Pitstop: Enabling a Virtual Network Free Network-on-Chip

被引:21
作者
Farrokhbakht, Hossein [1 ]
Kao, Henry [1 ]
Hasan, Kamran [1 ]
Gratz, Paul, V [2 ]
Krishna, Tushar [3 ]
San Miguel, Joshua [4 ]
Jerger, Natalie Enright [1 ]
机构
[1] Univ Toronto, Toronto, ON, Canada
[2] Texas A&M, College Stn, TX USA
[3] Georgia Inst Technol, Atlanta, GA 30332 USA
[4] Univ Wisconsin, Madison, WI USA
来源
2021 27TH IEEE INTERNATIONAL SYMPOSIUM ON HIGH-PERFORMANCE COMPUTER ARCHITECTURE (HPCA 2021) | 2021年
基金
加拿大自然科学与工程研究理事会;
关键词
DEADLOCK; NOC; EFFICIENT; COMPUTER;
D O I
10.1109/HPCA51647.2021.00063
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Maintaining correctness is of paramount importance in the design of a computer system. Within a multiprocessor interconnection network, correctness is guaranteed by having deadlock-free communication at both the protocol and network levels. Modern network-on-chip (NoC) designs use multiple virtual networks to maintain protocol-level deadlock freedom, at the expense of high power and area overheads. Other techniques involve complex detection and recovery mechanisms, or use misrouting which incurs additional packet latency. Considering that the probability of deadlocks occurring is low, the additional resources needed to avoid/resolve deadlocks should also be low. To this end, we propose Pitstop, a low-cost technique that guarantees correctness by resolving both protocol and network-level deadlocks without the use of virtual networks, complex hardware, or misrouting. Pitstop transfers blocked packets to the network interface (NI) creating a bubble (empty buffer slot) which breaks deadlock. The blocked packet can make forward progress through NI to NI traversals using low complexity bypassing mechanisms. This scheme performs better due to higher utilization of virtual channels and works on arbitrary irregular topologies without any virtual networks. Compared to state-of-the-art solutions, Pitstop can improve performance up to 11% and reduce power and area up to 41% and 40%.
引用
收藏
页码:682 / 695
页数:14
相关论文
共 66 条
[1]   GARNET: A Detailed On-Chip Network Model inside a Full-System Simulator [J].
Agarwal, Niket ;
Krishna, Tushar ;
Peh, Li-Shiuan ;
Jha, Niraj K. .
ISPASS 2009: IEEE INTERNATIONAL SYMPOSIUM ON PERFORMANCE ANALYSIS OF SYSTEMS AND SOFTWARE, 2009, :33-42
[2]  
Alazemi F., 2018, 2018 IEEE INT S HIGH
[3]  
ANJAN KV, 1995, ACM COMP AR, P201, DOI 10.1109/ISCA.1995.524561
[4]  
[Anonymous], 2017, ON CHIP NETWORKS
[5]  
[Anonymous], 2002, Interconnection Networks: An Engineering Approach
[6]  
Balkind J., 2016, OPENPITON OPEN SOURC
[7]  
Besta M, 2018, ACM SIGPLAN NOTICES, V53, P43, DOI [10.1145/3296957.3177158, 10.1145/3173162.3177158]
[8]   The PARSEC Benchmark Suite: Characterization and Architectural Implications [J].
Bienia, Christian ;
Kumar, Sanjeev ;
Singh, Jaswinder Pal ;
Li, Kai .
PACT'08: PROCEEDINGS OF THE SEVENTEENTH INTERNATIONAL CONFERENCE ON PARALLEL ARCHITECTURES AND COMPILATION TECHNIQUES, 2008, :72-81
[9]  
Binkert Nathan, 2011, Computer Architecture News, V39, P1, DOI 10.1145/2024716.2024718
[10]  
Chen C.-H., 2016, THESIS MIT THESIS MIT