t is well known that the standard formulation of the Smoothed Particle Hydrodynamics is usually poor when scattered data distribution is considered or when the approximation near the boundary occurs. Moreover, the method is computational demanding when a high number of data sites and evaluation points are employed. In this paper an enhanced version of the method is proposed improving the accuracy and the efficiency by using a HPC environment. Our implementation exploits the processing power of GPUs for the basic computational kernel resolution. The performance gain demonstrates the method to be accurate and suitable to deal with large sets of data.
|Numero di pagine||5|
|Stato di pubblicazione||Published - 2018|
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Computer Networks and Communications
- Computer Vision and Pattern Recognition
- Signal Processing