Volume Data Numerical Integration and Differentiation Using CUDA
Mingda Chen, Tung-Ju Hsieh, Yang-Lang Chang · 2011
Earthquake simulations generate large-scale ground-motion velocity wave-field data sets. One way to look at the data is to make it volume rendered so that researchers can examine the data efficiently. However, the volume data is usually quite large and a commodity graphics device can store one set of volume data. When the researcher need to look at the acceleration or displacement wave-field. The velocity data has to be integrated into displacement wave-field. Sometimes, the velocity data has to be differentiated into displacement wave-field. In this study, we used CUDA to compute the ground acceleration and displacement from velocity data. Numerical quadrature and centred difference method were implemented using CUDA for on-the-fly data exploration. We used CUDA to speed up ray casting method, trapezoidal quadrature, and centered difference method. We achieved a speed up of 100 times faster than using a CPU.