CUDA: Week in Review
Friday, March 26, 2010, Issue #14 - Newsletter Home  
Welcome to this week’s issue of "CUDA: Week in Review," a weekly newsletter for the worldwide CUDA and GPU Computing community. Contact us at:
Tokyo Institute of Technology Accelerates Weather Forecasting with GPUs
A research group led by Professor Takayuki Aoki at the Tokyo Institute of Technology is utilizing GPUs to accelerate a next-generation weather forecasting model called ASUCA. This model is being developed by the Japan Meteorological Agency. In a nutshell, ASUCA enables fast and sophisticated simulation of meteorological phenomena such as cloud formations. The research group has achieved an 80X performance increase on the NVIDIA Tesla GPU-based TSUBAME supercomputer. Development is being done in CUDA C, incorporating custom acceleration algorithms and optimization methods. The speed and accuracy of weather predictions have major implications for more efficient and effective planning and resource allocation. Results were presented this week at "Next-Generation Models for Climate Change," an international symposium in Tuskuba, Japan. See:
GPU Technology Conference 2010 Announced
NVIDIA announced that the next GPU Technology Conference (GTC) will take place on Sept. 20-23, 2010 in San Jose, Calif. Building on last year’s inaugural conference, GTC 2010 will feature an even broader and deeper selection of technical sessions, tutorials, technology previews, and industry and academic presentations. Three concurrent GPU-focused summits will take place under one roof:
Emerging Companies Summit, GPU Developers Summit, and NVIDIA Research Summit.
– More GTC 2010 info:
– Sign up for GTC 2010 updates:
– See Bill Dally, NVIDA Chief Scientist, discuss GTC 2010:
Palix Launches CFD Beta Program
Palix Technologies introduced a Computational Fluid Dynamics (CFD) product called ANDSolver, designed from the ground up to use GPUs for fast, efficient aerodynamic analysis. Palix comments that "the trend towards using GPUs for computation promises faster results with lower hardware acquisition and operating costs." ANDSolver delivers up to a 10X speedup compared to a typical quad core CPU.
– More info on Palix:
– White paper:
New on CUDA Zone: Accelerating SQL Database Operations on a GPU with CUDA
Submission extract: "Prior work has shown dramatic acceleration for various database operations on GPUs, but only using primitives that are not part of conventional database languages such as SQL. This paper implements a subset of the SQLite command processor directly on the GPU… [It] focuses on accelerating SELECT queries and describes the considerations in an efficient GPU implementation of the SQLite command processor. Results on an NVIDIA Tesla C1060 achieve speedups of 20-70X depending on the size of the result set." The source code will be released as a package in April. Authors: Peter Bakkum, Kevin Skadron; University of Virginia. See:
Submit Your Work
Have a CUDA-related paper or research? Show it on CUDA Zone:
The Harvard-Smithsonian Center for Astrophysics is accepting applications for a predoctoral project in radio astronomy with a strong emphasis on GPU computing. The project involves studies of the early universe, the sun, and pulsars with next generation radio telescope arrays - such as the Murchison Widefield Array (MWA) - utilizing computationally intensive radio astronomy on GPUs. Note: MWA is an advanced radio telescope array under construction in the remote Western Australia Outback.
– See posting here:
– See more CUDA/GPU computing jobs here:
CUDA Education
Acceleware-Certified CUDA Training
NEW: Silicon Valley, May 19-20:
Calgary, April 12-16:
Call for Papers
NEW: 3rd Workshop on UnConventional High Performance Computing 2010 (UCHPC 2010), Aug. 31-Sept. 1, Naples, Italy (with Euro-Par 2010). Submission deadline: June 14. See:

Symposium on Chemical Computations on GPGPUs, Aug. 22-26, Boston. Abstracts due April 5. Best paper wins an NVIDIA Tesla C2050. See:
Chemistry and Materials Science Symposium
Symposium on Applications of GPUs in Chemistry and Materials Science, June 28-30, University of Pittsburgh. See:
GPU Computing Webinars (CUDA C and OpenCL)
See schedule:
CUDA and GPU Computing Courses
Over 320 universities are teaching CUDA and GPU Computing courses. See the list:
– CUDA Videos on YouTube:
– CUDA Toolkit:
– Developer Guides:
– Programming Massively Parallel Processors, by D. Kirk, W. Hwu:
– Follow CUDA & GPU Computing on Twitter:
– Network with other developers:
– Stayed tuned to GPGPU news and events:
– Learn more about CUDA on CUDA Zone:
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.

See previous issues of CUDA: Week in Review:

Send comments and suggestions to:
You are receiving this email because you have previously expressed interest in NVIDIA products and technologies. Click here to opt in specifically to CUDA: Week in Review.

Feel free to forward this email to customers, partners and colleagues.

2701 San Tomas Expressway, Santa Clara, CA 95050

Copyright © 2010 NVIDIA Corporation. All rights reserved.