BUFFER ENGINEERING FOR MODIFIED FAT TREE NoCS FOR MANY-CORE SYSTEMS-ON-CHIP

被引:1
作者
Elrabaa, Muhammad E. S. [1 ]
Bouhraoua, Abdelhafid [1 ]
机构
[1] King Fahd Univ Petr & Minerals, Dept Comp Engn, Dhahran 31261, Saudi Arabia
关键词
Networks-on-chip; systems-on-chip; chip multi-processors; many-core systems; PERFORMANCE; COST; CMP;
D O I
10.1142/S0218126614501059
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
As networks-on-chips (NoCs) are expected to provide the necessary scalable communication medium for future many-core systems-on-chips (SoCs) optimizing their resources is of great importance. What is really needed is an efficient NoC architecture with optimized resources that requires very little customization by the SoC developers. One of the most important area and power hungry resources is the NoC's buffers. In this work, a new Modified Fat Tree (MFT) NoC architecture with buffers engineered for maximum efficiency (performance versus area) is presented. Extensive simulations are used to show optimum buffer design/placement under different conditions of traffic types and NoC sizes.
引用
收藏
页数:34
相关论文
共 45 条
[1]   Balancing Performance and Cost in CMP Interconnection Networks [J].
Abad, Pablo ;
Puente, Valentin ;
Angel Gregorio, Jose .
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2012, 23 (03) :452-459
[2]   AdNoC: Runtime Adaptive Network-on-Chip Architecture [J].
Al Faruque, Mohammad Abdullah ;
Ebi, Thomas ;
Henkel, Joerg .
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS, 2012, 20 (02) :257-269
[3]  
[Anonymous], P INT C FIELD PROGR
[4]  
[Anonymous], P INT S COMP ARCH JU
[5]  
[Anonymous], P HARDW SOFTW COD SY
[6]  
[Anonymous], P 4 INT C HARDW SOFT
[7]  
[Anonymous], P 20 ANN C INT CIRC
[8]  
[Anonymous], P INT S SYST ON CHIP
[9]  
[Anonymous], HINDAWI VLSI DES MAY
[10]  
[Anonymous], 2006, Proceedings of the 14th IEEE International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS'06), DOI [10.1109/MASCOTS.2006.9, DOI 10.1109/MASCOTS.2006.9]