High Performance Computing for Computational Science - VECPAR 2012

1. Front Matter

   PDF

2. Invited Presentations

   1. Barriers to Exascale Computing

      • Horst D. Simon

      Pages 1-3

   2. Toward a Theory of Algorithm-Architecture Co-design

      • Richard Vuduc, Kenneth Czechowski

      Pages 4-8

   3. Visualization of Strong Ground Motion from the 2011 Off Tohoku, Japan (Mw=9.0) Earthquake Obtained from Dense Nation-Wide Seismic Network and Large-Scale Parallel FDM Simulation

      • Takashi Furumura

      Pages 9-16

   4. Grand Challenge in Life Science on K Computer

      • Ryutaro Himeno

      Pages 17-22

   5. HPC/PF - High Performance Computing Platform: An Environment That Accelerates Large-Scale Simulations

      • Kenji Ono, Tomohiro Kawanabe, Toshio Hatada

      Pages 23-27

3. GPU Computing

   1. Programming the LU Factorization for a Multicore System with Accelerators

      • Jakub Kurzak, Piotr Luszczek, Mathieu Faverge, Jack Dongarra

      Pages 28-35

   2. Efficient Two-Level Preconditioned Conjugate Gradient Method on the GPU

      • Rohit Gupta, Martin B. van Gijzen, Cornelis Kees Vuik

      Pages 36-49

   3. Parallelization of the QR Decomposition with Column Pivoting Using Column Cyclic Distribution on Multicore and GPU Processors

      • Andrés Tomás, Zhaojun Bai, Vicente Hernández

      Pages 50-58

   4. A High Performance SYMV Kernel on a Fermi-core GPU

      • Toshiyuki Imamura, Susumu Yamada, Masahiko Machida

      Pages 59-71

   5. Optimizing Memory-Bound SYMV Kernel on GPU Hardware Accelerators

      • Ahmad Abdelfattah, Jack Dongarra, David Keyes, Hatem Ltaief

      Pages 72-79

4. Applications

   1. Numerical Simulation of Long-Term Fate of CO2 Stored in Deep Reservoir Rocks on Massively Parallel Vector Supercomputer

      • Hajime Yamamoto, Shinichi Nanai, Keni Zhang, Pascal Audigane, Christophe Chiaberge, Ryusei Ogata et al.

      Pages 80-92

   2. High Performance Simulation of Complicated Fluid Flow in 3D Fractured Porous Media with Permeable Material Matrix Using LBM

      • Jinfang Gao, H. L. Xing

      Pages 93-104

   3. Parallel Scalability Enhancements of Seismic Response and Evacuation Simulations of Integrated Earthquake Simulator

      • M. L. L. Wijerathne, Muneo Hori, Tsuyoshi Ichimura, Seizo Tanaka

      Pages 105-117

   4. QMC=Chem: A Quantum Monte Carlo Program for Large-Scale Simulations in Chemistry at the Petascale Level and beyond

      • Anthony Scemama, Michel Caffarel, Emmanuel Oseret, William Jalby

      Pages 118-127

5. Finite Element Method from Various Viewpoints

   1. Optimizing Sparse Matrix Assembly in Finite Element Solvers with One-Sided Communication

      • Niclas Jansson

      Pages 128-139

   2. Implementation and Evaluation of 3D Finite Element Method Application for CUDA

      • Satoshi Ohshima, Masae Hayashi, Takahiro Katagiri, Kengo Nakajima

      Pages 140-148

   3. Evaluation of Two Parallel Finite Element Implementations of the Time-Dependent Advection Diffusion Problem: GPU versus Cluster Considering Time and Energy Consumption

      • Alberto F. De Souza, Lucas Veronese, Leonardo M. Lima, Claudine Badue, Lucia Catabriga

      Pages 149-162

6. Cloud and Visualization

   1. A Service-Oriented Architecture for Scientific Computing on Cloud Infrastructures

      • Germán Moltó, Amanda Calatrava, Vicente Hernández

      Pages 163-176

   2. Interactive Volume Rendering Based on Ray-Casting for Multi-core Architectures

      • Alexandre S. Nery, Nadia Nedjah, Felipe M. G. França, Lech Jozwiak

      Pages 177-186

This book constitutes the thoroughly refereed post-conference proceedings of the 10th International Conference on High Performance Computing for Computational Science, VECPAR 2012, held in Kope, Japan, in July 2012. The 28 papers presented together with 7 invited talks were carefully selected during two rounds of reviewing and revision. The papers are organized in topical sections on CPU computing, applications, finite element method from various viewpoints, cloud and visualization performance, method and tools for advanced scientific computing, algorithms and data analysis, parallel iterative solvers on multicore architectures.

• data intensive computing
• distributed computing
• numerical algorithms
• performance analysis
• simulations
• algorithm analysis and problem complexity

• INPT (ENSEEIHT) - IRIT, University of Toulouse, Toulouse, France

  Michel Daydé

• Lawrence Berkeley National Laboratory, Berkeley, USA

  Osni Marques

• Information Technology Center, The University of Tokyo, Tokyo, Japan

  Kengo Nakajima

Policies and ethics