1. 首都师范大学 机构 信息工程学院,北京,102248
2. 电子系统可靠性技术北京市重点实验室 机构,北京,100048
3. 西安电子科技大学 电子工程学院,陕西,西安,710126
4. 北京成像理论与技术高精尖创新中心,北京,100048
纸质出版:2020
移动端阅览
武磊, 魏子涵, 张伟功, 王晶, 高岚. 一种通用CNN加速器的缓冲区地址调度方法[J]. 微电子学与计算机, 2020, 37(7): 82-86.
WU Lei, WEI Zi-han, ZHANG Wei-gong, et al. A buffer address scheduling method for general CNN accelerator[J]. 2020, 37(7): 82-86.
针对由神经网络参数多计算复杂度高导致的数据访问灵活性不足问题,本文提出了一种通用CNN加速器的缓冲区地址调度方法.通过在地址控制器中灵活调度片上缓存,卷积层均能由一个或两个特定卷积运算单元实现,降低资源开销;通过输入参数可配置不同大小的图像及卷积核,具有一定的通用性.实验结果表明,该地址调度方法能够适用于不同数目及尺寸的卷积、池化和全连接操作,并且计算性能有所提高.
Aiming at the problem of data access conflicts caused by multiple neural network parameters and high computational complexity
this paper proposes a buffer address scheduling method for general CNN accelerator. The on-chip buffer is flexibly scheduled in the address controller
and the convolutional layers can be implemented by one or two specific convolutional operation units to reduce resource consumption; the input parameters can be configured with images and convolution kernels of different sizes
with some universality. The experimental results show that the address scheduling method can be applied to different numbers and sizes of convolution
pooling and full connection operations
and the computing performance is improved.
RAJARAMAN S, CANDEMIR S, KIM I, et al. Visualization and Interpretation of Convolutional Neural Network Predictions in Detecting Pneumonia in Pediatric Chest Radiographs[J]. Applied Sciences, 2018, 8(10):1715. DOI: 1715
ZHOU Y, JIANG J. An FPGA-based accelerator implementation for deep convolutional neural networks[C]// International Conference on Computer Science and Network Technology. Changchun, China, IEEE, 2016: 829-832.
CHEN Y, LUO T.DaDianNao: A machine-learning supercomputer[C]// The 47th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO). Cambridge, United Kingdom, IEEE, 2014: 609-622.
MA Y, CAO Y, VRUDHULA S, et al. Optimizing the convolution operation to accelerate deep neural networks on FPGA[J]. IEEE Transactions on Very Large Scale Integration Systems, 2018, 26(7): 1354-1367. DOI: 1354
CHEN Y H, KRISHNA T, EMER J S, et al. Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks[C]// IEEE International Solid State Circuits Conference.San Francisco, CA, USA, IEEE, 2016: 262-263.
KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep convolutional neural networks[C]// International Conference on Neural Information Processing Systems. Curran Associates Inc.2012: 1097-1105.
ALWANI M, CHEN H, FERDMAN M, et al.Fused-layer CNN accelerators[C]// The 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO). Taipei, Taiwan, IEEE, 2016: 1-12.
ZHANG J, LI J. Improving the performance of Open CL-based FPGA accelerator for convolutional neural network[C]// Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays. Monterey, CA, USA, ACM, 2017: 25-34.
卢冶, 陈瑶, 李涛, 等.面向边缘计算的嵌入式FPGA卷积神经网络构建方法[J].计算机研究与发展, 2018, 55(3):551-562. DOI: 551
余子健, 马德, 严晓浪, 等.基于FPGA的卷积神经网络加速器[J].计算机工程, 2017, 43(1): 109-114. DOI: 109
翟社平, 邱程, 杨媛媛, 等.基于FPGA的卷积神经网络加速器设计与实现[J].微电子学与计算机, 2019, 36(8):83-86. DOI: 83
方荣强, 王晶, 姚治成, 等.多层神经网络算法的计算特征建模方法[J].计算机研究与发展, 2019, 56(6):1170-1181. DOI: 1170
王巍, 周凯利, 王伊昌, 等.卷积神经网络(CNN)算法的FPGA并行结构设计[J].微电子学与计算机, 2019, 36(4):57-62. DOI: 57
0
浏览量
19
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010602201714号