Applying GPU Dynamic Parallelism to High-Performance Normalization of Gene Expressions
National Laboratory for Scientific Computing;University of Malaga
@article{soutoapplying,
title={Applying GPU Dynamic Parallelism to High-Performance Normalization of Gene Expressions},
author={Souto, Roberto P and Osthoff, Carla and de Vasconcelos, Ana TR and Augusto, Douglas A and da Silva Dias, Pedro L and Rodriguez, Andres and Trelles, Oswaldo and Ujaldon, Manuel}
}
High-density oligonucleotide microarrays allow several millions of genetic markers in a single experiment to be observed. Current bioinformatics tools for gene expression quantile data normalization are unable to process such huge data sets. In parallel with this reality, the huge volume of molecular data produced by current high-throughput technologies in modern molecular biology has increased at a similar pace, challenging our capacity to process and understand data. The arrival of CUDA has unveiled the extraordinary power of Graphics Processing Units (GPUs) to accelerate data intensivegeneral purpose computing. In this work we have evaluated the use of dynamic parallelism for ordering gene expression data, where the management of kernels launching can be done not only by the host, but also by the device. We have compared the performance of the sequential quicksort algorithm from the GNU C Library (glibc) with the parallel implementation available in the CUDA-5.5 Toolkit Samples.
March 22, 2014 by hgpu
