Parallel Optimisation of Bootstrapping in R

TL;DR

This paper presents a parallel implementation of bootstrapping in R using the SPRINT package, significantly accelerating computations on multi-core and supercomputing systems for statistical inference tasks.

Contribution

It introduces a parallelization method for bootstrapping in R that achieves near-optimal speedup on multi-node systems, improving computational efficiency.

Findings

Achieves close to optimal speedup on 16 nodes of a supercomputer.

Reaches near 100-fold speedup on 512 nodes.

Outperforms existing native R parallelization options.

Abstract

Bootstrapping is a popular and computationally demanding resampling method used for measuring the accuracy of sample estimates and assisting with statistical inference. R is a freely available language and environment for statistical computing popular with biostatisticians for genomic data analyses. A survey of such R users highlighted its implementation of bootstrapping as a prime candidate for parallelization to overcome computational bottlenecks. The Simple Parallel R Interface (SPRINT) is a package that allows R users to exploit high performance computing in multi-core desktops and supercomputers without expert knowledge of such systems. This paper describes the parallelization of bootstrapping for inclusion in the SPRINT R package. Depending on the complexity of the bootstrap statistic and the number of resamples, this implementation has close to optimal speed up on up to 16 nodes of a supercomputer and close to 100 on 512 nodes. This performance in a multi-node setting compares favourably with an existing parallelization option in the native R implementation of bootstrapping.