Cache-aware algorithm for multidimensional correlations

Abstract

In the paper discusses a speed of a convolution or correlation functions in case of a big size of input data. When a data volume exceeds a cache size, a significant part of an execution time is spent on a loading data into the cache. A performance of correlation is explored an example of receiving a long radio signal by the use of comparison with a big number of patterns. To decrease this spending a method of reordering calculation and memory operations and is proposed. The method uses cache aware approach to construct cache friendly algorithms. A decreasing of execution time (in some case) achieves up to 44%