NVIDIA Update: CUDA Week in Review (Spotlight on Deep Neural Networks; CUDA 6)

Fri., April 25, 2014, Issue #110 Read Newsletter Online | See Previous Issues   Welcome to CUDA: Week In Review News and resources for the worldwide GPU and parallel programming community.   CUDA PRO TIP CUDA 6 XT library interfaces can automatically scale large matrix multiplies and 2D and 3D FFTs to multiple GPUs. Learn more on the Parallel Forall blog.   CUDA SPOTLIGHT GPU-Accelerated Deep Neural Networks This week’s Spotlight is on Dr. Dan Ciresan, a senior researcher at IDSIA in Switzerland and a pioneer in using CUDA for Deep Neural Networks (DNNs). Dan’s methods have won international acclaim on topics such as recognizing handwritten Chinese characters and detecting mitosis in cancer histology images. Read the Spotlight. CUDA NEWS CUDA 6 The CUDA 6 Production Release is now available for download. This version further simplifies parallel programming with new features such as Unified Memory; Drop-in Libraries; and Multi-GPU Scaling. To learn more, attend these CUDA 6 webinars: May 1: CUDA 6 Unified Memory May 7: CUDA 6 Drop-in Performance Optimized Libraries May 14: CUDA 6 Performance Review Bioinformatics + CUDA Interested in bioinformatics? Check out the new NVBIO page on CUDA Zone. NVBIO is a library of reusable components designed by NVIDIA to accelerate bioinformatics applications using CUDA. INCITE Call for Proposals Accelerate your science on Titan, world’s #1 supercomputer for open science, by harnessing more than 20 petaflops of parallel processing using GPUs. Open to all across the globe. Get started here. C-3PO and Machine Learning Technologist Rob Farber recently taught a course on OpenACC and CUDA to college students at KAUST in Saudi Arabia. In addition, he had the opportunity to introduce parallel programming to high school and middle school students. He used the character C-3PO from Star Wars to represent machine learning and demonstrated how a GPU can learn to read. See more on Rob’s new blog: TechEnablement. UPCOMING GPU WEBINARS back to the top May 1: CUDA 6 Unified Memory, M. Ebersole May 7: CUDA 6 Drop-in Performance Optimized Libraries May 13: Overview of AMBER 14, R. Walker, UCSD, S. Le Grand, Amazon, A. Roitberg, Univ. of Florida May 14: CUDA 6 Performance Review, J. Cohen May 22: C++ on GPUs Using OpenACC and PGI Compilers, M. Wolfe June 3: Next Steps for Folding@home, V. Pande, Stanford NEW ON THE BLOG back to the top Parallel Forall: Compilation/Linking of CUDA C++ Device Code, T. Scudiero, M. Murphy 5 Powerful New Features in CUDA 6, M. Harris NVIDIA: How a Team of Engineers Helps the Best Developers Get Even Better, L. Gomes CUDA CALENDAR back to the top 2014 4-Day CUDA Course (Acceleware)   May 6-9, 2014, Calgary, AB, Canada 2-Day Workshop on Computer Vision and GPUs (JGPU14)   May 8-9 May, 2014, Alicante, Spain IEEE Int’l Parallel & Distributed Processing Symposium   May 19-23, 2014, Phoenix, Arizona PRACE Scientific and Industrial Conference   May 20-22, 2014, Barcelona Spain Amber Workshop 2014   June 2-7, 2014, Barcelona, Spain Instructors: Ross Walker & Adrian Roitberg 1-Day CUDA Course (Delft University of Technology)   June 5, 2014, Delft, Netherlands Instructors: Kees Vuik & Kees Lemmens Intro to GPGPU Programming (XSEDE)   June 16-20, 2014 (Virtual course delivered at multiple locations) ISC ’14   June 22-26, 2014, Leipzig, Germany 4-Day CUDA Course (Acceleware)   June 24-27, 2014, San Jose, Calif. Programming Heterogeneous Systems in Physics (Workshop)   July 14-15, 2014, Jena, Germany GPUs and Scientific Applications (University of Alicante)   July 21-24, 2014, Alicante, Spain HPCS 2014   July 21-25, 2014, Bologna, Italy (To list an event, email: [email protected]) CUDA RESOURCES back to the top Online Learning Udacity | Coursera | APC Russia CUDA Consulting Training, programming and project development services are available from CUDA consultants around the world. To be considered for inclusion on list, email: [email protected]. GPU Test Drive Want to try Tesla K40 for free? Sign up here. CUDACasts Check out our new series of short videos about CUDA. Tell Us Your CUDA Story If you are a CUDA developer, tell us how you are using CUDA. GPU-Accelerated Apps See updated list of 270+ GPU-accelerated applications. GPU Meetups Learn about Meetups in your city, or start one up. CUDA Documentation The CUDA documentation site includes release notes, programming guides, manuals and code samples. NVIDIA Developer Forums Join us on the NVIDIA DevTalk forums to share your experience and learn from other developers. You can also ask questions on Stack Overflow, using the ’cuda’ tag. GPU Computing on Twitter For daily updates about GPU computing and parallel programming, follow @gpucomputing on Twitter. Downloads CUDA Nsight CUDA on the Web CUDA Spotlights CUDA Newsletters CUDA Zone GPU Test Drive GPUComputing.net GPGPU.org NVIDIA Newsletters Sign up for NVIDIA Newsletters, including Media & Entertainment, GeForce, NVIDIA GRID VDI and Shield. Please fill out our reader survey so we can improve in 2014. Thanks! 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 to [email protected] 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. To ensure that messages from NVIDIA arrive in your inbox safely, please add [email protected] to your e-mail address book or Safe Sender list. Please note that this message was sent to the following email address: ([email protected]) If you would like to stop receiving CUDA Week in Review emails from NVIDIA, click here to unsubscribe. If you would like to stop receiving all emails from NVIDIA, click here to unsubscribe. Copyright © 2014 NVIDIA Corporation. All rights reserved. 2701 San Tomas Expressway, Santa Clara, CA 95050.