CUDA Week in Review Newsletter Homepage
Fri., Sept. 28, 2012, Issue #80 - Newsletter Home  
Welcome to CUDA: WEEK IN REVIEW, a news summary for the worldwide CUDA, GPGPU and parallel programming community.
CUDA TECH TIP: Do you require pseudo-random numbers with standard distribution? If so, the Box-Muller algorithm can be efficiently implemented using the new sincospi() function in CUDA 5.0. See example below.
GTC 2013: The GTC Call for Submissions deadline is Oct. 3. NVIDIA is soliciting submissions in four categories: GPU Computing; Cloud Computing; Computer Graphics; and Game Development.


GPUs and Molecular Dynamics
This week’s Spotlight is on Dr. Erik Lindahl of KTH Royal Institute of Technology and Stockholm University. Erik is a founding project leader for GROMACS, a popular open-source molecular dynamics program. Read our interview here. Sign up to try GROMACS on a remotely-hosted GPU cluster here.

Dr. Erik Lindahl


London Seminar on GPU Acceleration in Bioinformatics
The Institute of Cancer Research in London is holding a first-of-its-kind seminar on GPUs and Bioinformatics on Oct. 9. Members of the public are welcome to attend. The agenda includes:
   • SOAP3-dp: GPU-based Dynamic Programming Tool for Short Read Alignment
      • by Ruibang Luo, Univ. of Hong Kong
   • Using GPUs to Single Out Functional Signals Within Regulatory Regions of Genes
      • by Oleg Vishnevsky, Russian Academy of Sciences
   • GPUs for Biologists: Optimized Algorithms in UGENE Bioinformatics Toolkit
      • by Yuri Vaskin, UNIPRO

HPCwire Readers Choice Awards
Last call to cast votes for top influencers in high-performance computing. Winners will be announced at SC12 in November.

The website GPUScience recently wrote about CUDAfy, a set of libraries and tools for programming GPUs within the Microsoft .NET framework. The post refers to an interesting article by John Michael Hauck on how to transfer CPU code to the GPU using the Traveling Salesman problem as an example.

Univ. of Missouri Earns Award at ACM Symposium in Delft
A team led by Michela Becchi, University of Missouri, won the Best Paper Award at the ACM Symposium on High-Performance Parallel and Distributed Computing (HPDC 12). Becchi’s paper is titled: “A Virtual Memory-Based Runtime to Support Multi-Tenancy in Clusters with GPUs.”

AccelerEyes Case Studies
Two new GPU case studies from AccelerEyes are now online:
SAR Image Formation Algorithms on the GPU | Signal Processing with Jacket

Nsight Visual Studio Edition Update
A refresh of NVIDIA Nsight Visual Studio Edition is available at

GPU Computing on Twitter
For daily updates about GPU computing and parallel programming, follow @gpucomputing on Twitter.

CUDA Consulting
Training, programming, and project development services are available from CUDA consultants around the world. To be considered for inclusion on list, email: (with CUDA Consulting in subject line).


At SC12, NVIDIA will highlight CUDA stories from around the world. If you are a CUDA developer, tell us how you are using CUDA in 140 characters or less. Your submission, along with your name and organization, will be considered for display in the NVIDIA booth. Here’s an example: "I use CUDA to accelerate reverse time migration algorithms for energy exploration research. Simulations that took a week now take a day." Respond by Oct. 10 at


Congrats to Tyson Lipscomb, Wake Forest University, on his dissertation titled "GPU-Optimized Molecular Dynamics Simulations." Advisor: Samuel S. Cho. Degree: Computer Science MS.


NVIDIA is seeking an exceptional CUDA System Software Development Manager to lead a team of world-class developers delivering CUDA driver and runtime software. Position is based in Santa Clara, Calif. See: (Job #1508447)


Do you require pseudo-random numbers with standard distribution? For efficient implementation of the Box-Muller algorithm, use the new sincospi() function in CUDA 5.0.

Input: U1, U2 are two independent random numbers with uniform distribution in (0,1)
Output: X1, X2 are two independent random numbers with normal distribution of zero mean and unit variance

x1 = sqrt (-2 * log (u1)) * cos (2 * PI * u2)
x2 = sqrt (-2 * log (u1)) * sin (2 * PI * u2)
double r, s, c, u1, u2, x1, x2;
r = sqrt (-2.0 * log (u1));
sincospi (2.0 * u2, &s, &c);
x1 = r * c;
x2 = r * s;
(Reference: G. E. P. Box and Mervin E. Muller, A Note on the Generation of Random Normal Deviates. The Annals of Mathematical Statistics, Vol. 29, No. 2, 610-611)


back to the top
Stay up to date by reading the NVIDIA blog:
U.S. Scientists, NSF To Host Nationwide GPU Computing Workshop, By Roy Kim
Let’s Turn Teachers Into Rock Stars, By Brian Caulfield
Kepler GPUs: The Right Tool For New High-Density Dell Servers, By Geoff Ballew
25,000 Grad Student Grants, by Chandra Cheij
How Tesla K20 Speeds Quicksort, a Familiar Comp-Sci Code, By Stephen Jones


back to the top
Find a GPU Meetup in your location, or start one up. Upcoming meetings include:
Silicon Valley, Oct. 8
Paris, Oct. 18 (special full day event)
Brisbane, Oct. 25
New York, Oct. 30

(Want to start a GPU Meetup? Contact


back to the top


- 4-Day CUDA Training Course (Acceleware)
Oct. 2-5, 2012, San Jose, Calif.

- Scaling Soft Matter Physics to 1000 GPUs and Beyond (Webinar)
Oct. 3, 2012, 9:00 am PT
Speaker: Dr. Alan Gray, University of Edinburgh

- Introducing CUDA 5: New Features and Benefits (Webinar)
Oct. 5, 2012, 10:00 am IST

- GPU Acceleration in Bioinformatics
Oct. 9, 2012, London, U.K.
Sponsored by Institute for Cancer Research and NVIDIA

- OpenACC Workshop (RWTH Aachen University)
Oct. 11-12, 2012, Aachen, Germany
Taught by Timo Stich, NVIDIA and Sandra Wienke, RWTH Aachen University

- Nsight Eclipse: High Productivity IDE for CUDA on Linux, MacOS (Webinar)
Oct. 12, 2012, 10:00 am IST

- Portability, Scalability, Numerical Stability in Accelerated Kernels (Webinar)
Oct. 16, 2012, 9:00 am PT
Speaker: John Stratton, University of Illinois at Urbana-Champaign

- 4-Day CUDA Training Course (Acceleware)
Nov. 6-9, 2012, Houston, Texas

- SC12
Nov. 10-16, 2012, Salt Lake City, Utah

- GPUs in the Cloud
Dec. 3-6, 2012, Taipei, Taiwan

- Many-Core Developer Conference (UKMAC 2012)
Dec. 5, 2012, University of Bristol, UK


- GPU Tech Conference
March 18-21, 2013, San Jose, Calif.

(To list an event, email:



– CUDA 5:
– CUDA 5 survey:
– Nsight:
– CARMA (pre-register):

CUDA on the Web

– GPU Test Drive:
– Learn more about CUDA:
– Follow CUDA & GPU Computing on Twitter:
– Network with other developers:
– Stay tuned to GPGPU news and events:
– Newsletter archive:
– CUDA Spotlights:


CUDA® is a parallel computing platform and programming model invented by NVIDIA. It enables dramatic increases in computing performance by harnessing the power of the graphics processing unit (GPU). NVIDIA provides a complete toolkit for programming on the CUDA architecture, supporting standard computing languages such as C, C++ and Fortran. Send comments and suggestions on the newsletter 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. NVIDIA - World Leader in Visual Computing Technologies
Feel free to forward this email to customers, partners and colleagues.

Copyright © 2012 NVIDIA Corporation. All rights reserved. 2701 San Tomas Expressway, Santa Clara, CA 95050.