Proceedings of the ACM/SIGDA international symposium on Field programmable gate arrays
Hi-index | 0.00 |
Heterogeneous hardware architectures play very important role in high performance computing. This trend is also visible in multiscale simulations, where algorithms characterized by different computational behavior are responsible for calculations in different scales. This paper presents analysis of cellular automata model, used for modeling of material phenomena in micro scale, dependently on a problem size and a number of iterations. The OpenCL kernels generated by the framework are performed on GPGPU and CPU separately as well as simultaneously. The obtained results are used to detect the optimal load balancing between CPU and GPGPU and minimize a time of calculations.