Gaussian convolutions computation is required in several scientific fields and, to this aim, efficient approximation methods, based on Recursive Filters (RFs), have been developed recently. Among them, Gaussian Recursive Filters (RFs) are designed to approximate the Gaussian convolution in a very efficient way. The accuracy of these methods, as is well known, can be improved by means of the use of the so-called K-iterated Gaussian recursive filters, that is in the repeated application of the basic RF. To improve the provided accuracy, K-iterated versions of these methods are also considered. Since it is often necessary to handle large size one-dimensional input signals, a parallel approach becomes mandatory. Recently, we proposed a parallel algorithm for the implementation of the K-iterated first-order Gaussian RF on multicore architectures. Here, using a similar parallelization strategy, based on a domain decomposition with overlapping, we propose a new implementation that would exploit, in terms of both accuracy and performance, the GPU (Graphics Processing Unit) capabilities on CUDA environment. Tests and experiments confirm the reliability and the efficiency of the proposed implementation.

Biological data contain very important information for genoma analysis. In last decades, the size of these data is constantly growing. So the Next Generation Sequence (NGS) data has been introduced. These kind of data are represented by different data formats, such as FASTQ, FASTA, SAM, etc. In order to allow a good analysis and storing of them, due to large dimension of these data, several compressors have been performed. FQSqueezer is a novel genomic compressor for FASTQ data files. But several issues are present due to multithread version that runs on multi-core hardware. It is wellknown that the number of cores in a CPU is limited and very minor with respect to GPUs’ cores number. In order to increase the performance related to this compressor method, in this work we present a GPU-parallel implementation of cited compressor by exploiting CUDA framework. More precisely, a suitable domain decomposition is able to give an appreciable gain of performance in terms of time and reliability. Several execution tests confirm the gain of efficiency achieved by our parallel implementation.