利用三維晶片網路實現多層融合深度神經網路節能加速

Energy-Efficient Fusion-Based Deep Neural Networks Acceleration with 3-D Network-on-Chip

葛佩玉(Pei-Yu Ge)

指導教授 ： 黃威

國立交通大學/電機學院/電子工程系所/碩士(2018年)

摘要

無資料

關鍵字

卷積神經網路 ； 三維記憶體 ； 深度學習 ； 三維晶片網路 ； 融合多層 ； 動態電壓/頻率調整 ； 預取

並列摘要

無資料

並列關鍵字

Convolutional Neural Network ； 3D Memory ； Deep Learning ； 3D Network-on-Chip ； Fused-Layer ； Dynamic Voltage/Frequency Scaling ； Prefetch

參考文獻

[1] Y. Chen, T. Krishna, J. S. Emer, and V. Sze, ‘‘Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks’’, Proc. IEEE Journal of Solid-State Circuits, Vol. 52, No. 1, January 2017, p127-p138.

[2] M. Gao, J. Pu, X. Yang, M. Horowitz, C. Kozyrakis, ‘‘TETRIS: Scalable and Efficient Neural Network Acceleration with 3D Memory,’’ Proc. ASPLOS, April 08 - 12, 2017, Xi’an, China.

[3] Yu-Hsin Chen, Joel Emer, Vivienne Sze, ‘‘Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks’’, Proc. ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), 2016, p367-p379.

[4] Y.-H. Chen, T. Krishna, J. Emer, and V. Sze, “Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks,” Proc. IEEE Int. Solid-State Circuits Conf. Dig. Tech. Papers (ISSCC), Jan./Feb. 2016, pp. 262–263.

[5] L. Du, Y. Du, Y. Li, J. Su, Y.C. Kuan, C. C. Liu, and M. C. Frank Chang, “Neurostream: Scalable and Energy Efficient Deep Learning with Smart Memory Cubes,” Proc. IEEE Transaction on parallel and Distributed Systems, VOL. 29, NO. 2, February 2018.