Supercomputing

1. Front Matter

   PDF

2. 591 TFLOPS Multi-trillion Particles Simulation on SuperMUC

   • Wolfgang Eckhardt, Alexander Heinecke, Reinhold Bader, Matthias Brehm, Nicolay Hammer, Herbert Huber et al.

   Pages 1-12

3. Up to 700k GPU Cores, Kepler, and the Exascale Future for Simulations of Star Clusters Around Black Holes

   • Peter Berczik, Rainer Spurzem, Shiyan Zhong, Long Wang, Keigo Nitadori, Tsuyoshi Hamada et al.

   Pages 13-25

4. Parallelizing a High-Order CFD Software for 3D, Multi-block, Structural Grids on the TianHe-1A Supercomputer

   • Chuanfu Xu, Xiaogang Deng, Lilun Zhang, Yi Jiang, Wei Cao, Jianbin Fang et al.

   Pages 26-39

5. Lattice QCD on Intel® Xeon PhiTM Coprocessors

   • Bálint Joó, Dhiraj D. Kalamkar, Karthikeyan Vaidyanathan, Mikhail Smelyanskiy, Kiran Pamnany, Victor W. Lee et al.

   Pages 40-54

6. Towards Addressing CPU-Intensive Seismological Applications in Europe

   • Michele Carpené, Iraklis A. Klampanos, Siew Hoon Leong, Emanuele Casarotti, Peter Danecek, Graziella Ferini et al.

   Pages 55-66

7. Leading Edge Hybrid Multi-GPU Algorithms for Generalized Eigenproblems in Electronic Structure Calculations

   • Azzam Haidar, Raffaele Solcà, Mark Gates, Stanimire Tomov, Thomas Schulthess, Jack Dongarra

   Pages 67-80

8. Heterogeneous Programming and Optimization of Gyrokinetic Toroidal Code and Large-Scale Performance Test on TH-1A

   • Xiangfei Meng, Xiaoqian Zhu, Peng Wang, Yang Zhao, Xin Liu, Bao Zhang et al.

   Pages 81-96

9. Achieving Efficient Strong Scaling with PETSc Using Hybrid MPI/OpenMP Optimisation

   • Michael Lange, Gerard Gorman, Michèle Weiland, Lawrence Mitchell, James Southern

   Pages 97-108

10. Designing Scalable Graph500 Benchmark with Hybrid MPI+OpenSHMEM Programming Models

    • Jithin Jose, Sreeram Potluri, Karen Tomko, Dhabaleswar K. Panda

    Pages 109-124

11. On the GPU Performance of 3D Stencil Computations Implemented in OpenCL

    • Huayou Su, Nan Wu, Mei Wen, Chunyuan Zhang, Xing Cai

    Pages 125-135

12. Improving Performance Portability in OpenCL Programs

    • Yao Zhang, Mark Sinclair II, Andrew A. Chien

    Pages 136-150

13. Auto-tuning of Sparse Matrix-Vector Multiplication on Graphics Processors

    • Walid Abu-Sufah, Asma Abdel Karim

    Pages 151-164

14. A Simple Concept for the Performance Analysis of Cluster-Computing

    • Heinz Kredel, Sabine Richling, Jan Philipp Kruse, Erich Strohmaier, Hans-Günther Kruse

    Pages 165-180

15. Using Simulation to Validate Performance of MPI(-IO) Implementations

    • Julian Martin Kunkel

    Pages 181-195

16. Software Design Space Exploration for Exascale Combustion Co-design

    • Cy Chan, Didem Unat, Michael Lijewski, Weiqun Zhang, John Bell, John Shalf

    Pages 196-212

17. Beyond the CPU: Hardware Performance Counter Monitoring on Blue Gene/Q

    • Heike McCraw, Dan Terpstra, Jack Dongarra, Kris Davis, Roy Musselman

    Pages 213-225

18. Maximizing Application Performance in a Multi-core, NUMA-Aware Compute Cluster by Multi-level Tuning

    • Gilad Shainer, Pak Lui, Martin Hilgeman, Jeffrey Layton, Cydney Stevens, Walker Stemple et al.

    Pages 226-238

19. Offload Compiler Runtime for the Intel® Xeon PhiTM Coprocessor

    • Chris J. Newburn, Rajiv Deodhar, Serguei Dmitriev, Ravi Murty, Ravi Narayanaswamy, John Wiegert et al.

    Pages 239-254

20. Fork-Join and Data-Driven Execution Models on Multi-core Architectures: Case Study of the FMM

    • Abdelhalim Amer, Naoya Maruyama, Miquel Pericàs, Kenjiro Taura, Rio Yokota, Satoshi Matsuoka

    Pages 255-266

This book constitutes the refereed proceedings of the 28th International Supercomputing Conference, ISC 2013, held in Leipzig, Germany, in June 2013. The 35 revised full papers presented together were carefully reviewed and selected from 89 submissions. The papers cover the following topics: scalable applications with 50K+ cores; performance improvements in algorithms; accelerators; performance analysis and optimization; library development; administration and management of supercomputers; energy efficiency; parallel I/O; grid and cloud.

• GPU performance
• computer clusters
• exascale supercomputers
• high-performance computing
• simulation

• University of Hamburg, Department of Informatics, Hamburg, Germany

  Julian Martin Kunkel

• Deutsches Klimarechenzentrum, Hamburg, Germany

  Thomas Ludwig

• Germany and Prometeus GmbH, University of Mannheim, Waibstadt, Germany

  Hans Werner Meuer

Policies and ethics