RAG: An Efficient Reliability Analysis of Logic Circuits on Graphics Processing Units

Provided by: European Design and Automation Association
Topic: Hardware
Format: PDF
Reliability analysis, a process of evaluating the effects of errors due to both intrinsic noise and external transients will play an important role for both today's and tomorrow's nanometer-scale circuits. In this paper, the authors present RAG, an efficient Reliability Analysis tool based on Graphics Processing Units (GPU). RAG is a fault injection based parallel stochastic simulator implemented on a state-of-the-art GPU. A two-stage simulation framework is proposed to exploit the high computation efficiency of GPUs. Experimental results demonstrate the accuracy and performance of RAG. An average speed up of 412

Find By Topic