panthema / tags / research
Two figures from the technical report

A Bulk-Parallel Priority Queue in External Memory with STXXL

Posted on 2015-04-03 14:54 by Timo Bingmann at Permlink with 0 Comments. Tags: research stxxl

Today, our technical report on "A Bulk-Parallel Priority Queue in External Memory with STXXL" is now available on arXiv as 1504.00545 or locally: 1504.00545v1.pdf 1504.00545v1.pdf with source 1504.00545v1.tar.gz 1504.00545v1.tar.gz (130 KiB). A big thanks goes to Thomas Keh for the hard work he did in his bachelor thesis, and to Peter Sanders for all the insights into priority queues. The technical report is an extended version of our paper that will appear at the 14th International Symposium on Experimental Algorithms - SEA 2015.

Download 1504.00545v1.pdf

The bulk-parallel priority queue is current available in the development repository of STXXL on Github.

On 2015-06-29, Thomas Keh presented the PPQ at SEA'15 in Paris.

Abstract

We propose the design and an implementation of a bulk-parallel external memory priority queue to take advantage of both shared-memory parallelism and high external memory transfer speeds to parallel disks. To achieve higher performance by decoupling item insertions and extractions, we offer two parallelization interfaces: one using "bulk" sequences, the other by defining "limit" items. In the design, we discuss how to parallelize insertions using multiple heaps, and how to calculate a dynamic prediction sequence to prefetch blocks and apply parallel multiway merge for extraction. Our experimental results show that in the selected benchmarks the priority queue reaches 75% of the full parallel I/O bandwidth of rotational disks and and 65% of SSDs, or the speed of sorting in external memory when bounded by computation.

Algorithm schema of Recurse Last Parallel Multiway Mergesort

Practical Massively Parallel Sorting -- Basic Algorithmic Ideas

Posted on 2014-10-24 22:30 by Timo Bingmann at Permlink with 0 Comments. Tags: research massive-sorting

Last Friday we were able to finish a technical report on "Practical Massively Parallel Sorting -- Basic Algorithmic Ideas", which is now available on arXiv as 1410.6754 or locally: 1410.6754v1.pdf 1410.6754v1.pdf with source 1410.6754v1.tar.gz 1410.6754v1.tar.gz (130 KiB). A big thanks goes to all the other authors, Michael Axtmann, Peter Sanders, and Christian Schulz.

The report proposes two new hierarchical algorithms "Recurse Last Mergesort" (RLM-Sort) and "Adaptive Multipass Sample Sort" (AMS-Sort), together with randomized data exchange schemes to avoid worst case behavior on large instances.

Download 1410.6754v1.pdf

We now plan to implement some of the new algorithms.

Abstract

To obtain sorting algorithms that scale to the largest available machines, conventional parallel sorting algorithms cannot be used since they either have prohibitive communication volume or prohibitive critical path length for computation. We outline ideas how to combine a number of basic algorithmic techniques which overcome these bottlenecks.

Example of intuition behind the inducing process

Presented Short Paper about eSAIS at MASSIVE'13 Workshop

Posted on 2013-09-05 18:00 by Timo Bingmann at Permlink with 0 Comments. Tags: research stringology c++ talk

Today, we presented a shorter version of our work on "Inducing Suffix and LCP Arrays in External Memory" at the MASSIVE Workshop 2013, held adjacently with ESA at ALGO 2013 in Sophia Antipolis, France.

The slides of our presentation 2013-09-05 eSAIS @ MASSIVE'13.pdf 2013-09-05 eSAIS @ MASSIVE'13.pdf and the corresponding short paper massive13esais.pdf massive13esais.pdf are available online via this webpage.

Download 2013-09-05 eSAIS @ MASSIVE'13.pdf
Download massive13esais.pdf

Please refer to the first eSAIS posting for details and source code.

Our thanks goes to all the organizers for making such an inspiring workshop possible.

Example of the Inducing Process

eSAIS - Inducing Suffix and LCP Arrays in External Memory

Posted on 2012-11-19 15:49 by Timo Bingmann at Permlink with 2 Comments. Tags: research stringology stxxl c++

This web page accompanies our conference paper "Inducing Suffix and LCP Arrays in External Memory", which we presented at the Workshop on Algorithm Engineering and Experiments (ALENEX 2013). A PDF of the publication is available from this site as alenex13esais.pdf alenex13esais.pdf or from the online proceedings. The paper was joint work with my colleagues Johannes Fischer and Vitaly Osipov.

Download alenex13esais.pdf

The slides to my presentation of the paper on January 7th, 2013 in New Orleans, LA, USA is available: alenex13esais-slides.pdf alenex13esais-slides.pdf. They contain little text and an example of the eSAIS algorithm with a simplified PQ.

Download alenex13esais-slides.pdf

We have also submitted a full version of the eSAIS paper to a journal. Due to long publication cycles, we make a pre-print of the journal article is available here: esais-preprint.pdf esais-preprint.pdf. The full paper contains more details on the inducing algorithm for the LCP array and additional experimental details.

Download esais-preprint.pdf

Our implementations of eSAIS, the eSAIS-LCP variants, DC3 and DC3-LCP algorithms as described in the paper are available below under the GNU General Public License v3 (GPL).

eSAIS and DC3 with LCP version 0.5.4 (current) updated 2013-12-13
Source code archive:
(includes STXXL 1.4.0)
eSAIS-DC3-LCP-0.5.4.tar.bz2 eSAIS-DC3-LCP-0.5.4.tar.bz2 (1.37 MiB) Browse online
Git repositories Suffix and LCP construction algorithms
git clone https://github.com/bingmann/eSAIS
cd eSAIS; git submodule init; git submodule update
STXXL 1.4.0
git clone https://github.com/stxxl/stxxl

For more information about compiling and testing the implementation, please refer to the README included in the source.

This blog entry continues on the next page ...

RSS 2.0 Weblog Feed Atom 1.0 Weblog Feed Valid XHTML 1.1 Valid CSS (2.1)
Copyright 2005-2015 Timo Bingmann - Impressum