Corpus ID: 30456854

Design and Analysis of a Hardware CNN Accelerator

@inproceedings{Kiningham2017DesignAA,
  title={Design and Analysis of a Hardware CNN Accelerator},
  author={Kevin Kiningham},
  year={2017}
}
  • Kevin Kiningham
  • Published 2017
  • Computer Science
  • In recent years, Convolutional Neural Networks (CNNs) have revolutionized computer vision tasks. However, inference in current CNN designs is extremely computationally intensive. This has lead to an explosion of new accelerator architectures designed to reduce power consumption and latency [20]. In this paper, we design and implement a systolic array based architecture we call ConvAU to efficiently accelerate dense matrix multiplication operations in CNNs. We also train an 8-bit quantized… CONTINUE READING
    6 Citations
    Flexible Modularized Artificial Neural Network Implementation on FPGA
    • Kiruki Cosmas, Kenichi Asami
    • Computer Science
    • 2018 5th International Conference on Soft Computing & Machine Intelligence (ISCMI)
    • 2018
    Performance Implications of Big Data in Scalable Deep Learning: On the Importance of Bandwidth and Caching
    • 1
    PREMA: A Predictive Multi-Task Scheduling Algorithm For Preemptible Neural Processing Units
    • Yujeong Choi, Minsoo Rhu
    • Computer Science
    • 2020 IEEE International Symposium on High Performance Computer Architecture (HPCA)
    • 2020
    • 10
    • PDF
    DCNN for Tactile Sensory Data Classification based on Transfer Learning
    • 3
    • Highly Influenced

    References

    SHOWING 1-10 OF 27 REFERENCES
    YodaNN: An Architecture for Ultralow Power Binary-Weight CNN Acceleration
    • 128
    • PDF
    Scalable and modularized RTL compilation of Convolutional Neural Networks onto FPGA
    • 88
    ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars
    • 673
    • PDF
    Quantized Convolutional Neural Networks for Mobile Devices
    • 558
    • PDF
    DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning
    • 952
    • PDF
    EIE: Efficient Inference Engine on Compressed Deep Neural Network
    • Song Han, Xingyu Liu, +4 authors W. Dally
    • Computer Science
    • 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA)
    • 2016
    • 1,319
    • PDF
    Improving the speed of neural networks on CPUs
    • 567
    • PDF
    Deep Convolutional Neural Network Inference with Floating-point Weights and Fixed-point Activations
    • 52
    • PDF
    Training deep neural networks with low precision multiplications
    • 352
    • PDF
    Fixed Point Quantization of Deep Convolutional Networks
    • 435
    • PDF