Leaving One Slot Empty: Flit Bubble Flow Control for Torus Cache-Coherent NoCs

作者: Sheng Ma , Zhiying Wang , Zonglin Liu Liu , Natalie Enright Jerger

DOI: 10.1109/TC.2013.2295523

关键词:

摘要: Short and long packets co-exist in cache-coherent NoCs. Existing designs for torus networks do not efficiently handle variable-size packets. For deadlock free operations, a design uses two VCs, which negatively affects the router frequency. Some optimizations use one VC. Yet, they regard all as maximum-length packets, inefficiently utilizing precious buffers. We propose flit bubble flow control (FBFC), maintains flit-size buffer slot to avoid deadlock. FBFC VC, does treat short ones. It achieves both high frequency efficient utilization. performs 92.8 34.2 percent better than LBS CBS synthetic traffic $4 \times 4$ torus. The gains increase larger networks; are 107.2 40.1 an $8 8$ average 13.0 speedup over PARSEC workloads. Our results also show that is more power CBS, with mesh.

参考文章(56)
Brian Patrick Towles, William James Dally, Principles and Practices of Interconnection Networks ,(2004)
Y. Tamir, G.L. Frazier, High-performance multiqueue buffers for VLSI communication switches international symposium on computer architecture. pp. 343- 354 ,(1988) , 10.1109/ISCA.1988.5245
Pablo Abad, Valentin Puente, José Angel Gregorio, Pablo Prieto, Rotary router Proceedings of the 34th annual international symposium on Computer architecture - ISCA '07. ,vol. 35, pp. 116- 125 ,(2007) , 10.1145/1250662.1250678
Minjeong Shin, John Kim, Leveraging torus topology with deadlock recovery for cost-efficient on-chip network international conference on computer design. pp. 25- 30 ,(2011) , 10.1109/ICCD.2011.6081371
William J. Dally, Charles L. Seitz, The Torus Routing Chip Distributed Computing. ,vol. 1, pp. 187- 196 ,(1986) , 10.1007/BF01660031
V. Puente, C. Izu, R. Beivide, J.A. Gregorio, F. Vallejo, J.M. Prellezo, The Adaptive Bubble Router Journal of Parallel and Distributed Computing. ,vol. 61, pp. 1180- 1208 ,(2001) , 10.1006/JPDC.2001.1746
P. Conway, B. Hughes, The AMD Opteron Northbridge Architecture IEEE Micro. ,vol. 27, pp. 10- 21 ,(2007) , 10.1109/MM.2007.43
Natalie Enright Jerger, Li-Shiuan Peh, On-Chip Networks ,(2009)
Satish Damaraju, Varghese George, Sanjeev Jahagirdar, Tanveer Khondker, Robert Milstrey, Sanjib Sarkar, Scott Siers, Israel Stolero, Arun Subbiah, A 22nm IA multi-CPU and GPU System-on-Chip international solid-state circuits conference. pp. 56- 57 ,(2012) , 10.1109/ISSCC.2012.6176876