Implementation of usual computerized tomography methods on GPU using the Compute Unified Device Architecture (CUDA)

Author

Recur, Benoit ; Desbarats, Pascal ; Domenger, Jean-Philippe

Author_Institution

LaBRI, Bordeaux 1 Univ., Talence, France

fYear

2009

fDate

24-26 Sept. 2009

Firstpage

41

Lastpage

46

Abstract

CUDA (Compute Unified Device Architecture) is an efficient architecture developed by NVIDIA to compute parallel algorithms on Graphic Processing Unit (GPU). Using the API associated with this architecture, we develop fast parallel algorithms to compute standard methods for computerized tomography. Computation times are compared to their similar implementations on CPU to illustrate the efficiency of GPU implementation. Some limitations are highlighted and we develop different GPU-computation strategies induced by the size of used/computed data.

Keywords

application program interfaces; computer graphic equipment; computerised tomography; coprocessors; medical image processing; parallel algorithms; API; CUDA; GPU; NVIDIA; compute unified device architecture; computerized tomography methods; graphic processing unit; parallel algorithms; Graphics processing unit; Image reconstruction; Instruction sets; Interpolation; Kernel; Pixel; Transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Signal Processing Algorithms, Architectures, Arrangements, and Applications Conference Proceedings (SPA), 2009

Conference_Location

Poznan

Print_ISBN

978-1-4577-1477-1

Electronic_ISBN

978-83-62065-06-6

Type

conf

Filename

5941283