Fri., Feb. 3, 2012, Issue #69          Click here for online versio

CUDA NEWS

New CUDA 4

Have you downloaded the newest version of CUDA? CUDA 4.1 offers a trifecta of features to make parallel programing with GPUs easier and faster:

•    New LLVM-based compiler delivering instant performance speed-up
•    Re-designed Visual Profiler with automated performance analysis
•    Hundreds of new imaging and signal processing functions

- Download CUDA 4.1 today

- Watch the CUDA 4.1 video

CUDA TECH TIPS

(You spoke. We listened. Based on our reader survey results, we've added a new section called "CUDA Tech Tips" for CUDA developers.)

Thrust

Today's featured topic is Thrust, a parallel algorithms library which resembles the C++ Standard Template Library (STL). Thrust's high-level interface enhances developer productivity while enabling performance portability between GPUs and multicore CPUs. Interoperability with established technologies (such as CUDA, TBB and OpenMP) facilitates integration with existing software.

Thrust offers a rich collection of data parallel primitives such as scan, sort and reduce. By describing your computation in terms of these high-level abstractions, you provide Thrust with the freedom to select the most efficient implementation automatically. Thrust can be utilized in rapid prototyping as well as production.

Code example:

// sort data on the device (846M keys per second on GeForce GTX 480) thrust::sort(d_vec.begin(), d_vec.end());

- See more Thrust code examples

- Read the Thrust QuickStart Guide

(To suggest a CUDA Tech Tip, email: This e-mail address is being protected from spambots. You need JavaScript enabled to view it )

CUDA SPOTLIGHT:

CUDA Spotlight: Dynamic Airspace Configuration

Bart Gallet

Our CUDA Spotlight is on Bart Gallet, a Principal Analyst at Mosaic ATM. Gallet and his team are focused on Dynamic Airspace Configuration (DAC), which will enable air traffic controllers to adapt to user demand in real-time while managing variables such as weather and traffic congestion.

- Read the story on the NVIDIA blog

- Read the interview with Bart Gallet

(To suggest a CUDA Spotlight, email: This e-mail address is being protected from spambots. You need JavaScript enabled to view it )

CUDA UPDATES

Parallel Nsight 2.1

NVIDIA Parallel Nsight brings GPU computing to Microsoft Visual Studio. The latest release supports CUDA 4.1 and includes features such as the new CUDA information window.

- Learn more about Parallel Nsight

- Watch the Intro to Debugging CUDA video

Usability Survey

The NVIDIA Usability Research Team is looking for North American CUDA developers (beginner or advanced) to participate in a 60-minute feedback session via conference call. If selected, you will receive a $100 Amazon gift card. Respond to this survey to indicate availability: http://bit.ly/xhsUFR

CUDA Training

Acceleware has launched its 2012 series of CUDA classes targeted to HPC professionals. Upcoming venues include Sunnyvale, Calif. and Houston, Texas. Courses are also available on-site at your location. More info available at http://acceleware.com/nvidia-cuda-opencl-training.

GPU MEETUPS

U.S.

New York | Silicon Valley | Boston | Denver/Boulder | New Mexico | Austin | Washington, DC

Europe

Paris | London | South Africa

APAC/India

Tokyo | Perth | Brisbane | Melbourne | New Zealand | India

(Interested in starting a Meetup? Email: This e-mail address is being protected from spambots. You need JavaScript enabled to view it )

CUDA Calendar

FEBRUARY-MARCH

- CUDA Programming 1-Day Course - Delft University of Technology

Feb. 3, 2012, Delft, Netherlands | http://ta.twi.tudelft.nl/users/vuik/gpu.html

- CUDA GPU Programming 2-Day Workshop

Feb. 4, 2012, Berlin, Germany | http://cuda-eorg.eventbrite.com/

Presenter: Dr. Kashif Rasul, Freie Universitat Berlin

- GPU Computing with CUDA and PGI Directives - Applied Parallel Computing

Feb. 5-8, 2012, Dublin, Ireland | http://cuda-course.eventbrite.com/

- PRACE Winter School at CINECA

Feb. 6-11, 2012, Bologna, Italy | http://www.cineca.it/en/page/training-and-courses

- Transformative Discovery in Computational Nanoscience...

Feb. 6-8, 2012, Oak Ridge, Tenn. | http://www.nics.tennessee.edu/feb-2012-accelerator-workshop

Note: Joint workshop between ORNL and University of Tennessee

- Happy Valentine's Day

Feb. 14, 2012

- OpenACC 1.0 (Webinar)

Feb. 14, 2012, 10 am PT | https://www2.gotomeeting.com/register/754327826

- Keeneland Workshop on GPU Heterogeneous Processing

Feb. 20-21, 2012, Atlanta, Georgia | http://keeneland.gatech.edu/2012-02-20-workshop

- Debugging CUDA with TotalView (Webinar)

Feb. 22, 2012, 9 am PT | https://www2.gotomeeting.com/register/653210522

Presenter: Chris Gottbrath, Rogue Wave Software

- GPU-Accelerated Quant Finance: The Way Forward (Webinar)

Feb. 29, 2012, 9 am PT | https://www2.gotomeeting.com/register/637936010

Presenter: Jerry Hanweck, Hanweck Associates

- GPGPU5

March 3, 2012, London, England | http://www.ece.neu.edu/GPGPU/GPGPU5/

- CUDA 4-Day Training Course - Acceleware and Microsoft

March 6-9, 2012, Sunnyvale, Calif. | http://acceleware.com/mar6sunnyvale

- Open Molecular Mechanics (OpenMM) Workshop

March 12-13, 2012, Stanford, Calif. | http://simbios.stanford.edu/MDWorkshops.htm

- CUDA 4-Day Training Course - Acceleware and Microsoft

March 20-23, 2012, Houston, Texas | http://acceleware.com/mar20houston

APRIL-JUNE

- SPIE: Defense, Security and Sensing

April 23-27, 2012, Baltimore, Maryland | http://spie.org/x6765.xml

Note: GPU for Defense Applications session, April 25, by Eric Kelmelis, EM Photonics

- State-of-the-Art Algorithms for Molecular Dynamics

April 30-May 2, 2012, Edinburgh, UK | http://bit.ly/zCQWRk

- INPAR 2012

May 13-14, 2012, San Jose, Calif. | http://www.innovativeparallel.org/

- GPU Technology Conference (GTC 2012)

May 14-17, 2012, San Jose, Calif. | http://www.gputechconf.com/

- Workshop on Emerging Parallel Architectures (WEPA 2012)

June 2-4, 2012, Omaha, Nebraska | http://www.staff.uni-mainz.de/schmi033/

- ISC'12

June 17-21, 2012, Hamburg, Germany | http://www.isc-events.com/isc12/

(To list an event, email: This e-mail address is being protected from spambots. You need JavaScript enabled to view it )

CUDA RESOURCE

NVIDIA CARMA Devkit

– Pre-register: http://bit.ly/carma_news

Downloads

– CUDA: www.nvidia.com/getcuda

– Parallel Nsight: http://developer.nvidia.com/nvidia-parallel-nsight

Webinars

– CUDA: www.nvidia.com/webinars

– Parallel Nsight: http://developer.nvidia.com/developer-webinars

CUDA Registered Developer Program

– Sign up: www.nvidia.com/paralleldeveloper

CUDA GPUs

– List of CUDA-enabled GPUs: http://developer.nvidia.com/cuda-gpus

CUDA on the Web

– Learn more about CUDA on CUDA Zone: www.nvidia.com/cudazone

– See previous issues of CUDA: Week in Review: http://is.gd/cBXbg

– Follow CUDA & GPU Computing on Twitter: www.twitter.com/gpucomputing

– Network with other developers: www.gpucomputing.net

– Stay tuned to GPGPU news and events: www.gpgpu.org

– Check out the NVIDIA Research page: www.nvidia.com/research

CUDA Recommended Reading

– CUDA books: http://developer.nvidia.com/cuda-books

CUDA Recommended Viewing

– GTC Express: http://www.gputechconf.com/object/gtc-express-webinar.html

– SC11 presentations: http://www.gputechconf.com/page/gtc-on-demand.html

ABOUT CUDA

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: This e-mail address is being protected from spambots. You need JavaScript enabled to view it