CUDA: Week in Review
Friday, April 16, 2010, Issue #17 - 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:
GTC 2010 - Call for Submissions
The GPU Technology Conference (GTC) 2010 will be held Sept. 20-23, 2010 in San Jose, Calif. Developers, researchers, scientists, and entrepreneurs from around the world are cordially invited to submit session proposals and research posters related to the GPU ecosystem. GTC 2010 is also accepting nominations for "CEO on Stage," an opportunity for CEOs of startups and emerging companies in the GPGPU/GPU Computing field to present to analysts and attendees.
– For GTC 2010 submissions info, see:
– For GTC 2010 general info, see:
Update from Las Vegas
The National Association of Broadcasters (NAB) show was held this week in Las Vegas. NVIDIA was there in full force to demonstrate new technology for 3D broadcasting leveraging the Quadro Digital Video Pipeline. This year, many exhibitors at NAB showed CUDA-accelerated products:
Adobe’s newly-announced Premiere Pro CS5 with the Mercury Playback Engine was
   developed on the CUDA architecture and is accelerated by NVIDIA GPUs. (See a good
   video on Premiere Pro CS5 here:

ARRI, a manufacturer of professional motion picture cameras and accessories, utilizes
   CUDA GPUs for real-time image decoding.
ASSIMILATE’s SCRATCH v5.1 digital process solution supports CUDA-based plug-ins.
   SCRATCH is a real-time, end-to-end pipeline for pre-and post-production.
BlackMagic’s Davinci Resolve color grading system uses CUDA as the foundation of
   its CUDA Optimized Resolve Engine (CORE).
MainConcept provides high-quality video/audio codec solutions for leading developers
   of multimedia applications. Their new CUDA H.264/AVC Encoder SDK beta delivers
   tremendous performance advantages over the CPU and is the first and only
   GPU-accelerated tool available to developers.
– Read more about NVIDIA Quadro and CUDA at NAB here and here.
New on CUDA Zone: Palo GPU from Jedox
Overview: "With Palo GPU, it is now possible to load databases into the memory of a GPU. GPUs are optimized for parallel calculations of values and are therefore ideally suited for fast processing of complex queries, such as those encountered in typical business intelligence applications. The more complicated the calculations are, the higher the performance gain over conventional processors (CPUs). Palo GPU was developed in cooperation with researchers from the University of Freiburg and the University of Western Australia, and co-funded by the German Research Foundation (DFG) and Jedox." See:
CUDA Zone Submissions
Have a CUDA-related pape, research, or application? Show it on CUDA Zone:
BAE Systems is looking for a GPGPU digital engineer to work on real-time embedded applications related to ground and airborne remote sensing systems. The ideal candidate will be proficient in all aspects of GPGPU system design and have significant experience with GPGPU programming in one or more of the following domains: remote sensing, parallel processing, digital signal processing, image processing, or computer vision. Requirements include demonstrated experience using debugging and profiling tools for CUDA/OpenCL programs and performance analysis of hybrid CPU/GPGPU programs. See:
Parallel Nsight Open Beta
NVIDIA announced the start of an open Beta program for Parallel Nsight this week at the Microsoft Visual Studio Conference and Expo. Sign up here:
EM Photonics’ CULA is a GPU-accelerated linear algebra library that utilizes CUDA to improve the computation speed of sophisticated mathematics. The library comes with the LAPACK (Linear Algebra PACKage) interface and MATLAB integration and achieves speedups from 2X to 4X over the Intel Math Kernel Library (MKL) LAPACK implementation. Download CULA Tools here:
Tokyo Tech Videos
In last week’s issue, we announced that Tokyo Tech was named Japan’s first CUDA Center of Excellence. As a follow up, here are links to some interesting Tokyo Tech videos:
– Prof. Satoshi Matsuoka speaks about TSUBAME 1.2:
– Aoki Laboratory Gallery:
CUDA Education
GPU Computing Webinars (CUDA C, OpenCL, Parallel Nsight and more…)
See schedule:
Acceleware-Certified CUDA Training
Silicon Valley, May 19-20:
GPGPU Conferences and Symposia
– GPU Computing in the Oil & Gas Industry (Microsoft/NVIDIA), May 12, Houston:
– GPUs in Chemistry and Materials Science, June 28-30, Univ. of Pittsburgh:
– Parallel Symbolic Computation 2010 (PASCO), July 21-23, France:
– Symposium on Chemical Computations on GPGPUs, Aug. 22-26, Boston:
– UnConventional High Performance Computing 2010 (UCHPC 2010), Aug. 31-Sept. 1, Italy:
– GPU Technology Conference 2010, Sept. 20-23, San Jose, Calif.:
CUDA and GPU Computing Courses
Over 320 universities are teaching CUDA and GPU Computing courses. See the list:
CUDA Books
"Programming Massively Parallel Processors," by Dr. David B. Kirk and Dr. Wen-mei Hwu.
– Available on
– Download CUDA Toolkit 3.0:
– Download Developer Guides:
– Follow CUDA & GPU Computing on Twitter:
– Network with other developers:
– Stayed tuned to GPGPU news and events:
– Learn more about CUDA on CUDA Zone:
– CUDA on YouTube:
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.

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