VT GPGPU Use Case Physics in Medical Imaging

From EGIWiki
Jump to: navigation, search
EGI Activity groups Special Interest groups Policy groups Virtual teams Distributed Competence Centres


EGI Virtual teams: Main Active Projects Closed Projects Guidelines

GO TO THE GPGPU WORKING GROUP

GO TO THE GPGPU USE CASES

Scientific Discipline

Physics in Medical Imaging

Institute or Community

  • Corpuscular Physics Institute of Valencia, Spain

Keywords

  • NVIDIA Tesla C2070

Description

Here at IFIC (Corpuscular Physics Institute) located in Valencia, the "Physics in Medical Imaging" research group is working on PET medical image reconstruction. They have implemented the reconstruction algorithm using GPU technology. They use an NVIDIA Tesla C2070, this GPU contains 448 cores and 6 Gbytes of RAM memory. They also use a scanner to get the simulations. The reconstruction time achieved on a GPU was 4.3 times faster than using a CPU and 2.5 times faster than a CPU-multi-core parallel implementation using eight cores (MPI).