In the paper we present the use of graphic processor units to accelerate the most time-consuming stages of a simulation of angiogenesis and tumor growth. By the use of advanced CUDA mechanisms such as shared memory, textures and atomic operations, we managed to speed up the CUDA kernels by a factor of 57x. However, in our simulation we used the GPU as a co-processor and data from CPU was copied back and forth in each phase. It decreased the speedup of rewritten stages by 40%. We showed that the performance of the entire simulation can be improved by a factor of 10 up to 20.
The paper presents the main issues of a computer animation of a set of elastic macroscopic objects based on the particle method. The main assumption of the generated animations is to achieve very realistic movements in a scene observed on the computer display. The objects (solid bodies) interact mechanically with each other. The movements and deformations of solids are calculated using the particle method. Phenomena connected with the behaviour of solids in the gravitational field, their deformations caused by collisions and interactions with the optional liquid medium are simulated. The simulation of the Iiquid is performed using the cellular automata method. The paper presents both simulation schemes (particle method and cellular automata rules) and the method of combining them in the single animation program. In order to speed up the execution of the program the parallel version based on the network of workstation was developed. The paper describes the methods of the parallelization and it considers problems of load-balancing, collision detection, process synchronization and distributed control of the animation.
