CUDA: Week in Review
Tuesday, Sept. 7, 2010, Issue #35 - Newsletter Home
Welcome to "CUDA: Week in Review," an online news summary for the worldwide CUDA and GPU Computing community. Follow us on Twitter: See previous issues:
T-Minus 12 Days!
GTC 2010 is the place to be on September 20-23. What should you expect? Four amazing days of GPU computing sessions, advanced technology tutorials, inspiring keynotes and collaborative networking, right in the heart of Silicon Valley. This is a one-of-a-kind opportunity to meet colleagues, peers, researchers, entrepreneurs and investors from around the world.

Here's what industry analyst Rob Enderle is saying about it:

"The GPU Technology Conference will have sessions covering advancements in artificial intelligence driven automobiles and robotics, because GPU computing is wonderful for AI. It will have sessions on advances in medical and modeling… and there will be examples of projects ranging from mapping the weather to exploring outer space that wouldn't have been completed had it not been for the introduction of GPU computing."

– For the session list, see:
– For keynote info, see: GTC blog post
– To register, go to: (code: GMCUDANEWS10)

Additional GTC info:
– Read VentureBeat's comments on the GTC Emerging Companies Summit:
– Read the Accelereyes blog highlighting "Jacketized" sessions at GTC:
CUDA for the Next Generation
NVIDIA Japan recently held a CUDA class in Tokyo. This event was especially noteworthy because it was for high school students! The participating students had an interest in GPU computing as well as a programming background. The distinguished guest speaker was Professor Takayuki Aoki of Tokyo Tech. The class was taught by Mr. Kei Tagwa of Fixstars. Steve Furney-Howe, Steven Zhang and Masaaki Sawai presented on behalf of NVIDIA.

Professor Aoki commented: "Supercomputers in the future will be powered by GPUs without any doubt… Younger people have already started using GPUs, thus they have a huge advantage." The class was sponsored by NVIDIA partners Fixstars, Acer, ELSA, Dell, Unitcom, DOSPARA and Mousecomputer.
New CUDA Training from CAPS
CAPS of Rennes, France, is offering a 3-day CUDA training class in late November. Participants will learn about the CUDA C programming model and how to handle multi-GPU applications. The training includes a hands-on lab. See:
SciComp Speeds up Monte Carlo with CUDA
SciComp of Austin, Texas, provides scientific computing solutions to the financial markets. Their Monte Carlo GPU code generation capabilities have been extended in the latest release of SciFinance, which supports CUDA 3.0 and the NVIDIA Tesla 20-Series. SciComp reports that "refinements have led to a further 30-50% performance increase in already very fast multi-factor Monte Carlo models." See SciComp's latest newsletter:
The website is a central site for GPU computing research. The organizers have started a new initiative called GPU Computing Research Forum, which will offer frequent Webex presentations (with live Q&A) from GPU researchers, users and vendors. The first one is on Sept. 15 and features NVIDIA's David Luebke. If you're interested in virtually presenting at this Forum (to introduce your lab, your project, call for solutions, etc.), contact Laurie Talkington at
CUDA Certification
– New certification program for GPU computing developers:
NVIDIA Parallel Nsight Webinar
– Debugging /Analyzing Graphics Apps with Parallel Nsight 1.0/Microsoft Visual Studio,
   Sept. 8, 9:30 am:
NVIDIA GPU Computing Webinars
– For info on all upcoming webinars, see:
Training from Acceleware
– Sept. 13-17, Calgary:
Training from EMPhotonics
– On-site training programs:
CUDA and Academia
Over 350 universities are teaching CUDA and GPU Computing courses around the world. Academic programs include:
CUDA Center of Excellence
CUDA Research Center
CUDA Teaching Center
Academic Partnership
– Learn more at
– Download CUDA 3.1 Toolkit:
– OpenCL v1.1 pre-release drivers and SDK code samples are available to GPU Computing
   registered developers. Log in or apply for an account to download.
September 2010

GPU Technology Conference (GTC) 2010 - Register today, space is limited
Sept. 20-23, San Jose, Calif.

Palo Open Conference: Business Intelligence Acceleration with GPUs
Sept. 30-Oct. 1, Frankfurt

MATLAB Conference 2010
Sept. 30, Wembley Stadium, London


Supercomputing 2010
Nov. 13-19, New Orleans, LA

IEEE International Parallel & Distributed Processing Symposium
May 16-20, 2011, Anchorage, AL

(To list an event, email:

CUDA Articles in Dr. Dobb's
– Supercomputing for the Masses, Part 19:
– Supercomputing for the Masses, Part 18:
– Supercomputing for the Masses, Part 17:
CUDA Books
– CUDA By Example by J. Sanders, E. Kandrot:
– Programming Massively Parallel Processors by D. Kirk, W. Hwu:
– See additional books here:
CUDA Documentation
– Download developer guides and documentation:
– See list of CUDA-enabled GPUs:
– Read previous issues of CUDA: Week in Review:
– Follow CUDA & GPU Computing on Twitter:
– Network with other developers:
– Stayed tuned to GPGPU news and events:
– Learn more about CUDA on CUDA Zone:
– Read Kudos for CUDA:
About CUDA
CUDA is NVIDIA’s parallel computing hardware architecture. NVIDIA provides a complete toolkit for programming on the CUDA architecture, supporting standard computing languages such as C, C++ and Fortran as well as APIs such as OpenCL and DirectCompute. Send comments and suggestions to:

Copyright © 2010 NVIDIA Corporation. All rights reserved. 2701 San Tomas Expressway, Santa Clara, CA 95050.