Corpus ID: 32290895

Accelerating Deep Neural Networks on Low Power Heterogeneous Architectures

@inproceedings{Loukadakis2018AcceleratingDN,
  title={Accelerating Deep Neural Networks on Low Power Heterogeneous Architectures},
  author={M. Loukadakis and J. Cano and M. O'Boyle},
  year={2018}
}
  • M. Loukadakis, J. Cano, M. O'Boyle
  • Published 2018
  • Computer Science
  • Deep learning applications are able to recognise images and speech with great accuracy, and their use is now everywhere in our daily lives. [...] Key Method More specifically, a serial version of VGG-16 is parallelised for both the CPU and GPU present on the board using OpenMP and OpenCL. We also investigate several optimisation techniques that exploit the specific hardware architecture of the ODROID board and can accelerate the inference further. One of these optimisations uses the CLBlast library…Expand Abstract
    Optimising Convolutional Neural Networks Inference on Low-Powered GPUs
    5
    Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks
    15
    Accelerating Deep Learning Applications in Space
    A Survey on Edge Intelligence
    4
    Comparison of early and late fusion techniques for movie trailer genre labelling
    • J. H. Mervitz, J. P. de Villiers, J. P. Jacobs, M. H. O. Kloppers
    • Computer Science
    • 2020
    Generating Semantic Adversarial Examples through Differentiable Rendering

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 30 REFERENCES
    DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices
    258
    DeepSense: A GPU-based Deep Convolutional Neural Network Framework on Commodity Mobile Devices
    34
    Compression of Deep Neural Networks on the Fly
    21
    Low precision arithmetic for deep learning
    156
    Deep Residual Learning for Image Recognition
    47906