Friday 30 November 2012

CUDA: WEEK IN REVIEW

CUDA: WEEK IN REVIEW, a news summary for the worldwide CUDA, GPGPU and parallel programming community.
CUDA TECH TIP: Need to measure GPU execution time of CUDA kernels and API calls? The most efficient and accurate run-time method is to use CUDA events. Learn more in this Parallel Forall blog post.

CUDA SPOTLIGHT

GPU-Accelerated Visual Effects
This week’s Spotlight is on Vladimir "Vlado" Koylazov, co-founder and head of software development at Chaos Group, developers of the popular V-Ray and V-Ray RT rendering software for artists and designers. Vlado comments: "The increased speed and interactivity enabled by GPU computing allows our users to work more efficiently than ever before."

Read our interview with Vlado Koylazov.

CUDA NEWS

Top Video Picks
Check out these timely presentations from the GPU Technology Theater at SC12:

Guest Speakers
Buddy Bland, ORNL: Titan: ORNL’s New Computer System for Science (19 mins)
Travis Oliphant, Continuum Analytics: Compiling Python to the GPU with Numba (20 mins)
John Urbanic, Pittsburgh SC: Bringing Supercomputing to the Masses with OpenACC (23 mins)
Wen-Mei Hwu, Univ. of Illinois: Kepler GPUs in Blue Waters (28 mins)

NVIDIA Speakers
Don Becker: CARMA: Developments in Power Efficient Computing (20 mins)
Bill Dally: The Road to Exascale (22 mins)
Mark Harris: New Features in CUDA 5 (26 mins)
Mark Ebersole: Intro to CUDA C/C++ (28 mins)
Ian Buck: CUDA: Past, Present and Future (30 mins)
Stephen Jones: Inside the Kepler Architecture (32 mins)

CUDA Documentation
Based on your feedback, NVIDIA has launched a brand new CUDA documentation site. It includes release notes, programming guides, manuals and code samples.

GPU THESIS WATCH

Title: Feasibility Study of the ‘Parareal’ Algorithm
Author: Allan S. Nielsen, Technical University of Denmark
Advisor: Dr. Allan P. Engsig Karup and Dr. Jan S. Hesthaven
Lab: GPUlab, DTU Informatics

CUDA JOB OF THE WEEK

back to the top
NVIDIA is seeking talented CUDA Library Software Engineers to develop performance application libraries and benchmarks for next generation GPUs. These include CUFFT, CURAND and other numerical libraries.

FROM THE BLOGOSPHERE

back to the top
Subscribe to the Parallel Forall RSS feed New on the Parallel Forall Blog:
Thinking Parallel, Part II: Tree Traversal on the GPU, by Tero Karras
How to Query Device Properties and Handle Errors in CUDA C/C++, by Mark Harris
How to Query Device Properties and Handle Errors in CUDA Fortran, by Greg Ruetsch

GPU MEETUPS

back to the top
Find a GPU Meetup in your location, or start one up. Upcoming meetings include:
New York, Nov. 29
Silicon Valley, Dec. 3
Perth, Dec. 5
Brisbane, Dec. 6
Boston, Dec. 14
Paris, Dec. 18

CUDA CALENDAR

back to the top
Parallel Computing with GPUs and CUDA for Finance (NVIDIA)
Nov. 29, 2012, 5:30 pm, Baruch College, New York, New York
Note: An Introduction for Financial Services Developers

Parallel Computing Course (SagivTech)
Dec. 2-5, 2012, Ramat Gan, Israel

Parallel Computing with GPUs and CUDA for Finance (NVIDIA)
Dec. 3, 2012, 5:30 pm, Microsoft, London, UK
Note: An Introduction for Financial Services Developers

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

4-Day CUDA Course, with Finance Focus (Acceleware)
Dec. 4-7, 2012, New York, New York
Instructor: Dr. Kelly Goss, Acceleware

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

CUDA and OpenACC (HPC@LR)
Dec. 6, 2012, Montpellier, France
Note: HPC@LR is the HPC competency center for Languedoc-Roussillon

Debugging of CUDA 5 Apps with Allinea DDT (Webinar)
Dec. 5, 2012, 10:00 am pacific
By Ian Lumb, Allinea

An Unlikely Symbiosis: Gaming and Supercomputing (Webinar)
Dec. 11, 2012, 10:00 am pacific
By Sarah Tariq, NVIDIA

Best Practices for Deploying and Managing GPU Clusters (Webinar)
Dec. 12, 2012, 10:00 am pacific
By Dale Southard, NVIDIA

Getting Started with ArrayFire: 30-Minute Jump Start (Webinar)
Dec. 13, 2012, noon pacific
Sponsored by AccelerEyes
2013
Understanding Parallel Graph Algorithms (Webinar)
Jan. 10, 2013, 9:00 am pacific
By Duane Merrill and Michael Garland, NVIDIA

GPU Tech Conference (GTC 2013)
March 18-21, 2013, San Jose, Calif.
Call for Posters
Developer Tutorials
Session Samples
(To list an event, email: cuda_week_in_review@nvidia.com)

CUDA RESOURCES

back to the top

NVIDIA Tesla K20 and K20X

NVIDIA Tesla K20 and K20X GPU Accelerators are now available.

GPU-Accelerated Apps

List of 200+ popular GPU-accelerated scientific and research applications.
Web | PDF

CUDA Education

NEW Coursera Course
NEW Udacity Course
NEW Book: CUDA Programming, by Shane Cook

NVIDIA Developer Forums

The new NVIDIA developer forums are now live. Join the new online community to learn from other developers and share your experience.

CUDA Consulting

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

GPU Computing on Twitter

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

Downloads

CUDA 5
CUDA 5 survey
Nsight
CARMA

CUDA on the Web

CUDA Spotlights
CUDA Newsletters
CUDA Zone
GPU Test Drive
GPUComputing.net
GPGPU.org

Wednesday 21 November 2012

AMD Embedded Solutions


 

AMD Embedded Solutions to Exhibit at electronica 2012

AMD will be showcasing its embedded solutions at electronica, November 13-16 in Munich, Germany. AMD will be featuring solutions based on its embedded APUs (Accelerated Processing Units) and we encourage interested attendees to visit us at stand #244 in Hall A6. Included in the stand will be demos of:
  • Multi-screen video wall running on Kontron’s AMD R-Series APU-based MiniITX board, with multi-screen capability powered by AMD Eyefinity
  • AMD G-Series APU-based system running on INTEGRITY, Green Hills’ real-time OS
  • And several more demos, boards and systems representing solutions a variety of industries!
» If you would like to meet with an AMD representative while at electronica, please email us
AMD Embedded Solutions to Exhibit at Embedded Technology 2012

AMD and partner, SHINDEN HIGHTEX, Corp., will be sharing a booth at Embedded Technology (ET), November 14-16 in Yokohama, Japan. AMD will be highlighting solutions based on its embedded APUs (Accelerated Processing Units) and we encourage interested attendees to visit us at booth #E-06. Demos in the booth will include:
  • Hands-on point-of-sale system by AdvanPOS, running on an AMD Embedded G-Series APU
  • Digital gaming capabilities featuring a Quixant system running on an AMD Embedded R-Series APU
  • And several more demos, boards and systems representing solutions for a variety of industries!
» If you would like to meet with an AMD representative while at ET, please email us

November Partner Focus: Kontron KTA70M/mITX

This new embedded Mini-ITX motherboard is based on the AMD Embedded R-Series APU and AMD A70M controller hub for rich media embedded applications. With its integrated discrete-class AMD Radeon™ HD 7000 Series Graphics, it provides accelerated processing capabilities and leading-edge graphics, making it an ideal solution for mid-range to high-performance rich media applications in vertical markets such as medical, industrial automation, gaming and digital signage.

» Learn More
 

CUDA NEWS

CUDA NEWS

SC12 Wrap-Up
NVIDIA Tesla K20 and K20X GPU acelerators are now available. Where to buy.

Over 200 popular scientific and research applications are now GPU-accelerated.

Oak Ridge’s Tesla-powered Titan is ranked #1 on the Top500.

40+ GPU Technology Theater talks are posted online.

HPCwire announced its Readers’ and Editors’ Choice Awards.

New CUDA Book
A big congratulations to Shane Cook on his new book: "CUDA Programming: A Developer’s Guide to Parallel Computing with GPUs." Available in paperback and as a Kindle app.

Allinea DDT Support
Allinea Software announced availability of debugging support in Allinea DDT for NVIDIA Tesla K20 and the CUDA 5 toolkit. See NVIDIA’s Duncan Poole speak about it here.

GTC 2013 Update
GTC is on March 18-21, 2013 in San Jose, Calif. Sign up for announcements.

GTC Call for Posters is open. This is a great opportunity to share innovative research in GPU computing, computer graphics, cloud graphics and game development.

GTC Registration opens in early December. Developer tutorials are available now for review, as well as a sample of the hundreds of session in store.

GPU THESIS WATCH

Title: Power Aware Computing on GPUs
Author: Kiran Kumar Kasichayanula, Univ. of Tennessee
Advisor: Dr. Gregory D. Peterson

CUDA JOB OF THE WEEK

back to the top
Join the GPU computing revolution. NVIDIA is seeking highly-motivated people for the following positions:

System Software Development Manager to lead team of world-class developers delivering CUDA driver and runtime software.

CUDA Library Software Engineers to develop performance application libraries and benchmarks for next generation GPUs.

FROM THE BLOGOSPHERE

back to the top
Subscribe to the Parallel Forall RSS feedNew on the Parallel Forall Blog:
Query Device Properties and Handle Errors in CUDA Fortran, by Greg Ruetsch
Thinking Parallel: Collision Detection on the GPU, by Tero Karras
Easy Introduction to CUDA C and C++, by Mark Harris
Subscribe to NVIDIA RSS feedNew on the NVIDIA blog:
World’s Fastest Computer is a Time Machine, by Brian Caulfield
New CUDA Research and Teaching Centers, by Chandra Cheij
GPUs Speed Diagnoses of Heart Problems, by Brian Caulfield

GPU MEETUPS

back to the top
Find a GPU Meetup in your location, or start one up. Upcoming meetings include:
Brisbane, Nov. 22
New York, Nov. 29
Silicon Valley, Dec. 3
Perth, Dec. 5
Boston, Dec. 14
Paris, Dec. 18

CUDA CALENDAR

back to the top
CUDA and Parallel Programming Course
Nov. 21-25, 2012, Riga Technical University, Russia
Sponsored by Applied Parallel Computing

Parallel Computing with GPUs and CUDA for Finance
Nov. 29, 2012, 5:30 pm, Baruch College, New York, New York
Note: An Introduction for Financial Services Developers

Parallel Computing with GPUs and CUDA for Finance
Dec. 3, 2012, 5:30 pm, Microsoft, London, UK
Note: An Introduction for Financial Services Developers

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

4-Day CUDA Course, with Finance Focus (Acceleware)
December 4-7, 2012, New York, New York
Instructor: Dr. Kelly Goss, Acceleware

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

CUDA and OpenACC (HPC@LR)
Dec. 6, 2012, Montpellier, France
Note: HPC@LR is the HPC competency center for Languedoc-Roussillon

Getting Started with ArrayFire: 30-Minute Jump Start (Webinar)
Dec. 13, 2012
Sponsored by AccelerEyes
2013
GPU Tech Conference (GTC 2013)
March 18-21, 2013, San Jose, Calif.
List of tutorials
(To list an event, emailcuda_week_in_review@nvidia.com)

CUDA RESOURCES

back to the top

NVIDIA Developer Forums

The new NVIDIA developer forums are now live. Join the new online community to learn from other developers and share your experience. Sign up.

CUDA Consulting

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

GPU Computing on Twitter

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

Downloads

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

CUDA on the Web

GPU Test Drive
Learn about upcoming Udacity course
Learn more about CUDA
Network with other developers
Stay tuned to GPGPU news and events
CUDA newsletter archives
CUDA Spotlights

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 cuda_week_in_review@nvidia.com

Friday 9 November 2012

CUDA: WEEK IN REVIEW

Welcome to CUDA: WEEK IN REVIEW, a news summary for the worldwide CUDA, GPGPU and parallel programming community.
NEW: NVIDIA Tesla K20 Now Available for Pre-Order. Tesla K20s for cluster nodes and workstations are available for pre-order today. With over 1 TF double precision performance, Tesla K20 is the world’s fastest and most energy-efficient GPU accelerator. Seehttp://www.nvidia.com/object/where-to-buy-tesla.html.
GTC 2013 UPDATE: Call for Posters is now open. This is a great opportunity to share innovative research topics in the areas of GPU computing, computer graphics, cloud graphics and game development. Visit the Call for Posters page.
CUDA TECH TIP: When debugging code or outputting results, the first go-to for any programmer is usually C’s trusty printf() command. Did you know that CUDA allows printf() directly from a GPU kernel? Read more.

CUDA SPOTLIGHT

GPU Power for James Bond
This week’s Spotlight is on Mark Jaszberenyi, co-founder of Colorfront in Budapest, Hungary.

Colorfront’s CUDA-accelerated technology powered the production workflow for the new James Bond 007 movie, Skyfall, which opens today in the U.S.

Read the interview with Mark Jaszberenyi.
GPU Power for James Bond

CUDA NEWS

GPU Technology Theater at SC12
Check out the NVIDIA GPU Technology Theater in booth #2217 to hear industry experts talk about advances in scientific discovery as well as parallel programming tips and hints. Featured speakers include:
   • Bill Dally, NVIDIA
   • Jack Dongarra, University of Tennessee and ORNL
   • Felice Pantaleo, CERN
Can’t make it to SC12? Watch the live web stream on the NVIDIA SC12 event page. For more info, visit www.nvidia.com/sc12.

Petascale Earthquake Simulation
ONERA, the French Aerospace Lab, will host a seminar on Nov. 19 in Chatillon, France on "Petascale Earthquake Simulations" by Prof. Yifeng Cui, San Diego Supercomputer Center. For info, contact thle@onera(dot)fr and gdenis@onera(dot)fr.

Abstract: "Earthquake system science seeks to provide society with better predictions of earthquake causes and effects. Toward this goal, we have developed a highly scalable 3D finite difference code called AWP-ODC that has achieved "M8", a full dynamical simulation of a magnitude-8 earthquake on the southern San Andreas fault. This code was implemented with CUDA-MPI to allow efficient utilization of accelerators on hybrid GPU systems."

NVIDIA Nsight 3.0 Visual Studio Edition Preview
The new NVIDIA Nsight 3.0 Visual Studio Edition preview release supports CUDA 5.0 and the Kepler architecture in Tesla K20, with full CUDA Dynamic Parallelism debugging support and tracing of parent/child kernel launches. Available to registered Nsight developers. See:https://developer.nvidia.com/nvidia-nsight-visual-studio-edition

NVIDIA Developer Forums
The new NVIDIA developer forums are now live. Join the new online community to learn from other developers and share your experience. Sign up at http://devtalk.nvidia.com.

GPU THESIS WATCH

Title: Scalable GPU Acceleration of B-Spline Signal Processing Operations
Author: Alexander Karantza, Rochester Institute of Technology
Advisor: Dr. Sonia Lopez Alarcon
URL: https://ritdml.rit.edu/handle/1850/15371

CUDA JOB OF THE WEEK

HGST, a Western Digital Company, seeks a researcher in the area of magnetic recording heads. Candidate should have expertise in analytical and numerical modeling of nano-structured devices using micromagnetic, electron and spin-transport, thermal, and/or optical modeling. Desired skills: Ph.D.in Physics or EE; MPI, OpenMP, and/or CUDA experience. Job #6366. Contact: hgstcareers (at) hitachigst.com

FROM THE BLOGOSPHERE

back to the top
New on the NVIDIA blog:
How NVIDIA Gave Film Makers Early Look at Skyfall, by Joachim Zell, EFILM
How GPUs Accelerate Innovation, by Liza Gabrielson
Four Amazing Things Carnegie Mellon is Doing, by Chandra Cheij
Beyond Seeing Through Walls to Real-Time Body Scanning, by Bob Sherbin

New on the Parallel Forall blog:
Performance Metrics in CUDA Fortran, by Greg Ruetsch
An Easy Introduction to CUDA C and C++, by Mark Harris
An Easy Introduction to CUDA Fortran, by Greg Ruetsch
Do More, Code Less with ArrayFire GPU Matrix Library, by Chris McClanahan, AccelerEyes
(Subscribe to the Parallel Forall RSS feed)

CUDA TECH TIP

back to the top
Output from a GPU Kernel with printf(): When debugging code or outputting results, the first go-to for any programmer is usually C’s trusty printf() command.

Did you know that CUDA allows printf() directly from a GPU kernel? All the usual format specifiers are supported, and every thread can call printf() independently. If you only want to output something once, however, then you must conditionally choose a thread. The following example shows how it works:
__global__ void helloCUDA() {
    if(threadIdx.x == 0)
       printf("Hello CUDA from...\n"); // Only thread 0 will print this
    printf("Thread %d\n", threadIdx.x); // Every thread will print this
}
Note that printf() in device code requires a GPU with Compute Capability 2.0 or later.
(Thank you to Mark Harris for this Tech Tip. Have one you’d like to share? Email: cuda_week_in_review@nvidia.com)

GPU MEETUPS

back to the top
Meetup Momentum: Congrats to the brand new GPU Meetup in Minneapolis, Minn., led by Kirk Dybvik. The New York GPU Meetup, led by Andrew "Shep" Sheppard, now has over 800 members. The Silicon Valley GPU Meetup, led by Jike Chong, has over 500 members. The Boston GPU Meetup, led by Eliot Eshelman, has over 250 members.

Find a GPU Meetup in your location, or start one up. Upcoming meetings include:
Paris, Nov. 13
Brisbane, Nov. 22
New York, Nov. 29
Silicon Valley, Dec. 3

CUDA CALENDAR

back to the top
SC12
Nov. 10-16, 2012, Salt Lake City, Utah
NVIDIA booth #2217
www.nvidia.com/sc12

Intro to OpenACC and CUDA (FCSCL)
Nov. 12-14, 2012, Leon, Spain
In partnership with the BSC/UPC CUDA Center of Excellence
http://bit.ly/PUTdWr

ONERA/DSNA Seminar
Nov. 19, 2012, Chatillon, France
Prof. Yifeng Cui, SDSC, on Petascale Earthquake Simulations
http://www.onera.fr
Contact: thle@onera(dot)fr and gdenis@onera(dot)fr

GPUs in the Cloud
Dec. 3-6, 2012, Taipei, Taiwan
http://gpu-cloud.cs.astate.edu/

Many-Core Developer Conference (UKMAC 2012)
Dec. 5, 2012, University of Bristol, UK
http://www.cs.bris.ac.uk/Research/Micro/UKMAC2012/

CUDA and OpenACC (HPC@LR)
Dec. 6, 2012, Montpellier, France
https://www.hpc-lr.univ-montp2.fr

Getting Started with ArrayFire: 30-Minute Jump Start (Webinar)
Dec. 13, 2012
http://bit.ly/VkDUZp
2013
GPU Tech Conference (GTC 2013)
March 18-21, 2013, San Jose, Calif.
http://www.gputechconf.com/
See list of tutorials: http://www.gputechconf.com/page/tutorials.html
(To list an event, emailcuda_week_in_review@nvidia.com)

CUDA RESOURCES

CUDA Consulting

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

GPU Computing on Twitter

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

Downloads

CUDA 5: www.nvidia.com/getcuda
CUDA 5 survey: www.surveymonkey.com/s/CUDA5Feedback
Nsight: http://www.nvidia.com/object/nsight.html
CARMA (pre-register): http://bit.ly/carma_news

CUDA on the Web

GPU Test Drive: www.nvidia.com/gputestdrive
Learn about upcoming Udacity course: http://bit.ly/RbFyHs
Learn more about CUDA: www.nvidia.com/cudazone
Network with other developers: www.gpucomputing.net
Stay tuned to GPGPU news and events: www.gpgpu.org
Newsletter archive: www.nvidia.com/object/cuda-newsletter.html
CUDA Spotlights: www.nvidia.com/object/cuda-in-action.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 cuda_week_in_review@nvidia.com
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.

To ensure that messages from NVIDIA arrive in your inbox safely, please add news@nvidia.com to your e-mail address book or Safe Sender list.

Please note that this message was sent to the following email address: (vemireddy.rkreddy@gmail.com)
If you would like to stop receiving emails from NVIDIA, click here to unsubscribe.

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