METEOR: Hybrid Photonic Ring-Mesh Network-on-Chip for Multicore Architectures

被引:44
作者
Bahirat, Shirish [1 ]
Pasricha, Sudeep [1 ]
机构
[1] Colorado State Univ, Dept Elect & Comp Engn, Ft Collins, CO 80523 USA
关键词
Design; Experimentation; Performance; Network-on-chip; photonic interconnect; chip multiprocessor; ULTRA-COMPACT; POWER; INTERCONNECTS; DESIGN; CHALLENGES; FUTURE;
D O I
10.1145/2567940
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
With increasing application complexity and improvements in process technology, Chip MultiProcessors (CMPs) with tens to hundreds of cores on a chip are becoming a reality. Networks-on-Chip (NoCs) have emerged as scalable communication fabrics that can support high bandwidths for these massively parallel multicore systems. However, traditional electrical NoC implementations still need to overcome the challenges of high data transfer latencies and large power consumption. On-chip photonic interconnects with high performance-per-watt characteristics have recently been proposed as an alternative to address these challenges for intra-chip communication. In this article, we explore using low-cost photonic interconnects on a chip to enhance traditional electrical NoCs. Our proposed hybrid photonic ring-mesh NoC (METEOR) utilizes a configurable photonic ring waveguide coupled to a traditional 2D electrical mesh NoC. Experimental results indicate a strong motivation to consider the proposed architecture for future CMPs, as it can provide about 5x reduction in power consumption and improved throughput and access latencies, compared to traditional electrical 2D mesh and torus NoC architectures. Compared to other previously proposed hybrid photonic NoC fabrics such as the hybrid photonic torus, Corona, and Firefly, our proposed fabric is also shown to have lower photonic area overhead, power consumption, and energy-delay product, while maintaining competitive throughput and latency.
引用
收藏
页数:33
相关论文
共 100 条
[1]   Fixed-outline floorplanning: Enabling hierarchical design [J].
Adya, SN ;
Markov, IL .
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2003, 11 (06) :1120-1135
[2]   Devices and architectures for photonic chip-scale integration [J].
Ahn, J. ;
Fiorentino, M. ;
Beausoleil, R. G. ;
Binkert, N. ;
Davis, A. ;
Fattal, D. ;
Jouppi, N. P. ;
McLaren, M. ;
Santori, C. M. ;
Schreiber, R. S. ;
Spillane, S. M. ;
Vantrease, D. ;
Xu, Q. .
APPLIED PHYSICS A-MATERIALS SCIENCE & PROCESSING, 2009, 95 (04) :989-997
[3]  
Al-Awwami ZH, 2001, 2001 INTERNATIONAL CONFERENCE ON COMPUTER NETWORKS AND MOBILE COMPUTING, PROCEEDINGS, P519, DOI 10.1109/ICCNMC.2001.962641
[4]  
[Anonymous], 2007, INT TECHNOLOGY ROADM
[5]  
Bahirat S., 2009, Proc. 7th IEEE/ACM Int. Conf. Hardware/software codesign and system synthesis, P129
[6]   A power-optimal repeater insertion methodology for global interconnects in nanometer designs [J].
Banerjee, K ;
Mehrotra, A .
IEEE TRANSACTIONS ON ELECTRON DEVICES, 2002, 49 (11) :2001-2007
[7]   Silicon photonics for compact, energy-efficient interconnects [Invited] [J].
Barwicz, T. ;
Byun, H. ;
Gan, F. ;
Holzwarth, C. W. ;
Popovic, M. A. ;
Rakich, P. T. ;
Watts, M. R. ;
Ippen, E. P. ;
Kaertner, F. X. ;
Smith, H. I. ;
Orcutt, J. S. ;
Ram, R. J. ;
Stojanovic, V. ;
Olubuyide, O. O. ;
Hoyt, J. L. ;
Spector, S. ;
Geis, M. ;
Grein, M. ;
Lyszczarz, T. ;
Yoon, J. U. .
JOURNAL OF OPTICAL NETWORKING, 2007, 6 (01) :63-73
[8]   Current-mode signaling in deep submicrometer global interconnects [J].
Bashirullah, R ;
Liu, WT ;
Cavin, RK .
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2003, 11 (03) :406-417
[9]   Building manycore processor-to-DRAM networks with monolithic silicon photonics [J].
Batten, Christopher ;
Joshi, Ajay ;
Orcutt, Jason ;
Khilo, Anatoly ;
Moss, Benjamin ;
Holzwarth, Charles ;
Popovic, Milos ;
Li, Hanqing ;
Smith, Henry ;
Hoyt, Judy ;
Kartner, Franz ;
Ram, Rajeev ;
Stojanovic, Vladimir ;
Asanovic, Krste .
16TH ANNUAL IEEE SYMPOSIUM ON HIGH-PERFORMANCE INTERCONNECTS, PROCEEDINGS, 2008, :21-+
[10]  
Beausoleil R., 2011, ACM J EMERGING TECHN, V7, P21