Path to Petascale: Adapting GEO/CHEM/ASTRO Applications for Accelerators and Accelerator Clusters

National Center for Supercomputing Applications GPU clusters
Galen Arnold, NCSA

Arctic Region Supercomputing Center Cell cluster
Anton Kulchitsky, ARSC

Laboratory for Computational Science and Engineering Cell cluster
Jagan Jayaraj and Pei-Hung Lin, University of Minnesota

Intro/overview of GPU-based accelerators and programming
Wen-mei Hwu

NVIDIA GPU technology roadmap, NVIDIA's CUDA programming ecosystem
Nathan Bell, NVIDIA

Experiences with multi-GPU acceleration in VMD
John Stone, University of Illinois at Urbana-Champaign

IBM Cell technology roadmap, IBM's Cell programming ecosystem
Vipin Sachdeva, IBM

Introduction/overview of Cell-based accelerators, programming models, and general application implementation considerations
Ben Bergen, Los Alamos National Lab

Cell programming seen through a fluid dynamics code example
Paul Woodward, University of Minnesota

PGI-GPU compiler
Michael Wolfe, The Portland Group, Inc.

Accelerating climate and weather simulations with Cell: Achievements and Lessons Learned
Shujia Zhou, NASA GSFC/Northrop Grumman

Development and Use of a Fortran -> CUDA translator to run a NOAA Global Weather Model on a GPU cluster
Mark Govett, NOAA Earth System Research Laboratory

Experience with NAMD on GPU-accelerated clusters
Jim Phillips, University of Illinois at Urbana-Champaign

Reverse acceleration: An alternative path to petascale programming
Scott Pakin, Los Alamos National Lab

Tree-based algorithms on GPUs
Matthew Knepley, University of Chicago

GPU CFD implementation
Jonathan Cohen, NVIDIA

Some optimization strategies for running weather codes efficiently on GPUs
Mark Govett, NOAA Earth System Research Laboratory

GPU implementation of multiphase lattice-Boltzmann simulations
Stuart Walsh, Department of Geology and Geophysics, the University of Minnesota

Modeling of Tsunami Equations and Atmospheric Swirling Flows with a Graphics Processing Unit (GPU) and Radial Basis Functions (RBF)
Jessica Schmidt, College of Saint Scholastica

Evaluating the Jaccard-Tanimoto Index on Multi-Core Architectures
Vipin Sachdeva, IBM Future Technology Solution Design Center

Quantum Monte Carlo on Graphical Processing Units
Amos Anderson, Caltech

Liouville-von Neumann Molecular Dynamics
Jacek Jakowski, Emerson Center for Scientific Computation and Department of Chemistry, Emory University

Two-Electron Integral Evaluation on FPGA, Cell and GPGPU accelerators
Guochun Shi, NCSA

Accelerating Cosmology codes
Robert Brunner, Department of Astronomy, University of Illinois at Urbana-Champaign

Solar wind properties at 1 AU, big time series analysis on the Cell cluster at ARSC
Anton Kulchitsky, Arctic Region Supercomputing Center, UAF

GPU acceleration of continuum quantum Monte Carlo Simulations
Ken Esler, NCSA

Real-time Registration of 3D Medical Images
Ramtin Shams, The Australian National University

Auto-tuning sparse matrix-vector "stencil" computations for GPUs
Chris Hill, MIT

Porting GENESIS (GENetic-Evolutionary Stokes Inversion Strategy) to NVIDIA's CUDA Architecture
Brian Harker-Lundberg and Kenneth Mighell, National Optical Astronomy Observatory

High-Performance Large Eddy Simulations (LES) of Turbulent Flows using Graphics Processing Units (GPUs)
Aaron Shinn and Pratap Vanka, University of Illinois at Urbana-Champaign

Visualization and Computational Steering of Level Sets on the GPU for Seismic Interpretation
Benjamin Kadlec, University Corporation for Atmospheric Research

Seismic Applications on Cell/B.E.
Mi Yan, IBM

Porting a high-order finite-element earthquake modeling application to NVIDIA graphics cards using CUDA
Gordon Erlebacher, Florida State University

Accelerating Kernels from WRF on GPUs
John Michalakes, NCAR

First principles calculations of large molecules on graphical processing units (GPU)
Ivan Ufimtsev, Stanford University

Uncontracted Rys Quadrature on GPU
Andrey Asadchev, Iowa State University

HOOMD: General purpose molecular dynamics on multiple GPUs implemented using CUDA
Joshua Anderson, Iowa State University

Roadrunner Universe project
Adrian Pope, Los Alamos National Lab

Supercomputing in the Outback: A GPU pipeline for the Murchison Widefield Array
Richard Edgar, Initiative in Innovative Computing (Harvard)

Accelerating the Computation of Theoretical Spectro-Polarimetric Signals: Comparative Analysis Using the Cell BE and NVIDIA GPU for Implementing the Voigt Function
Jose Garcia, NCAR

Solar Radiation Calculations on GPU Hardware
Rory Kelly, NCAR

Tsunami Wave Propagation Problems as studied with GPUs
Dave Yuen, Minnesota Supercomputing Institute, University of Minnesota

Parallel finite volume shallow water kernels on GPU hardware
Chris Hill, MIT

Dynamics, Radiation, Compilers, and the Cell
Shujia Zhou, NASA GSFC/Northrop Grumman

Sparse Matrix Vector Products on the GTX8800 GPU
Alistair Rendell, Australian National University

GPGPU for correlated quantum chemistry calculations
Alan Aspuru-Guzik, Harvard University

OpenMM: Molecular Dynamics Simulation on GPUs
Peter Eastman, Stanford University

What does the paradigm shift mean for large mature codes like FLASH
Anshu Dubey, University of Chicago

Developing a new cosmological n-body code for hybrid cell supercomputers
Adrian Pope, Los Alamos National Lab

Discussion