Thermal-aware Design Strategies for the 3D NoC-based Multi-Core Systems

To enhance the performance of 3D NoC-based systems, we have proposed design techniques for 3D NoC-based systems, in Chaps. 3– 5. However, thermal issues have become critical roadblocks in achieving highly reliable 3D systems. In the last chapter, we have presented a solution to such problem for 2D NoC-based systems using thermal-aware application mapping strategy. The thermal problem becomes more severe in 3D NoC-based systems compared to 2D NoC, due to the increased power density and lower thermal conductivity of inter-tier dielectrics. Furthermore, in 3D systems, the heat sink is far away from some of the layers. Excessive high temperature can significantly degrade the interconnect and device reliability which may, in turn, cause functional and timing faults, reduce the mean time to failure and speed up the ageing process in 3D systems. Another concern introduced by technology scaling is the increased leakage power dissipation. Higher temperature results in increased leakage power dissipation, due to its exponential dependency on temperature. Increased leakage power leads to higher total power consumption, which in turn generates more heat and creates a vicious cycle. Thus, the excessively high temperature has to be controlled by an upper bound provided by a designer.

[1]  Jason Cong,et al.  Thermal via planning for 3-D ICs , 2005, ICCAD-2005. IEEE/ACM International Conference on Computer-Aided Design, 2005..

[2]  Kevin Skadron,et al.  Temperature-aware microarchitecture , 2003, ISCA '03.

[3]  Takuji Nishimura,et al.  Mersenne twister: a 623-dimensionally equidistributed uniform pseudo-random number generator , 1998, TOMC.

[4]  Jason Cong,et al.  A thermal-driven floorplanning algorithm for 3D ICs , 2004, ICCAD 2004.

[5]  Sung-Mo Kang,et al.  Cell-level placement for improving substrate thermal distribution , 2000, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst..

[6]  Zhao Hai,et al.  Convergence Analysis of a Dynamic Discrete PSO Algorithm , 2008, 2008 First International Conference on Intelligent Networks and Intelligent Systems.

[7]  James Kennedy,et al.  Particle swarm optimization , 2002, Proceedings of ICNN'95 - International Conference on Neural Networks.

[8]  Makoto Matsumoto,et al.  SIMD-Oriented Fast Mersenne Twister: a 128-bit Pseudorandom Number Generator , 2008 .

[9]  Andrew B. Kahng,et al.  ORION 2.0: A Power-Area Simulator for Interconnection Networks , 2012, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[10]  Khaled Benkrid,et al.  Mersenne Twister Random Number Generation on FPGA, CPU and GPU , 2009, 2009 NASA/ESA Conference on Adaptive Hardware and Systems.

[11]  Jie Meng,et al.  Optimizing energy efficiency of 3-D multicore systems with stacked DRAM under power and thermal constraints , 2012, DAC Design Automation Conference 2012.