<?xml version="1.0" encoding="utf-8"?>
<export-example>
  <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>5036</id>
    <completedYear/>
    <publishedYear/>
    <thesisYearAccepted/>
    <language>eng</language>
    <pageFirst/>
    <pageLast/>
    <pageNumber/>
    <edition/>
    <issue/>
    <volume/>
    <type>reportzib</type>
    <publisherName/>
    <publisherPlace/>
    <creatingCorporation/>
    <contributingCorporation/>
    <belongsToBibliography>0</belongsToBibliography>
    <completedDate>--</completedDate>
    <publishedDate>2014-02-06</publishedDate>
    <thesisDateAccepted>--</thesisDateAccepted>
    <title language="eng">Multi-threaded Kernel Offloading to GPGPU Using Hyper-Q on Kepler Architecture</title>
    <abstract language="eng">Small-scale computations usually cannot fully utilize the compute capabilities of modern GPGPUs. With the Fermi GPU architecture Nvidia introduced the concurrent kernel execution feature allowing up to 16 GPU kernels to execute simultaneously on a shared GPU device for a better utilization of the respective resources. Insufficient scheduling capabilities in this respect, however, can significantly reduce the theoretical concurrency level. With the Kepler GPU architecture Nvidia addresses this issue by introducing the Hyper-Q feature with 32 hardware managed work queues for concurrent kernel execution.&#13;
We investigate the Hyper-Q feature within heterogeneous workloads with multiple concurrent host threads or processes offloading computations to the GPU each.&#13;
By means of a synthetic benchmark kernel and a hybrid parallel CPU-GPU real-world application, we evaluate the performance obtained with Hyper-Q on GPU and compare it against a kernel reordering mechanism introduced by the authors for the Fermi architecture.</abstract>
    <identifier type="issn">1438-0064</identifier>
    <identifier type="urn">urn:nbn:de:0297-zib-50362</identifier>
    <author>Florian Wende</author>
    <submitter>Florian Wende</submitter>
    <author>Thomas Steinke</author>
    <author>Frank Cordes</author>
    <series>
      <title>ZIB-Report</title>
      <number>14-19</number>
    </series>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>GPGPU</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Hyper-Q</value>
    </subject>
    <subject>
      <language>eng</language>
      <type>uncontrolled</type>
      <value>Concurrent Kernel Execution</value>
    </subject>
    <collection role="ccs" number="B.">Hardware</collection>
    <collection role="pacs" number="80.00.00">INTERDISCIPLINARY PHYSICS AND RELATED AREAS OF SCIENCE AND TECHNOLOGY</collection>
    <collection role="msc" number="00-XX">GENERAL</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/5036/ZR-14-19.pdf</file>
  </doc>
</export-example>
