The procedural generation of planetoids finds its place in the field of visualization of virtual worlds in video games, movies, and simulation tools. Due to the growing popularity of the application, the requirements for the quality, uniqueness, and scalability of visualization results are increasing, which, in turn, leads to higher requirements for hardware computing resources.
The features of the computational model of discrete transforms of Fourier class based on cyclic convolutions to determine the algorithmic calculation error are analyzed. Based on the approach of efficient computation of discrete transforms of Fourier class of arbitrary size N, using of a hashing array to transform a discrete basis matrix into a set of block-cyclic submatrices, the components of computational costs are considered. These components of computational costs depend on the type of transform, the size and the block-cycle structure of the transformation core.
The consideration of modelling buttom-up visual attention is given in this paper. Particularly, saliency-based Itti’s model as one of the basic and widely used is analysed here. Advantages and limitations, open questions, and some hypotheses of improvement of this model are shown. Especially, we propose to change WTA network of leakly integrate-and-fire neurons on most modern simple network. We assume that using CMYK or HSV color model will give possibility of allowance of additional visual features.
The article presents the new computational model which we name the parallel ordered-access machine because of its base – the parallel ordered-access memory. It also describes the computer architecture which implements proposed computational model and owing to this does not have such a limitation as the memory wall and provides parallel conflict-free memory access. The efficiency of the proposed ordered-access machine computational model is evaluated and an example of its implementation is presented.