Parallel Space Saving on Multi and Many-Core Processors

TL;DR

This paper develops and evaluates parallel shared-memory algorithms for the $k$-majority problem, demonstrating significant performance improvements with MPI/OpenMP implementations on multi-core systems, but no gains on Intel Phi accelerators.

Contribution

It introduces a shared-memory version of the Space Saving algorithm for $k$-majority detection and compares hybrid MPI/OpenMP and pure MPI implementations on various hardware.

Findings

MPI/OpenMP version outperforms pure MPI version

Intel Phi does not improve performance over Xeon cores

Parallel algorithms are effective for large-scale frequent item detection

Abstract

Given an array $\mathcal{A}$ of $n$ elements and a value $2 \leq k \leq n$, a frequent item or $k$-majority element is an element occurring in $\mathcal{A}$ more than $n/k$ times. The $k$-majority problem requires finding all of the $k$-majority elements. In this paper we deal with parallel shared-memory algorithms for frequent items; we present a shared-memory version of the Space Saving algorithm and we study its behavior with regard to accuracy and performance on many and multi-core processors, including the Intel Phi accelerator. We also investigate a hybrid MPI/OpenMP version against a pure MPI based version. Through extensive experimental results we prove that the MPI/OpenMP parallel version of the algorithm significantly enhances the performance of the earlier pure MPI version of the same algorithm. Results also prove that for this algorithm the Intel Phi accelerator does not introduce any improvement with respect to the Xeon octa-core processor.