Power and Performance Characterization and Modeling of GPU-Accelerated Systems
Authors:
- Yuki AbeYAYuki Abe
- Hiroshi SasakiHSHiroshi Sasaki
- Shinpei KatoSKShinpei Kato
- Koji InoueKIKoji Inoue
- Masato EdahiroMEMasato Edahiro
- Martin PeresMPMartin Peres
- 1 May 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15302075,p. 113-122
Abstract
Graphics processing units (GPUs) provide an order-of-magnitude improvement on peak performance and performance-per-watt as compared to traditional multicore CPUs. However, GPU-accelerated systems currently lack a generalized method of power and performance prediction, which prevents system designers from an ultimate goal of dynamic power and performance optimization. This is due to the fact that their power and performance characteristics are not well captured across architectures, and as a result, existing power and performance modeling approaches are only available for a limited range of particular GPUs. In this paper, we present power and performance characterization and modeling of GPU-accelerated systems across multiple generations of architectures. Characterization and modeling both play a vital role in optimization and prediction of GPU-accelerated systems. We quantify the impact of voltage and frequency scaling on each architecture with a particularly intriguing result that a cutting-edge Kepler-based GPU achieves energy saving of 75% by lowering GPU clocks in the best scenario, while Fermi- and Tesla-based GPUs achieve no greater than 40% and 13%, respectively. Considering these characteristics, we provide statistical power and performance modeling of GPU-accelerated systems simplified enough to be applicable for multiple generations of architectures. One of our findings is that even simplified statistical models are able to predict power and performance of cutting-edge GPUs within errors of 20% to 30% for any set of voltage and frequency pair.Keywords
This publication has 16 references indexed in Scilit:
- Power-efficient time-sensitive mapping in heterogeneous systems2012
- GreenGPU: A Holistic Approach to Energy Efficiency in GPU-CPU Heterogeneous Architectures2012
- GPUstore2012
- A performance analysis framework for identifying potential benefits in GPGPU applications2012
- Improving Throughput of Power-Constrained GPUs Using Dynamic Voltage/Frequency and Core Scaling2011
- Performance and Power Analysis of ATI GPU: A Statistical Approach2011
- Motion planning for autonomous driving with a conformal spatiotemporal lattice2011
- A characterization of the Rodinia benchmark suite with comparison to contemporary CMP workloads2010
- Power and Performance Characterization of Computational Kernels on the GPU2010
- Statistical power modeling of GPU kernels using performance counters2010