In-place parallel super scalar samplesort (IPS^4o)

DOI10.4230/LIPICS.ESA.2017.9zbMATH Open1442.68043arXiv1705.02257OpenAlexW2964316344MaRDI QIDQ5111694FDOQ5111694

Michael Axtmann, Sascha Witt, Peter Sanders, Daniel Ferizovic

Publication date: 27 May 2020

Abstract: We present a sorting algorithm that works in-place, executes in parallel, is cache-efficient, avoids branch-mispredictions, and performs work O(n log n) for arbitrary inputs with high probability. The main algorithmic contributions are new ways to make distribution-based algorithms in-place: On the practical side, by using coarse-grained block-based permutations, and on the theoretical side, we show how to eliminate the recursion stack. Extensive experiments show that our algorithm IPS${}^4$o scales well on a variety of multi-core machines. We outperform our closest in-place competitor by a factor of up to 3. Even as a sequential algorithm, we are up to 1.5 times faster than the closest sequential competitor, BlockQuicksort.

Full work available at URL: https://arxiv.org/abs/1705.02257

Recommendations

• Algorithms – ESA 2004
• Parallel sorting by regular sampling
• Parallel string sample sort
• An efficient parallel sorting algorithm
• Robust massively parallel sorting

zbMATH Keywords

shared memoryin-place algorithmparallel sortingcomparison-based sortingbranch prediction

Mathematics Subject Classification ID

Searching and sorting (68P10) Parallel algorithms in computer science (68W10)

Cites Work

• Multi-Pivot Quicksort: Theory and Experiments
• How Branch Mispredictions Affect Quicksort
• Samplesort: A Sampling Approach to Minimal Storage Tree Sorting
• Parallel String Sample Sort
• Algorithms – ESA 2004
• Engineering a cache-oblivious sorting algorithm
• Multiway In-Place Merging
• Title not available (Why is that?)
• A simple algorithm for in-place merging
• An in-place sorting with O ( n log n ) comparisons and O ( n ) moves
• BlockQuicksort: Avoiding Branch Mispredictions in Quicksort
• On a model of virtual address translation
• Title not available (Why is that?)
• In-Place Parallel Super Scalar Samplesort (IPSSSSo)

Cited In (4)

• BlockQuicksort
• In-Place Parallel Super Scalar Samplesort (IPSSSSo)
• Computational Science - ICCS 2004
• Algorithms – ESA 2004

Uses Software

• MCSTL
• CMU Benchmarks
• Intel TBB
• Quicksort
• GitHub

This page was built for publication: In-place parallel super scalar samplesort (\(\mathrm{IPS}^4\mathrm{o}\))

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5111694)