Affiliations: [a] Institute for Data Processing and Electronics, Karlsruhe Institute of Technology (KIT), mathii2009@gmail.com | [b] Department of Automation and Computer Systems, Tomsk Polytechnic University (TPU) | [c] Institute for Data Processing and Electronics, Karlsruhe Institute of Technology (KIT) | [d] European Synchrotron Radiation Facility
Note: [*] Address for correspondence: Institute for Data Processing and Electronics, Karlsruhe Institute of Technology (KIT), Kaiserstr. 12 Karlsruhe, Baden-Württemberg 76131 Germany.
Note: [†] Also works: Department of Automation and Computer Systems, Tomsk Polytechnic University (TPU)
Abstract: On-line monitoring of synchrotron 3D-imaging experiments requires very fast tomographic reconstruction. Direct Fourier methods (DFM) have the potential to be faster than standard Filtered Backprojection. We have evaluated multiple DFMs using various interpolation techniques. We compared reconstruction quality and studied the parallelization potential. A method using Direct Fourier Inversion (DFI) and a sinc-based interpolation was selected and parallelized for execution on GPUs. Several optimization steps were considered to boost the performance. Finally we evaluated the achieved performance for the latest generation of GPUs from NVIDIA and AMD. The results show that tomographic reconstruction with a throughput of more than 1.5 GB/sec on a single GPU is possible.
