利用参数稀疏性的卷积神经网络计算优化及其FPGA加速器设计

刘勤让; 刘崇阳

doi:10.11999/JEIT170819

利用参数稀疏性的卷积神经网络计算优化及其FPGA加速器设计

doi: 10.11999/JEIT170819

刘勤让¹,
刘崇阳¹

基金项目:

国家科技重大专项(2016ZX01012101)，国家自然科学基金(61572520, 61521003)

计量
- 文章访问数: 2445
- HTML全文浏览量: 416
- PDF下载量: 451
- 被引次数: 0
出版历程
- 收稿日期: 2017-08-21
- 修回日期: 2018-01-05
- 刊出日期: 2018-06-19

Calculation Optimization for Convolutional Neural Networks and FPGA-based Accelerator Design Using the Parameters Sparsity

LIU Qinrang¹,
LIU Chongyang¹

Funds:

The National Science and Technology Major Project of the Ministry of Science and Technology of China (2016ZX01012101), The National Natural Science Foundation of China (61572520, 61521003)

摘要

摘要: 针对卷积神经网络(CNN)在嵌入式端的应用受实时性限制的问题，以及CNN卷积计算中存在较大程度的稀疏性的特性，该文提出一种基于FPGA的CNN加速器实现方法来提高计算速度。首先，挖掘出CNN卷积计算的稀疏性特点；其次，为了用好参数稀疏性，把CNN卷积计算转换为矩阵相乘；最后，提出基于FPGA的并行矩阵乘法器的实现方案。在Virtex-7 VC707 FPGA上的仿真结果表明，相比于传统的CNN加速器，该设计缩短了19%的计算时间。通过稀疏性来简化CNN计算过程的方式，不仅能在FPGA实现，也能迁移到其他嵌入式端。
- 卷积神经网络 /
- 稀疏性 /
- 计算优化 /
- 矩阵乘法器 /
- FPGA
Abstract: Concerning the problem of real-time restriction on the application of Convolution Neural Network (CNN) in embedded field, and the large degree of sparsity in CNN convolution calculations, this paper proposes an implement method of CNN accelerator based on FPGA to improve computation speed. Firstly, the sparseness characteristics of CNN convolution calculation are seeked out. Secondly, in order to use the parameters sparseness, CNN convolution calculations are converted to matrix multiplication. Finally, the implementation method of parallel matrix multiplier based on FPGA is proposed. Simulation results on the Virtex-7 VC707 FPGA show that the design shortens the calculation time by 19% compared to the traditional CNN accelerator. The method of simplifying the CNN calculation process by sparseness not only can be implemented on FPGA, but also can migrate to other embedded ends.
- Convolution Neural Network (CNN) /
- Sparseness /
- Computational optimization /
- Matrix multiplier /
- FPGA

HTML全文

参考文献(24)

曾毅, 刘成林, 谭铁牛. 类脑智能研究的回顾与展望[J]. 计算机学报, 2016, 39(1): 212-222. doi: 10.11897/SP.J.1016.2016. 00212.

ZENG Yi, LIU Chenglin, and TAN Tieniu. Retrospect and outlook of brain-inspired intelligence research[J]. Chinese Journal of Computers, 2016, 39(1): 212-222. doi: 10.11897/ SP.J.1016.2016.00212.

常亮, 邓小明, 周明全, 等. 图像理解中的卷积神经网络[J]. 自动化学报, 2016, 42(9): 1300-1312. doi: 10.16383/j.aas. 2016.c150800.

CHANG Liang, DENG Xiaoming, ZHOU Mingquan, et al. Convolutional neural networks in image understanding[J]. Acta Automatica Sinica, 2016, 42(9): 1300-1312. doi: 10.16383/j.aas.2016.c150800.

JI S, XU W, YANG M, et al. 3D convolutional neural networks for human action recognition[J]. IEEE Transactions on Pattern Analysis Machine Intelligence, 2012, 35(1): 221-231. doi: 10.1109/TPAMI.2012.59.

CHAKRADHAR S, SANKARADAS M, JAKKULA V, et al. A dynamically configurable coprocessor for convolutional neural networks[J]. ACM Sigarch Computer Architecture News, 2010, 38(3): 247-257. doi: 10.1145/1816038.1815993.

KRIZHEVSKY A, SUTSKEVER I, and HINTON G E. ImageNet classification with deep convolutional neural networks[C]. International Conference on Neural Information Processing Systems, Lake Tahoe, Nevada, 2012: 1097-1105. doi: 10.1145/3065386.

SUDA N, CHANDRA V, DASIKA G, et al. Throughput- optimized openCL-based FPGA accelerator for large-scale convolutional neural networks[C]. ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, Monterey, California, USA, 2016: 16-25. doi: 10.1145/2847263.2847276.

QIU J, WANG J, YAO S, et al. Going deeper with embedded FPGA platform for convolutional neural network[C]. ACM/ SIGDA International Symposium on Field-Programmable Gate Arrays, Monterey, California, USA, 2016: 26-35. doi: 10.1145 /2847263.2847265.

ANWAR S, HWANG K, and SUNG W. Fixed point optimization of deep convolutional neural networks for object recognition[C]. IEEE International Conference on Acoustics, Speech and Signal Processing, Brisbane, QLD, Australia, 2015: 1131-1135. doi: 10.1109/ICASSP.2015.7178146.

ZHANG C, LI P, SUN G, et al. Optimizing FPGA-based accelerator design for deep convolutional neural networks[C]. ACM/SIGDA International Symposium on Field- Programmable Gate Arrays, Monterey, California, USA, 2015: 161-170. doi: 10.1145/2684746.2689060.

SHEN Y, FERDMAN M, and MILDER P. Maximizing CNN accelerator effciency through resource partitioning[C]. Annual International Symposium on Computer Architecture, Toronto, ON, Canada, 2017: 535-547. doi: 10.1145/3140659. 3080221.

DU Z, FASTHUBER R, CHEN T, et al. ShiDianNao: Shifting vision processing closer to the sensor[C]. Annual International Symposium on Computer Architecture, Portland, Oregon, 2015: 92-104. doi: 10.1145/2749469. 2750389.

CHEN T, DU Z, SUN N, et al. DianNao: A small-footprint high-throughput accelerator for ubiquitous machine- learning[C]. International Conference on Architectural Support for Programming Languages and Operating Systems, Salt Lake City, Utah, USA, 2014: 269-284. doi: 10.1145/ 2541940.2541967.

HADJIS S, ABUZAID F, ZHANG C, et al. Caffe con troll: Shallow ideas to speed up deep learning[C]. Proceedings of the Fourth Workshop on Data analytics, Melbourne, VIC, Australia, 2015: 1-4. doi: 10.1145/2799562.2799641.

YAVITS L, MORAD A, and GINOSAR R. Sparse matrix multiplication on an associative processor[J]. IEEE Transactions on Parallel Distributed Systems, 2015, 26(11): 3175-3183. doi: 10.1109/TPDS.2014.2370055.

CHELLAPILLA K, PURI S, and SIMARD P. High performance convolutional neural networks for document processing[C]. Tenth International Workshop on Frontiers in Handwriting Recognition, La Baule, France, 2006: 1-6.

CHETLUR S, WOOLLEY C, VANDERMERSCH P, et al. CuDNN: Efficient primitives for deep learning[C]. International Conference on Neural Information Processing Systems, Montreal, Canada, 2014: 1-9.

田翔, 周凡, 陈耀武, 等. 基于FPGA的实时双精度浮点矩阵乘法器设计[J]. 浙江大学学报(工学版), 2008, 42(9): 1611-1615. doi: 10.3785/j.issn.1008-973X.2008.09.027.

TIAN Xiang, ZHOU Fan, CHEN Yaowu, et al. Design of field programmable gate array based real-time double-precision floating-point matrix multiplier[J]. Journal of Zhejiang University (Engineering Science), 2008, 42(9): 1611-1615. doi: 10.3785/j.issn.1008-973X.2008.09.027.

JANG J, CHOI S B, and PRASANNA V K. Energy- and time-efficient matrix multiplication on FPGAs[J]. IEEE Transactions on Very Large Scale Integration Systems, 2005, 13(11): 1305-1319. doi: 10.1109/TVLSI.2005.859562.

KUMAR V B Y, JOSHI S, PATKAR S B, et al. FPGA based high performance double-precision matrix multiplication[J]. International Journal of Parallel Programming, 2010, 38(3/4): 322-338. doi: 10.1109/VLSI.Design.2009.13.

DONAHUE J, JIA Y, VINYALS O, et al. DeCAF: A deep convolutional activation feature for generic visual recognition[C]. International Conference on Machine Learning, Beijing, China, 2014: 647-655.

PETE Warden. Why GEMM is at the heart of deep learning[OL]. https://petewarden.com/2015/04/20/ why-gemm-is-at-the-heart-of-deep-learning/.

施引文献

资源附件(0)

访问统计