An Area-efficient Hexagonal Interconnection Network for Multi-core Processors

被引:0
作者
Kresch, Edward [1 ]
Wang, Xiaofang [1 ]
机构
[1] Villanova Univ, Dept Elect & Comp Engn, Villanova, PA 19085 USA
来源
2014 INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING & SIMULATION (HPCS) | 2014年
关键词
network on chip; 1-word buffering; hexagonal network;
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
With the rapid increase in the number of processor cores on a chip, packet-switching networks on chip (NoCs) have emerged as a promising paradigm for designing scalable communication infrastructures for future multi-core processors. The quest for high-performance networks, however, has led to very area-consuming and complex routers with marginal return in performance. On the other hand, studies show that real parallel applications generate traffic at a much lower rate than the offered rate at the cost of expensive and power-hungry buffers. This paper presents a low-cost hexagonal network design with only one buffer in each router. Efficient routing algorithms are proposed. Extensive simulation results with a 19-node network show that our network, in addition to its lower cost, provides low network latency under low to medium network load, which matches the communication requirement imposed by applications for multi-core processors.
引用
收藏
页码:39 / 46
页数:8
相关论文
共 15 条
[1]  
Adriahantenaina A, 2003, DESIGNERS FORUM: DESIGN, AUTOMATION AND TEST IN EUROPE CONFERENCE AND EXHIBITION, P70
[2]   Networks on chips: A new SoC paradigm [J].
Benini, L ;
De Micheli, G .
COMPUTER, 2002, 35 (01) :70-+
[3]   ADDRESSING, ROUTING, AND BROADCASTING IN HEXAGONAL MESH MULTIPROCESSORS [J].
CHEN, MS ;
SHIN, KG ;
KANDLUR, DD .
IEEE TRANSACTIONS ON COMPUTERS, 1990, 39 (01) :10-18
[4]  
DALLY WJ, 1987, IEEE T COMPUT, V36, P547, DOI 10.1109/TC.1987.1676939
[5]   3D hexagonal network:: Modeling, topological properties, addressing scheme, and optimal routing algorithm [J].
Decayeux, C ;
Semé, D .
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2005, 16 (09) :875-884
[6]  
Gratz P, 2007, NOCS 2007: FIRST INTERNATIONAL SYMPOSIUM ON NETWORKS-ON-CHIP, PROCEEDINGS, P7
[7]   A 5-GHz mesh interconnect for a teraflops processor [J].
Hoskote, Yatin ;
Vangal, Sriram ;
Singh, Arvind ;
Borkar, Nitin ;
Borkar, Shekhar .
IEEE MICRO, 2007, 27 (05) :51-61
[8]  
Kim J, 2009, IEEE CUST INTEGR CIR, P255, DOI 10.1109/CICC.2009.5280852
[9]  
Malony AllenD., 1988, the 2nd Symposium on the Frontiers of Massively Parallel Computation, P499
[10]  
Moscibroda T, 2009, CONF PROC INT SYMP C, P196, DOI 10.1145/1555815.1555781