 |
EDITOR'S NOTE |
Happy New Year to the GPU computing community! To usher in 2012, the NVIDIA team suggests these Top 10 New Year's Resolutions:
- Promote your apps and papers on CUDA Zone
- Join or start a GPU Meetup in your city
- Download CUDA Toolkit 4.1 RC2
- Sign up for CARMA (CUDA on ARM devkit) updates
- Nominate a colleague for a CUDA Spotlight interview
- Attend a GPU computing webinar
- Submit a poster for GTC 2012
- Accelerate your Fortran app with directives
- Become a CUDA Registered Developer
- Fill out the 1-minute reader survey to help us improve in 2012!
|
|
|
CUDA SPOTLIGHT |
GPU-Accelerated Air Traffic Management
Our first spotlight of 2012 is on Dr. Monish Tandale, Research Scientist at Optimal Synthesis Inc. (OSI), a high-tech R&D firm specializing in algorithm and software development. Here's a preview of the interview: |
 |
|
| NVIDIA: Monish, tell us about OSI's work with the NASA Ames Research Center. |
Monish: At any given moment, there are over 7000 aircraft flying in the skies of the U.S. This number is only going to increase, adding more complexity to air traffic flow management. The project we are working on with NASA is related to NextGen, a
multi-agency initiative to improve the coordination of air traffic flow in the U.S. National Airspace System (NAS). |
| NVIDIA: What advantages have you achieved with GPU computing? |
| Monish: Using CUDA and GPU computing we were able to achieve a 250X speedup over NASA’s baseline software. The shallow learning curve associated with CUDA allowed us to smoothly transition from C/C++ based CPU programming to parallel computing on GPUs. |
|
- Watch the video on YouTube
- Read the full interview with Monish Tandale |
|
CUDA DEVELOPER NEWS |
back to the top |
WIRED Magazine on Genomics and GPUs |
The WIRED article "Chinese Crunch Human Genome With Videogame Chips" reports on groundbreaking work at Shenzhen-based BGI. Author Eric Smalley writes: "The world’s largest genome sequencing center once needed four days to analyze data describing a human genome. Now it needs just six hours."
- www.wired.com/wiredenterprise/2012/01/genomes-and-gpus/
NVIDIA CARMA Devkit Pre-Registration
You can now pre-register for the NVIDIA CARMA Devkit (the CUDA on ARM development kit announced at SC11). It features a Tegra 3 quad-core CPU and Quadro 1000M CUDA GPU and will be available for purchase in the second quarter of the year.
- http://bit.ly/carma_blog
University of Canterbury's GPU Computing Group
The University of Canterbury in New Zealand launched a new group for researchers, developers and students interested in GPU computing. GPU professionals and enthusiasts are welcome to attend the monthly meetings and tutorials.
- www.math.canterbury.ac.nz/php/groups/study/GPU/
New Hybrid GPU Cluster at Bielefeld University
Bielefeld University in Germany will install a new hybrid supercomputer for quantum chromodynamics. Equipped with 400 Tesla GPUs, it will have a cumulative peak performance of ~500 teraflops.
- http://insidehpc.com/2011/12/16/new-gpu-cluster-at-bielefeld-university-to-crack-quantum-chromodynamics/
|
|
GPU MEETUPS |
back to the top |
| |
The GPU Meetups are starting strong in January. Congrats to the brand-new Meetup in Paris, led by Jerome Piat, which will hold its first event on Jan. 25. And, a big thank you to Andrew "Shep" Sheppard for his enthusiastic nurturing of the GPU Meetup community. Here's a list of upcoming meetings:
| U.S. |
| GPU Meetup New Mexico, Jan. 11, 7:00 pm |
| GPU Meetup Boston, Jan. 12, 6:30 pm |
| GPU Meetup Southern California, Jan. 19, 7:00 pm |
| GPU Meetup South Florida, Jan. 23, 6:30 pm |
| GPU Meetup New York, Jan. 23, 6:00 pm |
| GPU Meetup Silicon Valley, Jan. 30, 6:15 pm |
|
|
|
CUDA Calendar |
back to the top
|
- Debugging Workshop for CUDA 4.1 using Allinea DDT (Webinar)
- Accelerating SEISMIC_CPML Using High-level GPU Programming (Webinar)
- GPU Computing with CUDA and PGI Directives - Applied Parallel Computing
- Intro to Bright Cluster Manager - Advanced Clusters Made Easy (Webinar)
- CUDA 4-Day Training Course - Acceleware and Microsoft
- GPUs in Computational Statistics Workshop
- CUDA Programming 1-Day Course - Delft University of Technology
- CUDA GPU Programming 2-Day Workshop
- GPU Computing with CUDA and PGI Directives - Applied Parallel Computing
- PRACE Winter School at CINECA
- Transformative Discovery in Comp. Nanoscience, Advanced Materials, Energy Research
- CUDA 4-Day Training Course - Acceleware and Microsoft
- Debugging CUDA with TotalView (Webinar)
- GPGPU5
- CUDA 4-Day Training Course - Acceleware and Microsoft
- CUDA 4-Day Training Course - Acceleware and Microsoft
- SPIE: Defense, Security and Sensing
| April 23-27, 2012, Baltimore, Maryland |
| Note: GPU for Defense Applications session, April 25, by Eric Kelmelis, EM Photonics |
| http://spie.org/x6765.xml |
- INPAR 2012
- GPU Technology Conference (GTC 2012)
- Workshop on Emerging Parallel Architectures (WEPA 2012)
(To list an event, email: cuda_week_in_review@nvidia.com) |
|
|
CUDA RESOURCES |
back to the top |
|
|
|
|
| – Sign up: www.nvidia.com/paralleldeveloper |
|
| – List of CUDA-enabled GPUs: http://developer.nvidia.com/cuda-gpus |
|
– 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 books: http://developer.nvidia.com/cuda-books |
|
| – 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 as well as APIs such as OpenCL and DirectCompute. Send comments and suggestions to: cuda_week_in_review@nvidia.com
|
|
|
 |
Click here to opt in specifically to CUDA: Week in Review.
Copyright © 2012 NVIDIA Corporation. All rights reserved. 2701 San Tomas Expressway, Santa Clara, CA 95050. |
