FSimGP^2: An Efficient Fault Simulator with GPGPU
Authors:
- Min LiMLMin Li
- Michael S. HsiaoMHMichael S. Hsiao
- 1 December 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 15-20
Abstract
General Purpose computing on Graphical Processing Units (GPGPU) is a paradigm shift in computing that promises a dramatic increase in performance. But GPGPU also brings an unprecedented level of complexity in algorithmic design and software development. In this paper, we present an efficient parallel fault simulator, FSimGP 2 , that exploits the high degree of parallelism supported by a state-of-the-art graphic processing unit (GPU) with the NVIDIA Compute Unified Device Architecture (CUDA). A novel three-dimensional parallel fault simulation technique is proposed to achieve extremely high computation efficiency on the GPU. The experimental results demonstrate a speedup of up to 42× compared to another GPU-based fault simulator and up to 53× over a state-of-the-art algorithm on conventional processor architectures.Keywords
This publication has 5 references indexed in Scilit:
- Fault Table Computation on GPUsJournal of Electronic Testing, 2010
- Event-driven gate-level simulation with GP-GPUs2009
- Towards acceleration of fault simulation using graphics processing units2008
- NVIDIA Tesla: A Unified Graphics and Computing ArchitectureIEEE Micro, 2008
- Combinational profiles of sequential benchmark circuits2003