Supporting Distributed Shared Memory on Multi-core Network-on-Chips Using a Dual Microcoded Controller

被引:17
作者
Chen, Xiaowen [1 ,2 ]
Lu, Zhonghai [2 ]
Jantsch, Axel [2 ]
Chen, Shuming [1 ]
机构
[1] Natl Univ Def Technol, Changsha 410073, Hunan, Peoples R China
[2] KTH Royal Inst Technol, S-16440 Stockholm, Sweden
来源
2010 DESIGN, AUTOMATION & TEST IN EUROPE (DATE 2010) | 2010年
基金
中国国家自然科学基金;
关键词
D O I
10.1109/DATE.2010.5457240
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Supporting Distributed Shared Memory (DSM) is essential for multi-core Network-on-Chips for the sake of reusing huge amount of legacy code and easy programmability. We propose a microcoded controller as a hardware module in each node to connect the core, the local memory and the network. The controller is programmable where the DSM functions such as virtual-to-physical address translation, memory access and synchronization etc. are realized using microcode. To enable concurrent processing of memory requests from the local and remote cores, our controller features two mini-processors, one dealing with requests from the local core and the other from remote cores. Synthesis results suggest that the controller consumes 51k gates for the logic and can run up to 455 MHz in 130 nm technology. To evaluate its performance, we use synthetic and application workloads. Results show that, when the system size is scaled up, the delay overhead incurred by the controller may become less significant when compared with the network delay. In this way, the delay efficiency of our DSM solution is close to hardware solutions on average but still have all the flexibility of software solutions.
引用
收藏
页码:39 / 44
页数:6
相关论文
共 16 条
[1]  
AGARWAL A, 1995, ACM COMP AR, P2, DOI 10.1109/ISCA.1995.524544
[2]   A survey of research and practices of network-on-chip [J].
Bjerregaard, Tobias ;
Mahadevan, Shankar .
ACM COMPUTING SURVEYS, 2006, 38 (01) :1-51
[3]   Thousand core chips-a technology perspective [J].
Borkar, Shekhar .
2007 44TH ACM/IEEE DESIGN AUTOMATION CONFERENCE, VOLS 1 AND 2, 2007, :746-749
[4]   SMTp: An architecture for next-generation scalable multi-threading [J].
Chaudhuri, M ;
Heinrich, M .
31ST ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE, PROCEEDINGS, 2004, :124-135
[5]  
Hennessy J., 2007, Computer Architecture-A Quantitative Approach
[6]   How scaling will change processor architecture [J].
Horowitz, M ;
Daily, W .
2004 IEEE INTERNATIONAL SOLID-STATE CIRCUITS CONFERENCE, DIGEST OF TECHNICAL PAPERS, 2004, 47 :132-133
[7]  
Jantsch A, 2003, NETWORKS ON CHIP, P3
[8]  
KUSKIN J, 1994, CONF PROC INT SYMP C, P302
[9]   Challenges in embedded memory design and test [J].
Marinissen, EJ ;
Prince, B ;
Keitel-Schulz, D ;
Zorian, Y .
DESIGN, AUTOMATION AND TEST IN EUROPE CONFERENCE AND EXHIBITION, VOLS 1 AND 2, PROCEEDINGS, 2005, :722-727
[10]   Research challenges for on-chip interconnection networks [J].
Owens, John D. ;
Dally, William J. ;
Ho, Ron ;
Jayasimha, D. N. ;
Keckler, Stephen W. ;
Peh, Li-Shiuan .
IEEE MICRO, 2007, 27 (05) :96-108