A GPU/CUDA Implementation of the Collection-Diffusion Model to Compute SER of Large Area and Complex Circuits - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

A GPU/CUDA Implementation of the Collection-Diffusion Model to Compute SER of Large Area and Complex Circuits

Résumé

This work reports the CUDA implementation of the collection-diffusion model to compute the soft-error rate (SER) of large area and/or complex circuits on graphics processing units (GPU). We detail the time parallelization introduced in the algorithm to accelerate by one order of magnitude the SER calculation. Code performances are evaluated on a NVIDIA Tesla C1060 GPU card for the calculation of the SER of a 65nm SRAM circuit subjected to an alpha-particle source irradiation.
Fichier non déposé

Dates et versions

hal-04393640 , version 1 (14-01-2024)

Identifiants

Citer

Jean-Luc Autran, Slawosz Uznanski, Sebastien Martinie, Philippe Roche, Gilles Gasiot, et al.. A GPU/CUDA Implementation of the Collection-Diffusion Model to Compute SER of Large Area and Complex Circuits. International Conference on Integrated Circuit Design and Technology (ICICDT 2010), Jun 2010, Grenoble, France. pp.67-70, ⟨10.1109/ICICDT.2010.5510293⟩. ⟨hal-04393640⟩
3 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More