<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <doc>
    <id>3458</id>
    <completedYear>2009</completedYear>
    <publishedYear>2009</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>281</pageFirst>
    <pageLast>289</pageLast>
    <pageNumber/>
    <edition/>
    <issue>3</issue>
    <volume>25</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">MediGRID: Towards A User Friendly Secured Grid Infrastructure</title>
    <parentTitle language="eng">Future Generation Computer Systems (FGCS)</parentTitle>
    <identifier type="doi">10.1016/j.future.2008.05.005</identifier>
    <enrichment key="PeerReviewed">yes</enrichment>
    <author>Dagmar Krefting</author>
    <author>Julian Bart</author>
    <author>Kamen Beronov</author>
    <author>Olga Dzhimova</author>
    <author>Jürgen Falkner</author>
    <author>Michael Hartung</author>
    <author>Andreas Hoheisel</author>
    <author>Tobias Knoch</author>
    <author>Thomas Lingner</author>
    <author>Yassene Mohammed</author>
    <author>Kathrin Peter</author>
    <author>Erhard Rahm</author>
    <author>Ulrich Sax</author>
    <author>Dietmar Sommerfeld</author>
    <author>Thomas Steinke</author>
    <author>Thomas Tolxdorff</author>
    <author>Michael Vossberg</author>
    <author>Fred Viezens</author>
    <author>Anette Weisbecker</author>
    <collection role="institutes" number="vas">Distributed Algorithms and Supercomputing</collection>
    <collection role="persons" number="steinke">Steinke, Thomas</collection>
  </doc>
  <doc>
    <id>918</id>
    <completedYear/>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>reportzib</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2006-05-18</completedDate>
    <publishedDate>2006-05-18</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">THESEUS - Protein Structure Prediction at ZIB</title>
    <abstract language="eng">THESEUS, the ZIB threading environment, is a parallel implementation of a protein threading based on a multi-queued branch-and-bound optimal search algorithm to find the best sequence-to-structure alignment through a library of template structures. THESEUS uses a template core model based on secondary structure definition and a scoring function based on knowledge-based potentials reflecting pairwise interactions and the chemical environment, as well as pseudo energies for homology detection, loop alignment, and secondary structure matching. The threading core is implemented in C++ as a SPMD parallization architecture using MPI for communication. The environment is designed for generic testing of different scoring functions, e.g. different secondary structure prediction terms, different scoring matrices and information derived from multiple sequence alignments. A validaton of the structure prediction results has been done on the basis of standard threading benchmark sets. THESEUS successfully participated in the 6th Critical Assessment of Techniques for Protein Structure Prediction (CASP) 2004.</abstract>
    <identifier type="serial">06-24</identifier>
    <identifier type="opus3-id">918</identifier>
    <identifier type="urn">urn:nbn:de:0297-zib-9184</identifier>
    <author>Patrick May</author>
    <author>Thomas Steinke</author>
    <series>
      <title>ZIB-Report</title>
      <number>06-24</number>
    </series>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Protein Structure Prediction</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Bioinformatics</value>
    </subject>
    <collection role="ddc" number="000">Informatik, Informationswissenschaft, allgemeine Werke</collection>
    <collection role="msc" number="92-08">Computational methods</collection>
    <collection role="msc" number="92E10">Molecular structure (graph-theoretic methods, methods of differential topology, etc.)</collection>
    <collection role="institutes" number="vas">Distributed Algorithms and Supercomputing</collection>
    <collection role="persons" number="steinke">Steinke, Thomas</collection>
    <file>https://opus4.kobv.de/opus4-zib/files/918/ZR-06-24.pdf</file>
    <file>https://opus4.kobv.de/opus4-zib/files/918/ZR-06-24.ps</file>
  </doc>
  <doc>
    <id>1556</id>
    <completedYear/>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>reportzib</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2012-07-05</completedDate>
    <publishedDate>2012-07-05</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">A Novel Hybrid Approach to Automatically Determine Kernel Interface Data Volumes</title>
    <abstract language="eng">Scheduling algorithms for heterogeneous platforms make scheduling decisions based on several metrics. One of these metrics is the amount of data to be transferred from and to the accelerator. However, the automated determination of this metric is not a simple task. A few schedulers and runtime systems solve this problem by using regression models, which are imprecise though. Our novel approach for the determination of data volumes removes this limitation and thus provides a solution to obtain exact information.</abstract>
    <identifier type="issn">1438-0064</identifier>
    <identifier type="urn">urn:nbn:de:0297-zib-15569</identifier>
    <author>Sebastian Dreßler</author>
    <submitter>Sebastian Dreßler</submitter>
    <author>Thomas Steinke</author>
    <series>
      <title>ZIB-Report</title>
      <number>12-23</number>
    </series>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>function parameter analysis</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>function parameter sizes</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>heterogeneous systems</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>scheduling metrics</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>tool flow</value>
    </subject>
    <collection role="ccs" number="D.">Software</collection>
    <collection role="institutes" number="vas">Distributed Algorithms and Supercomputing</collection>
    <collection role="persons" number="steinke">Steinke, Thomas</collection>
    <collection role="projects" number="2011-ENHANCE">2011-ENHANCE</collection>
    <file>https://opus4.kobv.de/opus4-zib/files/1556/kdv_dressler_steinke_zibreport.pdf</file>
  </doc>
  <doc>
    <id>4218</id>
    <completedYear/>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>reportzib</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2013-08-26</completedDate>
    <publishedDate>2013-08-26</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Swendsen-Wang Multi-Cluster Algorithm for the 2D/3D Ising Model on Xeon Phi and GPU</title>
    <abstract language="eng">Simulations of the critical Ising model by means of local update algorithms suffer from critical slowing down. One way to partially compensate for the influence of this phenomenon on the runtime of simulations is using increasingly faster and parallel computer hardware. Another approach is using algorithms that do not suffer&#13;
from critical slowing down, such as cluster algorithms. This paper reports on the Swendsen-Wang multi-cluster algorithm on Intel Xeon Phi coprocessor 5110P, Nvidia Tesla M2090 GPU, and x86&#13;
multi-core CPU. We present shared memory versions of the said algorithm for the simulation of the two- and three-dimensional Ising model. We use a combination of local cluster search and global label reduction by means of atomic hardware primitives. Further, we&#13;
describe an MPI version of the algorithm on Xeon Phi and CPU, respectively. Significant performance improvements over known im&#13;
plementations of the Swendsen-Wang algorithm are demonstrated.</abstract>
    <identifier type="issn">1438-0064</identifier>
    <identifier type="urn">urn:nbn:de:0297-zib-42187</identifier>
    <identifier type="doi">10.1145/2503210.2503254</identifier>
    <enrichment key="SourceTitle">Appeared in: Proceeding SC '13 Proceedings of SC13: International Conference for High Performance Computing, Networking, Storage and Analysis Article No. 83 ACM New York, NY, USA, 2013</enrichment>
    <enrichment key="PeerReviewed">yes</enrichment>
    <author>Florian Wende</author>
    <submitter>Florian Wende</submitter>
    <author>Thomas Steinke</author>
    <series>
      <title>ZIB-Report</title>
      <number>13-44</number>
    </series>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Swendsen-Wang Multi-Cluster Algorithm</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Ising Model</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Xeon Phi</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>GPGPU</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Connected Component Labeling</value>
    </subject>
    <collection role="ccs" number="B.">Hardware</collection>
    <collection role="ccs" number="J.">Computer Applications</collection>
    <collection role="pacs" number="80.00.00">INTERDISCIPLINARY PHYSICS AND RELATED AREAS OF SCIENCE AND TECHNOLOGY</collection>
    <collection role="msc" number="68-XX">COMPUTER SCIENCE (For papers involving machine computations and programs in a specific mathematical area, see Section -04 in that area)</collection>
    <collection role="msc" number="82-XX">STATISTICAL MECHANICS, STRUCTURE OF MATTER</collection>
    <collection role="institutes" number="vas">Distributed Algorithms and Supercomputing</collection>
    <collection role="persons" number="steinke">Steinke, Thomas</collection>
    <collection role="projects" number="no-project">no-project</collection>
    <file>https://opus4.kobv.de/opus4-zib/files/4218/wende_steinke.pdf</file>
  </doc>
  <doc>
    <id>4222</id>
    <completedYear/>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>reportzib</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2013-08-30</completedDate>
    <publishedDate>2013-08-30</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">An Automated Approach for Estimating the Memory Footprint of Non-Linear Data Objects</title>
    <abstract language="eng">Current programming models for heterogeneous devices with disjoint physical memory spaces require explicit allocation of device memory and explicit data transfers. While it is quite easy to manually  implement these operations for linear data objects like arrays, this task becomes more difficult for non-linear objects, e.g. linked lists or multiple inherited classes. The difficulties arise due to dynamic memory requirements at run-time and the dependencies between data structures. In this paper we present a novel method to build a graph-based static data type description which is used to create code for injectable functions that automatically determine the memory footprint of data objects at run-time. Our approach is extensible to implement automatically generated optimized data transfers across physical memory spaces.</abstract>
    <identifier type="issn">1438-0064</identifier>
    <identifier type="urn">urn:nbn:de:0297-zib-42224</identifier>
    <identifier type="doi">10.1007/978-3-642-54420-0_25</identifier>
    <enrichment key="SourceTitle">Appeared in:  Euro-Par 2013: Parallel Processing Workshops. Lecture Notes in Computer Science 8374. 2014, pp. 249-258</enrichment>
    <author>Sebastian Dreßler</author>
    <submitter>Sebastian Dreßler</submitter>
    <author>Thomas Steinke</author>
    <series>
      <title>ZIB-Report</title>
      <number>13-46</number>
    </series>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>memory footprint</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>non-linear objects</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>static analysis</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>dynamic analysis</value>
    </subject>
    <collection role="ccs" number="E.">Data</collection>
    <collection role="institutes" number="vas">Distributed Algorithms and Supercomputing</collection>
    <collection role="persons" number="steinke">Steinke, Thomas</collection>
    <collection role="projects" number="2013-Many-Core-HPC">2013-Many-Core-HPC</collection>
    <file>https://opus4.kobv.de/opus4-zib/files/4222/DresslerSteinke-MemoryFootprint.pdf</file>
  </doc>
  <doc>
    <id>7230</id>
    <completedYear/>
    <publishedYear>2018</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst>e25851</pageFirst>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>Emerging Architectures in Computational Chemistry</issue>
    <volume/>
    <type>article</type>
    <publisherName>Wiley Online Library</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>2018-12-19</completedDate>
    <publishedDate>2018-12-19</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">OpenMP in VASP: Threading and SIMD</title>
    <abstract language="eng">The Vienna Ab initio Simulation Package (VASP) is a widely used electronic structure code that originally exploits process-level parallelism through the Message Passing Interface (MPI) for work distribution within and across nodes.&#13;
Architectural changes of modern parallel processors urge programmers to address thread- and data-level parallelism as well to benefit most from the available compute resources within a node.&#13;
We describe for VASP how to approach for an MPI + OpenMP parallelization including data-level parallelism through OpenMP SIMD constructs together with a generic high-level vector coding scheme.&#13;
We can demonstrate an improved scalability of VASP and more than 20% gain over the MPI-only version, as well as a 2x increased performance of collective operations using the multiple-endpoint MPI feature.&#13;
The high-level vector coding scheme applied to VASP's general gradient approximation routine gives up 9x performance gain on AVX512 platforms with the Intel compiler.</abstract>
    <parentTitle language="deu">International Journal of Quantum Chemistry</parentTitle>
    <identifier type="doi">10.1002/qua.25851</identifier>
    <enrichment key="PeerReviewed">yes</enrichment>
    <enrichment key="SubmissionStatus">in press</enrichment>
    <enrichment key="AcceptedDate">2018-12-19</enrichment>
    <submitter>Florian Wende</submitter>
    <author>Florian Wende</author>
    <author>Martijn Marsman</author>
    <author>Jeongnim Kim</author>
    <author>Fedor Vasilev</author>
    <author>Zhengji Zhao</author>
    <author>Thomas Steinke</author>
    <collection role="institutes" number="vas">Distributed Algorithms and Supercomputing</collection>
    <collection role="persons" number="steinke">Steinke, Thomas</collection>
    <collection role="projects" number="2013-Many-Core-HPC">2013-Many-Core-HPC</collection>
  </doc>
  <doc>
    <id>3415</id>
    <completedYear>2011</completedYear>
    <publishedYear>2011</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Granular Security for a Science Gateway in Structural Bioinformatics</title>
    <parentTitle language="eng">Proc. IWSG-Life 2011</parentTitle>
    <enrichment key="PeerReviewed">yes</enrichment>
    <author>Sandra Gesing</author>
    <author>Richard Grunzke</author>
    <author>Akos Balasko</author>
    <author>Georg Birkenheuer</author>
    <author>Dirk Blunk</author>
    <author>Sebastian Breuers</author>
    <author>André Brinkmann</author>
    <author>Gregor Fels</author>
    <author>Sonja Herres-Pawlis</author>
    <author>Peter Kacsuk</author>
    <author>Miklos Kozlovszky</author>
    <author>Jens Krüger</author>
    <author>Lars Packschies</author>
    <author>Patrick Schäfer</author>
    <author>Bernd Schuller</author>
    <author>Johannes Schuster</author>
    <author>Thomas Steinke</author>
    <author>Anna Szikszay Fabri</author>
    <author>Martin Wewior</author>
    <author>Ralph Müller-Pfefferkorn</author>
    <author>Oliver Kohlbacher</author>
    <collection role="institutes" number="vas">Distributed Algorithms and Supercomputing</collection>
    <collection role="persons" number="patrick.schaefer">Schäfer, Patrick</collection>
    <collection role="persons" number="steinke">Steinke, Thomas</collection>
    <collection role="projects" number="2009-MosGrid">2009-MosGrid</collection>
  </doc>
  <doc>
    <id>3419</id>
    <completedYear>2011</completedYear>
    <publishedYear>2011</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume>826</volume>
    <type>conferenceobject</type>
    <publisherName>CEUR Workshop Proceedings</publisherName>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">MoSGrid: Progress of Workflow driven Chemical&#13;
Simulations</title>
    <parentTitle language="eng">Proc. of Grid Workflow Workshop 2011, Cologne, Germany</parentTitle>
    <identifier type="url">http://CEUR-WS.org/Vol-826/paper02.pdf</identifier>
    <enrichment key="PeerReviewed">yes</enrichment>
    <author>Georg Birkenheuer</author>
    <author>Dirk Blunk</author>
    <author>Sebastian Breuers</author>
    <author>Andre Brinkmann</author>
    <author>Gregor Fels</author>
    <author>Sandra Gesing</author>
    <author>Richard Grunzke</author>
    <author>Sonja Herres-Pawlis</author>
    <author>Oliver Kohlbacher</author>
    <author>Jens Krüger</author>
    <author>Ulrich Lang</author>
    <author>Lars Packschies</author>
    <author>Ralph Müller-Pfefferkorn</author>
    <author>Patrick Schäfer</author>
    <author>Johannes Schuster</author>
    <author>Thomas Steinke</author>
    <author>Klaus Dieter Warzecha</author>
    <author>Martin Wewior</author>
    <collection role="institutes" number="vas">Distributed Algorithms and Supercomputing</collection>
    <collection role="persons" number="patrick.schaefer">Schäfer, Patrick</collection>
    <collection role="persons" number="steinke">Steinke, Thomas</collection>
    <collection role="projects" number="2009-MosGrid">2009-MosGrid</collection>
  </doc>
  <doc>
    <id>3421</id>
    <completedYear>2011</completedYear>
    <publishedYear>2011</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue>0</issue>
    <volume>-</volume>
    <type>article</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Solutions for biomedical grid computing – Case studies from the D-Grid project Services@MediGRID</title>
    <parentTitle language="eng">Journal of Computational Science</parentTitle>
    <identifier type="doi">10.1016/j.jocs.2011.06.006</identifier>
    <identifier type="url">http://www.sciencedirect.com/science/article/pii/S1877750311000603</identifier>
    <enrichment key="PeerReviewed">yes</enrichment>
    <author>Frank Dickmann</author>
    <author>Jürgen Falkner</author>
    <author>Wilfried Gunia</author>
    <author>Jochen Hampe</author>
    <author>Michael Hausmann</author>
    <author>Alexander Herrmann</author>
    <author>Nick Kepper</author>
    <author>Tobias Knoch</author>
    <author>Svenja Lauterbach</author>
    <author>Jörg Lippert</author>
    <author>Kathrin Peter</author>
    <author>Eberhard Schmitt</author>
    <author>Ulrich Schwardmann</author>
    <author>Juri Solodenko</author>
    <author>Dietmar Sommerfeld</author>
    <author>Thomas Steinke</author>
    <author>Anette Weisbecker</author>
    <author>Ulrich Sax</author>
    <collection role="institutes" number="vas">Distributed Algorithms and Supercomputing</collection>
    <collection role="persons" number="steinke">Steinke, Thomas</collection>
  </doc>
  <doc>
    <id>3407</id>
    <completedYear>2012</completedYear>
    <publishedYear>2012</publishedYear>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>conferenceobject</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>--</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">The MoSGrid Community – From National to International Scale</title>
    <parentTitle language="eng">EGI Community Forum 2012</parentTitle>
    <enrichment key="PeerReviewed">yes</enrichment>
    <author>Sandra Gesing</author>
    <author>Sonja Herres-Pawlis</author>
    <author>Georg Birkenheuer</author>
    <author>Andre Brinkmann</author>
    <author>Richard Grunzke</author>
    <author>Peter Kacsuk</author>
    <author>Oliver Kohlbacher</author>
    <author>Miklos Kozlovszky</author>
    <author>Jens Krüger</author>
    <author>Ralph Müller-Pfefferkorn</author>
    <author>Patrick Schäfer</author>
    <author>Thomas Steinke</author>
    <collection role="institutes" number="vas">Distributed Algorithms and Supercomputing</collection>
    <collection role="persons" number="patrick.schaefer">Schäfer, Patrick</collection>
    <collection role="persons" number="steinke">Steinke, Thomas</collection>
    <collection role="projects" number="2009-MosGrid">2009-MosGrid</collection>
  </doc>
</export-example>
