-Tuners with Structured Bayesian Optimization , 2017, WWW.

[4] Harold J. Kushner,et al. A New Method of Locating the Maximum Point of an Arbitrary Multipeak Curve in the Presence of Noise , 1964 .

[5] Yuan Yu,et al. TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[6] Jasper Snoek,et al. Practical Bayesian Optimization of Machine Learning Algorithms , 2012, NIPS.

[7] Jack J. Dongarra,et al. The LINPACK Benchmark: past, present and future , 2003, Concurr. Comput. Pract. Exp..

[8] Rainer Storn,et al. Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[9] Vianney Perchet,et al. Gaussian Process Optimization with Mutual Information , 2013, ICML.

[10] Ryan P. Adams,et al. Slice sampling covariance hyperparameters of latent Gaussian models , 2010, NIPS.

[11] Ruben Martinez-Cantin,et al. BayesOpt: a Bayesian optimization library for nonlinear optimization, experimental design and bandits , 2014, J. Mach. Learn. Res..