Abstract

The authors present a fast GPU-based thermal simulation methods for 3D full-chip thermal analysis, applicable to both 2D and 3D chip designs. Given the fact that heat removal is an even greater challenge for 3D-ICs, the thermal simulation approach has extensions that incorporate integrated microchannel cooling, and hence is able to analyze the impact of liquid cooling technologies. Based on the physical heat dissipation paths of 3D-ICs with integrated microchannels, the researchers propose novel preconditioned iterative methods that can be efficiently accelerated on GPU's massively parallel computing platforms. Unlike the CPU-based solver development environment in which many existing sophisticated numerical simulation methods (matrix solvers) can be readily adopted and implemented, GPU-based thermal simulation demands more efforts in the algorithm and data structure design phase, and requires careful consideration of GPU's thread/memory organizations, data access/communication patterns, arithmetic intensity, as well as the hardware occupancies. As shown in various experimental results, the GPU based 3D thermal simulation solvers can achieve up to 360X speedups over the best available direct solvers and more than 35X speedups compared with the CPU-based iterative solvers, without loss of accuracy.