Friday, 19 September 2014

NVIDIA Update: CUDA Week in Review (Spotlight on Harvard's Cris Cecka; Announcing cuDNN)

CUDA PRO TIP

Always set the current device to avoid multithreading bugs. Learn more on the Parallel Forall blog.

CUDA SPOTLIGHT

Cris CeckaAn Interview with Harvard's Cris Cecka
This week's Spotlight features Cris Cecka, a lecturer and research scientist at the Institute for Applied Computational Science (IACS) at Harvard University. His research focuses on computational mathematics, particularly for interdisciplinary applications in science and engineering. Cris teaches CUDA in Harvard's CS205 course, a core requirement for the IACS Master's program. He is also performing research with the Mathematics Department at the Massachusetts Institute of Technology. Read the Spotlight.

CUDA NEWS

Introducing cuDNN for Machine Learning Developers
Machine Learning, a sub-field of Artificial Intelligence, is becoming pervasive. It's at the foundation of applications such as internet search, fraud detection, image tagging and brain mapping, to name a few. The hottest area in Machine Learning is the area of Deep Neural Networks (DNNs). The success of DNNs has been greatly accelerated with GPU computing.

cuDNNBecause of the increasing importance of DNNs in both industry and academia, NVIDIA has introduced a new library for deep neural networks called cuDNN. The cuDNN library makes it easy to obtain state-of-the-art performance with DNNs, along with other important benefits. Learn more.

Cancer Research Funding Announced 
The NVIDIA Foundation and the National Cancer Institute have kicked off funding opportunities in the fight against cancer. Up to $2 million is available for projects that leverage the power of computation in the search for a cure. Applications are due Oct. 8. Learn more.

Tell Us Your GPU Story 
At SC14, NVIDIA will highlight GPU programming/science stories from around the world. If you are a GPU developer or researcher, tell us how you are using GPUs in 140 characters or less. Your submission will be considered for display in the NVIDIA booth and/or on the NVIDIA website. Respondhere by Oct. 10.

CUDA 6.5 Available Now
The CUDA 6.5 Production Release is now available to the public. Download CUDA 6.5.

GPU Technology Conference 2015: Call for Submissions
The Call for Submissions for the GPU Technology Conference (March 17-20, 2015) is open until Oct 6.

Global Impact Award: Now Accepting Applications
The NVIDIA Global Impact Award is an annual grant of $150,000 for groundbreaking work using NVIDIA technology to address social and humanitarian problems. Nominations are due Oct. 31.

UPCOMING GPU WEBINARS

back to the top 
Sept. 17: CUDA 6.5 Performance Overview, J. Cohen
Sept. 24: Convolutional Networks: ML for Computer Perception, Y. LeCun, Facebook & NYU
Sept. 25: HOOMD-blue 1.0: MD on GPUs, J. Anderson, J. Glaser, University of Michigan
Oct. 8: Enabling Next Generation Intelligent Applications, M. Zeiler, Clarifai
Oct. 15: Essential CUDA Optimization Techniques, C. Mason, Acceleware

NEW ON THE BLOG

back to the top 
Subscribe to the Parallel Forall RSS feedParallel Forall:
Accelerate Machine Learning with the cuDNN Deep Neural Network Library, L. Brown
CUDA Pro Tip: Always Set the Current Device to Avoid Multithreading Bugs, J. Luitjens
Three Versatile OpenACC Interoperability Techniques, J. Larkin
CUDACasts Episode 20: Getting Started with Jetson TK1 and OpenCV, M. Ebersole
Remote Application Development Using NVIDIA Nsight Eclipse Edition, S. Salian

NVIDIA:
GPUs Power Deep Learning Winners in World Cup of Image Recognition, S. Jones
NVIDIA Foundation, National Cancer Institute to Distribute Up to $2M to Cancer Researchers, L. Austin

CUDA CALENDAR

back to the top 

SEPTEMBER


IEEE Cluster 2014
 Sept. 22-26, 2014, Madrid, Spain

CUDA Course (Acceleware)
 Sept. 23-26, 2014, Frankfurt, Germany

OCTOBER-DECEMBER


OpenACC Hackathon (ORNL)
 Oct. 17-31, 2014, Oak Ridge, Tenn

Oil & Gas Workshop (Univ. of Houston/OpenACC)
 Oct. 20, 2014, Houston, Texas

Computational Biophysics Workshop (UIUC, Georgia Tech)
 Nov. 3-7, 2014, Atlanta, Georgia

SC14
 Nov. 16-21, 2014, New Orleans, Louisiana

CUDA Course (Acceleware)
 Dec. 2-5, 2014, New York
(Finance focus)
(To list an event, emailcuda_week_in_review@nvidia.com)

No comments:

Post a Comment