Enabling Energy-Efficient DNN Training on Hybrid GPU-FPGA Accelerators

Xin He, Jiawen Liu, Zhen Xie, Hao Chen, Guoyang Chen, Weifeng Zhang, Dong Li
Hunan University Changsha, China
International Conference on Supercomputing (ICS ’21), 2021


   title={Enabling Energy-Efficient DNN Training on Hybrid GPU-FPGA Accelerators},

   author={He, Xin and Liu, Jiawen and Xie, Zhen and Chen, Hao and Chen, Guoyang and Zhang, Weifeng and Li, Dong},



Download Download (PDF)   View View   Source Source   



DNN 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.
Rating: 5.0/5. From 1 vote.
Please wait...

* * *

* * *

* * *

HGPU group © 2010-2022 hgpu.org

All rights belong to the respective authors

Contact us: