16954

Programming

Mohsen Imani, Daniel Peroni, Yeseong Kim, Abbas Rahimi, Tajana Rosing
View View   Download Download (PDF)   
Robert V. Lim, Boyana Norris, Allen D. Malony
View View   Download Download (PDF)   
Joao Paulo Tarasconi Ruschel
Anshuman Verma, Ahmed E. Helal, Konstantinos Krommydas, Wu-Chun Feng
View View   Download Download (PDF)   
Rui Fan, Ke Xu, Jichang Zhao
Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, Jeff Dean
View View   Download Download (PDF)   
Dzmitry Razmyslovich
View View   Download Download (PDF)   
Gaetan Hadjeres, Francois Pachet

Graphics Processing Units (GPUs) support dynamic voltage and frequency scaling (DVFS) in order to balance computational performance and energy consumption. However, there still lacks simple and accurate performance estimation of a given GPU kernel under different frequency settings on real hardware, which is important to decide best frequency configuration for energy saving. This paper reveals a fine-grained model to estimate the execution time of GPU kernels with both core and memory frequency scaling. Over a 2.5x range of both core and memory frequencies among 12 GPU kernels, our model achieves accurate results (within 3.5%) on real hardware. Compared with the cycle-level simulators, our model only needs some simple micro-benchmark to extract a set of hardware parameters and performance counters of the kernels to produce this high accuracy.

VN:F [1.9.22_1171]
Rating: 4.2/5 (5 votes cast)
Mohamed Essadki, Jonathan Jung, Adam Larat, Milan Pelletier, Vincent Perrier
View View   Download Download (PDF)   
Garrett B. Goh, Nathan O. Hodas, Abhinav Vishnu
View View   Download Download (PDF)   
Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senellart, Alexander M. Rush
Page 5 of 726« First...34567...102030...Last »

* * *

* * *

HGPU group © 2010-2017 hgpu.org

All rights belong to the respective authors

Contact us: