At SC09, NVIDIA® (booth# 2365) will be showcasing the breadth of NVIDIA® CUDA™-based GPU computing solutions that are powering the next wave of HPC. We invite you to visit our booth and learn more about the latest from NVIDIA® Tesla® GPU computing solutions.
NVIDIA GPU Computing Theater
Tuesday, November 17 – Thursday November 19 | NVIDIA Booth # 2365
The theater featured talks given by experts on a wide range of topics on high performance computing. Open to all attendees, the theater is located in the NVIDIA booth and will feature scientists, developers, and industry luminaries including:
- Mike Clark, Harvard University
- Paul Crozier, Sandia National Laboratories
- Bill Dally, NVIDIA
- Jack Dongarra, University of Tennessee
- Satoshi Matsuoka, Tokyo Institute of Technology
- Pat McCormick, Los Alamos National Laboratory
- John Stone, University of Illinois at Urbana-Champaign
- Jeff Vetter, Oak Ridge National Laboratory
- Ross Walker, San Diego Supercomputing Center, UCSD
Click here to view streamed recordings and download the talks from the NVIDIA GPU Computing Theater.
NVIDIA GPU Computing Poster Showcase
Monday, November 16 | 7:00 PM – 9:00 PM | NVIDIA Booth # 2365
See "what’s next" out of the world of research and academia with over 80 posters featured.
Click here for the complete list of posters.
Tutorial: High Performance Computing with CUDA
Sunday, November 15 | 8:30 AM – 5:00 PM | Oregon Ballroom 204
In this tutorial NVIDIA engineers will partner with academic and industrial researchers to present CUDA and discuss its advanced use for science and engineering domains. The morning session will introduce CUDA programming, motivate its use with many brief examples from different HPC domains, and discuss tools and programming environments. The afternoon will discuss advanced issues such as optimization and sophisticated algorithms/data structures, closing with real-world case studies from domain scientists using CUDA for computational biophysics, fluid dynamics, seismic imaging, and theoretical physics.
To view or download PDF copies of the tutorial presentations click here.
NVIDIA SESSIONS AT SC09
Tutorial: GPU Programming with the PGI Accelerator Programming Model and with PGI CUDA Fortran
Monday, November 16 | 8:30 AM – 5:30 PM | 1 N. Center Court St., Portland, OR
A full-day training course hosted by The Portland Group, with a complementary single-seat node-locked license of PGI Accelerator Fortran/C/C++ compilers and tools with PGI CUDA Fortran. Please visit the tutorial page for more details.
Tutorial: OpenCL - A Standard Platform for Programming Heterogeneous Parallel Computers
Monday, November 16 | 1:30 PM – 5:00 PM | Oregon Ballroom 204
This session will cover the specification explaining the key features and how to use them to write HPC software, then provide a series of case studies to show how OpenCL is used in practice. By the conclusion of the tutorial, attendees should be able to start writing complex scientific computing applications on their own using OpenCL.
Papers Session: Implementing Sparse Matrix-Vetor Multiplication on Throughput-Oriented Processors
Tuesday, November 17 | 2:00 PM – 2:30 PM | Room PB252
In this session, we explore SpMV methods that are well-suited to throughput-oriented architectures like the GPU and which exploit several common sparsity classes.
Panel: Teach Parallel Panel in the SC education program
Tuesday, November 17 | 5:30 PM – 6:30 PM | Room C124
Birds of a Feather Session: The Art of Performance Tuning for CUDA and Manycore Architectures
Tuesday, November 17 | 5:30 PM – 7:00 PM | Room E141-142
This session will explore the art of performance tuning for CUDA. Topics will include profiling to identify bottlenecks, effective use of the GPU's memory hierarchy and DRAM interface to maximize bandwidth, data versus task parallelism, avoiding branch divergence, and effective use of native hardware functionality such as transcendentals and synchronization primitives to optimize CPU utilization.
Birds of a Feather Session: Practical HPC Considerations for Advanced CFD
Wednesday, November 18 | 12:15 PM – 1:15 PM | Room E141-142
This BOF will examine the current state of parallel CFD for HPC cluster environments at industry-scale. BOF panel members will comprise parallel CFD experts from commercial CFD software developers ANSYS and CD-adapco, and HPC practitioners from industry who deploy both commercial and research-developed CFD application software.
Panel: Preparing the World of Ubiquitous Parallelism
Friday, November 20 | 10:30 AM – 12:00 PM | Room PB252