High Performance GPU Computing with NVIDIA, CUDA, and Fermi:
A workshop and discussion forum
Thursday 15 July 2010
9:15-15:30
N101, Ground Floor, Computer Science and Information Technology Building 108, ANU
Presented by
Mark Harris (NVIDIA) withDragan Dimitrovici (Xenon Systems),
John Taylor (CSIRO),
Eric McCreath (ANU College of Engineering and Computer Science), and
Joseph Antony (NCI).
The workshop is free, but please email Eric.McCreath@anu.edu.au for catering purposes. (We have capacity for at most 50 attendees.)
Talk Slides
Mark's slides are available for download :
Abstract:
CUDA is a parallel computing architecture and programming environment from NVIDIA that enables dramatic increases in computing performance by harnessing the power of the GPU (graphics processing unit).Computing is evolving from "central processing" on the CPU to "co-processing" on the CPU and GPU. To enable this new computing paradigm, NVIDIA invented the CUDA parallel computing architecture. With over 100 million CUDA-enabled GPUs sold to date, software developers, scientists and researchers are finding broad-ranging uses for CUDA, including image and video processing, computational biology and chemistry, fluid dynamics simulation, CT image reconstruction, seismic analysis, financial computing, ray tracing, and much more.
The latest CUDA-enabled GPU architecture from NVIDIA, code-named "Fermi", is now available in the form of the Tesla 20 series GPU computing solutions, which support many “must have” features for technical and enterprise computing. These include ECC memory for uncompromised accuracy and scalability, support for C++ and 8x the double precision performance compared to Tesla 10-series GPU computing products. NVIDIA Tesla GPUs are being used in 100s of clusters and data centers around the world, including the Nebulae cluster, currently the 2nd fastest supercomputer in the world.
In this workshop you will learn about CUDA, the Fermi architecture, and Tesla GPU Computing products. You will learn about the basics of programming GPUs using CUDA C and C++, the variety of available computational libraries for CUDA, tools for profiling and debugging CUDA applications, and approaches for optimizing CUDA parallel applications. You will also learn about CUDA-enabled desktop, workstation, and cluster computing solutions provided by Xenon Systems. The workshop will also include brief presentations on some of the ways these technologies have been used at CSIRO, NCI, and the ANU College of Engineering and Computer Science.
Agenda
| 9:15 | Arrival and Registration |
| 9:30 | Eric McCreath - Welcome and Introduction |
| 9:45 | Mark Harris - Introduction to NVIDIA CUDA, Tesla, and the Fermi Architecture |
| 10:30 | Tea Break |
| 10:50 | Dragan Dimitrovici - CUDA-enabled Hardware Options from Xenon Systems |
| 11:10 | Joseph Antony - NCI |
| 11:30 | Mark Harris - CUDA Parallel Programming Model and Live CUDA Programming Demo |
| 12:30 | Lunch |
| 1:10 | Mark Harris - CUDA Debugging and Profiling Tools |
| 1:40 | Eric McCreath & Fang Zhou Xiao - A Machine Learning Application |
| 2:00 |
Mark Harris - Optimizing Performance on NVIDIA GPUs Future Directions, Q & A. |
| 3:10 | John Taylor - GPU's at CSIRO |
| 3:30 | Eric McCreath - Close |
Bio: Mark Harris
Mark Harris is a Senior Developer Technology Engineer at NVIDIA, where he works with developers around the world on software for high-performance computing and computer graphics. His research interests include parallel computing, general-purpose computation on GPUs,physically based simulation, real-time rendering, and gastronomy. Mark earned his Ph.D.in computer science from the University of North Carolina at Chapel Hill in 2003 and his B.S. from the University of Notre Dame in 1998. Mark founded and maintains GPGPU.org, a web site dedicated to general-purpose computation on GPUs. Mark has recently moved to Australia after living in the United Kingdom for five years.
Bio: Dragan Dimitrovici
Dragan Dimitrovici is the Founder and driving force of the XENON Technology Group. He founded the company in 1996 at the age of 21, when he recognised the opportunity to sell locally assembled computer hardware. The XENON Technology Group (XTG) which consists of of XENON systems, Mediaproxy and XDT develops mission critical solutions for new & emerging markets within the Defence, Scientific Research, Broadcast, film & Education industry. Its solutions are tailored to individual customer requirements. Each year XTG invest heavily in research and partners with world class Vendors including NVIDIA, Supermicro,Mellanox, ScaleMP, Adaptec, Accelereyes (Jacket for Matlab) & Microsoft. Dragan studied Information Management at Melbourne University and is a certified Intel Server Integration Specialist. In 2006, Dragan was an Ernst & Young, Entrepreneur of the year finalist.
Bio: John Taylor
Dr. John Taylor is the science and business leader for Computational and Simulation Sciences at CSIRO. Dr. Taylor has written more than 140 articles and books on computational and simulation science and its application to such areas as climate change, global biogeochemical cycles, air quality, and environmental policy. John's research has addressed local and global scientific and environmental policy issues. He spent more than 10 years working in the United States as a computational scientist in Mathematics and Computer Science Division at Argonne National Laboratory, where he also held appointments as a senior fellow at both the Computation Institute and the Environment Center at the University of Chicago. John was also a physicist and group leader at Lawrence Livermore National Laboratory and was Professor and the Director of the Doctoral Program in Environmental Management at Montclair State University.
Bio: Eric McCreath
Eric McCreath completed his Ph.D. degree in 1999 from the University of New South Wales. This was on research involving Inductive Logic Programming (ILP) which is a sub-field of Machine Learning. He joined the Basser Department of Computer Science (now the School of Information Technologies) at Sydney University in 1999 as a lecturer and then in 2001 he moved to the Australian National University. Dr McCreath currently holds a lecturing position at the ANU and is pursuing research in the Computer Systems research group. Eric has a particular interest in novel architectures such as: FPGAs, the Cell processor, and GPUs and their application to computational tasks.
