Redirigiendo al acceso original de articulo en 16 segundos...
Inicio  /  Computation  /  Vol: 8 Par: 2 (2020)  /  Artículo
ARTÍCULO
TITULO

Accurate Energy and Performance Prediction for Frequency-Scaled GPU Kernels

Kaijie Fan    
Biagio Cosenza and Ben Juurlink    

Resumen

Energy optimization is an increasingly important aspect of today?s high-performance computing applications. In particular, dynamic voltage and frequency scaling (DVFS) has become a widely adopted solution to balance performance and energy consumption, and hardware vendors provide management libraries that allow the programmer to change both memory and core frequencies manually to minimize energy consumption while maximizing performance. This article focuses on modeling the energy consumption and speedup of GPU applications while using different frequency configurations. The task is not straightforward, because of the large set of possible and uniformly distributed configurations and because of the multi-objective nature of the problem, which minimizes energy consumption and maximizes performance. This article proposes a machine learning-based method to predict the best core and memory frequency configurations on GPUs for an input OpenCL kernel. The method is based on two models for speedup and normalized energy predictions over the default frequency configuration. Those are later combined into a multi-objective approach that predicts a Pareto-set of frequency configurations. Results show that our approach is very accurate at predicting extema and the Pareto set, and finds frequency configurations that dominate the default configuration in either energy or performance.

Palabras claves

 Artículos similares

       
 
Qiankun Wang, Ke Zhu, Peiwen Guo, Jiaji Zhang and Zhihua Xiong    
Faced with the challenges of global climate change, zero-carbon buildings (ZCB) serve as a crucial means to achieve carbon peak and carbon neutrality goals, particularly in the development of tropical island regions. This study aims to establish a ZCB te... ver más
Revista: Applied Sciences

 
Yanqi Wang, Xinyan Qin, Wenxing Jia, Jin Lei, Dexin Wang, Tianming Feng, Yujie Zeng and Jie Song    
In order to improve the flight efficiency of a flying?walking power transmission line inspection robot (FPTLIR) during flight missions, an accurate energy consumption model is constructed, and a multiobjective optimization approach using the improved NSG... ver más
Revista: Applied Sciences

 
Bicheng Zhou, Anatoly V. Brouchkov and Jiabo Hu    
Frost heaving in soils is a primary cause of engineering failures in cold regions. Although extensive experimental and numerical research has focused on the deformation caused by frost heaving, there is a notable lack of numerical investigations into the... ver más
Revista: Water

 
Daicheng Peng, Fei Cheng, Hao Xu and Yuquan Zong    
Precise surveys are indispensable in coastal engineering projects. The extensive presence of sand in the coastal area leads to significant attenuation of seismic waves within unsaturated loose sediments. As a result, it becomes challenging for seismic wa... ver más

 
Giovanni Briguglio and Vincenzo Crupi    
The increasingly stringent requirements?in terms of limiting pollutants and the constant need to make maritime transport safer?generated the necessity to foresee different solutions that are original. According to the European Maritime Safety Agency, the... ver más