© The Institution of Engineering and Technology
The state-of-the-art convolutional neural networks (CNNs) have been widely applied to many deep neural networks models. As the model becomes more accurate, both the number of computation and the data accesses are significantly increased. The proposed design uses the row stationary with network-on-chip and the fast convolution algorithm in process elements to reduce the number of computation and data accesses simultaneously. The experimental evaluation which using the CNN layers of VGG-16 with a batch size of three shows that the proposed design is more energy-efficient than the state-of-the-art work. The proposed design improves the total GOPs of the algorithm by 1.497 times and reduces the on-chip memory and off-chip memory accesses by 1.07 and 1.46 times than prior work, respectively.
References
-
-
1)
-
3. Chen, Y.-H., Yang, T.-J., Emer, J., et al: ‘Eyeriss v2: a flexible accelerator for emerging deep neural networks on Mobile devices’, IEEE J. Emerg. Sel. Top. Circuits Syst., 2019, 9, (2), pp. 292–308, (doi: 10.1109/JETCAS.2019.2910232).
-
2)
-
1. Chen, Y.-H., Emer, J., Sze, V.: ‘Eyeriss: a spatial architecture for energy-efficient dataflow for convolutional neural networks’. Proc. 43rd Annual Int. Symp. Computer Architecture (ISCA), Seoul, South Korea, June 2016, pp. 367–379, .
-
3)
-
6. Chen, Y.H., Krishna, T., Emer, J.S., et al: ‘Eyeriss: an energy-efficient reconfigurable accelerator for deep convolutional neural networks’, IEEE J. Solid-State Circuits, 2017, 52, (1), pp. 127–138, (doi: 10.1109/JSSC.2016.2616357).
-
4)
-
2. Verhelst, M., Moons, B.: ‘Embedded deep neural network processing: algorithmic and processor techniques bring deep learning to IoT and edge devices’, IEEE Solid-State Circuits Mag., 2017, 9, (4), pp. 55–65, (doi: 10.1109/MSSC.2017.2745818).
-
5)
-
4. Szegedy, C., Liu, W., Jia, Y., et al: ‘Going deeper with convolutions’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, June 2015, pp. 1–9, .
-
6)
-
5. Long, J., Shelhamer, E., Darrell, T.: ‘Fully convolutional networks for semantic segmentation’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, June 2015, pp. 3431–3440, .
http://iet.metastore.ingenta.com/content/journals/10.1049/el.2019.4188
Related content
content/journals/10.1049/el.2019.4188
pub_keyword,iet_inspecKeyword,pub_concept
6
6