|
|
Fast Tissue Image Reconstruction Using a Graphics Card
Kadlubiak, Kristián ; Kula, Michal (referee) ; Jaroš, Jiří (advisor)
The photoacoustic spectroscopy is a recently developed imaging method that finds applications in many scientific fields such as medicine, biochemistry, materials engineering and many others. The photoacoustic spectroscopy finds particularly nice applications in medicine due to its properties such as non-invasiveness, non-aggressiveness and great accuracy. The source of this accuracy lies in advanced time-consuming calculations including operations like FFT and trilinear interpolation. This thesis is dedicated to the acceleration of this technique on a graphics card. In our implementation, we have taken a full advantage of various features provided in modern GPUs such as shared memory and texture hardware. Our implementation has been tested on one of the most powerful GPU designed for high performance computing, namely NVIDIA K20m. In this environment, our application speeds up certain parts of reconstruction by a factor above 400. In a single run mode, the whole reconstruction runs a bit longer than the pure MATLAB version due to the necessity of transferring data between MATLAB and the CUDA code, although the developed approach reduced the data transfers between MATLAB and GPU by 37%. The real potential of the implementation reveals while processing large batches of photoacoustic images.
|
|
|
Fast Tissue Image Reconstruction Using a Graphics Card
Kadlubiak, Kristián ; Kula, Michal (referee) ; Jaroš, Jiří (advisor)
The photoacoustic spectroscopy is a recently developed imaging method that finds applications in many scientific fields such as medicine, biochemistry, materials engineering and many others. The photoacoustic spectroscopy finds particularly nice applications in medicine due to its properties such as non-invasiveness, non-aggressiveness and great accuracy. The source of this accuracy lies in advanced time-consuming calculations including operations like FFT and trilinear interpolation. This thesis is dedicated to the acceleration of this technique on a graphics card. In our implementation, we have taken a full advantage of various features provided in modern GPUs such as shared memory and texture hardware. Our implementation has been tested on one of the most powerful GPU designed for high performance computing, namely NVIDIA K20m. In this environment, our application speeds up certain parts of reconstruction by a factor above 400. In a single run mode, the whole reconstruction runs a bit longer than the pure MATLAB version due to the necessity of transferring data between MATLAB and the CUDA code, although the developed approach reduced the data transfers between MATLAB and GPU by 37%. The real potential of the implementation reveals while processing large batches of photoacoustic images.
|
guest ::
