Abstract
Deep learning is one of the hottest research directions in the field of artificial intelligence. It has achieved results which subvert these of traditional methods. However, the demand for computing ability of hardware platform is also increasing. The academia and industry mainly use heterogeneous GPUs to accelerating computation. ARM is relatively more open than GPUs. The purpose of this paper is to study the performance and related acceleration techniques of ThunderX high-performance many-core ARM chips under large-scale inference tasks. In order to study the computational performance of the target platform objectively, several deep models are adapted for acceleration. Through the selection of computational libraries, adjustment of parallel strategies, application of various performance optimization techniques, we have excavated the computing ability of many-core ARM platforms deeply. The final experimental results show that the performance of single-chip ThunderX is equivalent to that of the i7 7700 K chip, and the overall performance of dual-chip can reach 1.77 times that of the latter. In terms of energy efficiency, the former is inferior to the latter. Stronger cooling system or bad power management may lead to more power consumption. Overall, high-performance ARM chips can be deployed in the cloud to complete large-scale deep learning inference tasks which requiring high throughput.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Szegedy, C., Liu, W., Jia, Y., et al.: Going deeper with convolutions. In: CVPR (2015)
Lee, V.W., Kim, C., Chhugani, J., et al.: Debunking the 100X GPU vs. CPU myth: an evaluation of throughput computing on CPU and GPU. ACM SIGARCH Comput. Arch. News 38(3), 451–460 (2010)
Ni, H.: Ncnn: a high-performance neural network inference framework optimized for the mobile platform (2017). https://github.com/Tencent/ncnn
Rungsuptaweekoon, K., Visoottiviseth, V., Takano, R.: Evaluating the power efficiency of deep learning inference on embedded GPU systems. In: 2nd International Conference on Information Technology (INCIT) 2017, pp. 1–5. IEEE (2017)
Zhu, K., Jiang, J.: DSP based acceleration for long short-term memory model based word prediction application. In: 2017 10th International Conference on Intelligent Computation Technology and Automation (ICICTA), pp. 93–99. IEEE (2017)
Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. arXiv preprint arXiv:1409.2329 (2014)
Jin, R., Dou, Y., Wang, Y., et al.: Confusion graph: detecting confusion communities in large scale image classification. In: Proceedings of the 26th International Joint Conference on Artificial Intelligence, pp. 1980–1986. AAAI Press (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhu, K., Jiang, J. (2018). Research on Parallel Acceleration for Deep Learning Inference Based on Many-Core ARM Platform. In: Li, C., Wu, J. (eds) Advanced Computer Architecture. ACA 2018. Communications in Computer and Information Science, vol 908. Springer, Singapore. https://doi.org/10.1007/978-981-13-2423-9_3
Download citation
DOI: https://doi.org/10.1007/978-981-13-2423-9_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-2422-2
Online ISBN: 978-981-13-2423-9
eBook Packages: Computer ScienceComputer Science (R0)