H-PITRE (High-performance software for Phase-sensitive x-ray Image processing and Tomography REconstruction) is a fast tomography reconstruction program which uses the parallel computing abilities of NVIDIA GPU (Graphics Processing Unit).
NVIDIA revolutionized the GPU computing world in 2006-2007 by introducing a new massively parallel architecture called CUDA. The model for GPU computing is to use both CPU and GPU together in a heterogeneous co-processing computing. The sequential part of the application runs on the CPU and the computationally-intensive part is accelerated by the GPU. From the user's perspective, the application just runs faster because it is using the GPU to boost performance.
Tomography reconstruction, which is an image processing intensive task, can also take advantage of GPU computing to get accelerated. H-PITRE has been developed on the basis of Qt, C++ and CUDA and -at the moment- supports parallel beam tomography data processing. H-PITRE (beta version) is freeware and can be downloaded from this page.
If you need help or if you want to provide any feedback please contact email@example.com
Last update: 30/08/2012
Page editor: Luigi Rigon
For questions or comments about this site please contact firstname.lastname@example.org.
Image in the page header: an artistically enhanced picture of particle tracks in the BEBC, Big European Bubble Chamber (Copyright CERN).