25277

HALF: Holistic Auto Machine Learning for FPGAs

Jonas Ney, Dominik Loroch, Vladimir Rybalkin, Nico Weber, Jens Krüger, Norbert Wehn
University of Kaiserslautern, Kaiserslautern, Germany
arXiv:2106.14771 [cs.AR], (28 Jun 2021)

@misc{ney2021half,

   title={HALF: Holistic Auto Machine Learning for FPGAs},

   author={Jonas Ney and Dominik Loroch and Vladimir Rybalkin and Nico Weber and Jens Krüger and Norbert Wehn},

   year={2021},

   eprint={2106.14771},

   archivePrefix={arXiv},

   primaryClass={cs.AR}

}

Download Download (PDF)   View View   Source Source   

908

views

Deep Neural Networks (DNNs) are capable of solving complex problems in domains related to embedded systems, such as image and natural language processing. To efficiently implement DNNs on a specific FPGA platform for a given cost criterion, e.g. energy efficiency, an enormous amount of design parameters has to be considered from the topology down to the final hardware implementation. Interdependencies between the different design layers have to be taken into account and explored efficiently, making it hardly possible to find optimized solutions manually. An automatic, holistic design approach can improve the quality of DNN implementations on FPGA significantly. To this end, we present a cross-layer design space exploration methodology. It comprises optimizations starting from a hardware-aware topology search for DNNs down to the final optimized implementation for a given FPGA platform. The methodology is implemented in our Holistic Auto machine Learning for FPGAs (HALF) framework, which combines an evolutionary search algorithm, various optimization steps and a library of parametrizable hardware DNN modules. HALF automates both the exploration process and the implementation of optimized solutions on a target FPGA platform for various applications. We demonstrate the performance of HALF on a medical use case for arrhythmia detection for three different design goals, i.e. low-energy, low-power and high-throughput respectively. Our FPGA implementation outperforms a TensorRT optimized model on an Nvidia Jetson platform in both throughput and energy consumption.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2024 hgpu.org

All rights belong to the respective authors

Contact us: