Paper Info
Title
Enabling energy-efficient DNN training on hybrid GPU-FPGA accelerators
Abstract
ABSTRACTDNN training consumes orders of magnitude more energy than inference and requires innovative use of accelerators to improve energy-efficiency. However, despite having complementary features, GPUs and FPGAs have been mostly used independently for the entire training process, thus neglecting the opportunity in assigning individual but distinct operations to the most suitable hardware. In this paper, we take the initiative to explore new opportunities and viable solutions in enabling energy-efficient DNN training on hybrid accelerators. To overcome fundamental challenges including avoiding training throughput loss, enabling fast design space exploration, and efficient scheduling, we propose a comprehensive framework, Hype-training, that utilizes a combination of offline characterization, performance modeling, and online scheduling of individual operations. Experimental tests using NVIDIA V100 GPUs and Intel Stratix 10 FPGAs show that, Hype-training is able to exploit a mixture of GPUs and FPGAs at a fine granularity to achieve significant energy reduction, by 44.3% on average and up to 59.7%, without any loss in training throughput. Hype-training can also enforce power caps more effectively than state-of-the-art power management mechanisms on GPUs.
Year
DOI
Venue
2021
10.1145/3447818.3460371
ICS
DocType
Citations 
PageRank 
Conference
1
0.35
References 
Authors
0
7
Name
Order
Citations
PageRank
Xin He110.35
Jiawen Liu2173.24
Zhen Xie321.04
Hao Chen4145.59
Guoyang Chen5132.83
Weifeng Zhang6239.87
Li, Dong776448.56