Performance Analysis of an Ultrasound Reconstruction Algorithm for Non Destructive Testing

Antoine Pedron, Lionel Lacassagne, Victor Barbillon, Franck Bimbard, Gilles Rougeron, Stephane Le Berre
CEA, LIST, F-91191 Gif-sur-Yvette, France
PARCO, 2011


   title={Performance Analysis of an Ultrasound Reconstruction Algorithm for Non Destructive Testing},

   author={PEDRON, A. and LACASSAGNE, L. and BARBILLON, V. and BIMBARD, F. and ROUGERON, G. and LE BERRE, S.},



Download Download (PDF)   View View   Source Source   



The CIVA software platform developed by CEA-LIST offers various simulation and data processing modules dedicated to non-destructive testing (NDT). In particular, ultrasonic imaging and reconstruction tools are proposed in the purpose of localizing echoes and identifying and sizing the detected defects. Because of the complexity of data processed, computation time is now a limitation for the optimal use of available information. In this article, we present performance results on parallelization of one computationally heavy algorithm on general purpose processors (GPP) and graphic processing units (GPU). Although GPU implementation makes an intensive use of atomic intrinsics, it gave the highest performances. Only a dual 6-core GPP catches up its performances. Both architectures have been evaluated with different APIs: OpenMP, CUDA and OpenCL.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: