Pairwise Distance Matrix Computation for Multiple Sequence Alignment on the Cell Broadband Engine

Abstract

Abstract. Multiple sequence alignment is an important tool in bioinformatics. Although efficient heuristic algorithms exist for this problem, the exponential growth of biological data demands an even higher throughput. The recent emergence of accelerator technologies has made it possible to achieve a highly improved execution time for many bioinformatics applications compared to general-purpose platforms. In this paper, we demonstrate how the PlayStation®3, powered by the Cell Broadband Engine, can be used as a computational platform to accelerate the distance matrix computation utilized in multiple sequence alignment algorithms.

Introducing and Implementing the Allpairs Skeleton for Programming Multi-GPU Systems

“…In previous work, efficient parallel implementations of allpairs computations on modern parallel processors were studied (e. g., multi-core CPUs [2], the Cell processor [18], and GPUs [3]) in the context of specific applications. In contrast to [16], which presents an efficient implementation scheme of allpairs computations for GPUs, we abstract the computation as an algorithmic skeleton and offer its efficient implementation to application developers as part of the SkelCL skeleton library.…”

“…These applications share a common computational pattern: for two sets of entities, the same computation is performed independently for all pairs in which entities from the first set are combined with entities from the second set. Previous work discussed specific allpairs applications and their parallel implementations on multi-core CPUs [2], the Cell processor [18], and GPUs [3,16]; it demonstrated that developing well-performing implementations for allpairs is challenging, especially on GPU systems, as it requires exploiting their complex memory hierarchy and assumes a deep knowledge of the target hardware architecture.…”

Accelerating Pairwise Computations on Cell Processors

“…Such problems have been studied on parallel systems before; for example, see [1] for many-body simulations. There is considerable recent interest in executing pairwise computations on Cell processors [4], [7], [8]. This work is carried out in the context of a specific application that the authors are trying to solve.…”

Applications on emerging paradigms in parallel computing

“…Arora et al [6] demonstrate the all-pairs N -body computational kernels on various multi-core platforms, including the Cell processor and NVIDIA graphics processors. Acceleration of the pairwise distance matrix computation employed in multiple sequence alignment algorithms was demonstrated on the Cell processor by Wirawan et al [114]. Also, Barrachina et al [15] explored graphics processors for matrix multiplication on dense matrices, and Bell et al [23] for sparse matrices.…”

“…Such problems have been studied on parallel systems before, for example, see [61] for many-body simulations. There is considerable recent interest in executing pairwise computations on Cell processors [6,118,114,117] as well as graphics processors [15,23]. These work are carried out in the context of a specific application that the authors are trying to solve.…”