Archiwum dla Luty, 2010

Tygodniowy newsletter “CUDA: Week in Review.” – 19.02.2010

Napisany przez e-on w Aktualności dnia 25.02.2010

CUDA: Week in Review

Friday, February 19, 2010, Issue #9

Tygodniowy newsletter “CUDA: Week in Review.” – 12.02.2010

Napisany przez e-on w Aktualności dnia 17.02.2010

 

WELCOME
CUDA NEWS
CUDA and HD Video: Olympian Style
In the spirit of the Vancouver 2010 Games, Seattle-based VholdR is teaming up with NVIDIA next week to demonstrate a groundbreaking HD “headcam” called ContourHD. This hands-free camera’s “cool factor” is that it captures dramatic 1080p high-def video of high-speed adventures, whether you are zooming down ski slopes, doing a daring sky dive, or white-river rafting on class 6 rapids. The HD video, which plays back smoothly on NVIDIA ION netbooks, can be edited for image quality and stabilization and shared on iPhones using CUDA-accelerated software like MotionDSP’s vReveal, CyberLink’s MediaShow Espresso, and Elemental’s Badaboom. Capturing, editing, and sharing action-packed HD video is a fast-growing trend and NVIDIA will partner with VholdR to demo this technology at popular events around the country, including the X Games. The ContourHD headcam can be worn on goggles and helmets or attached to bikes and vehicles. It’s time to tap into your inner Olympian! Learn more about VholdR here: http://www.vholdr.com/contourhd/helmetcam
Gene Sequence Analysis Just Got Faster Using GPUs
With NVIDIA’s recently-announced Tesla Bio Workbench, complex molecular simulations that had been possible only with supercomputing resources can now be run on individual workstations, optimizing the scientific workflow and accelerating the pace of research. Tesla Bio Workbench now offers a range of sequence analysis and docking applications that are accelerated using GPUs, including BLASTP, HMMER, MUMmer, MEME, Smith Waterman and short-read error-correction. Read here for more info: http://www.nvidia.com/object/tesla_bio_workbench.html
CUDA APPS
CUDA on YouTube
While browsing on YouTube, we found some informative videos posted by CUDA aficionados to share with you:

Ocean Simulation with CUDA
URL: http://www.youtube.com/watch?v=BR5iTYzrFpk
Posted by: sebAlyo035
Web description: “Video demo of Alyotech’s real-time ocean simulator captured using an NVIDIA GeForce GTX 280. The software uses both OpenGL and CUDA. The sea surface generation is based on the ‘choppy wave’ model.”

Neural Network Analysis with CUDA
URL: http://www.youtube.com/watch?v=25TwDdUvWwU&feature=related
Posted by: MultiNeurons
Web description: “This is a spiking neural network composed of about 65,000 neurons using the CUDA C/C++ extension. 20% are inhibitory neurons and the remaining are excitatory. Each neuron has 64 presynaptic neurons placed on a 3D cube.”

Geometry Instancing with CUDA
URL: http://www.youtube.com/watch?v=j2en8nrOMzY
Posted by: ber85it
Web description: “GPU-accelerated path following NVIDIA CUDA and OpenGL geometry instancing. ISISLab, University of Salerno.”
CUDA ZONE
CUDA: Week in Review

Friday‚ February 12‚ 2010‚ Issue #8  
WELCOME
Welcome to this week’s issue of “CUDA: Week in Review.”
CUDA NEWS
University of Maryland Named CUDA Center of Excellence
University of Maryland has been recognized as a CUDA Center of Excellence. Amitabh Varshney‚ Professor of Computer Science‚ comments: “Maryland was one of the first universities to start integrating the use of GPUs and the CUDA architecture into our courses and research.” Other CCOEs include Cambridge University‚ Chinese Academy of Sciences‚ Harvard‚ National Taiwan University‚ Tokyo Institute of Technology‚ Tsinghua University‚ University of Illinois at Urbana-Champaign‚ University of Tennessee and University of Utah. See: http://twitthis.com/zyjzci
Moldex Adds CUDA Support
Moldex3D is a 3D injection molding simulation software that helps users evaluate and optimize part and mold designs before manufacturing and production. “We are impressed with the computational speed up that we have seen with NVIDIA´s GPUs‚” says Dr. David Hsu‚ Vice President R&D of CoreTech System Co.‚ Ltd. See: http://bit.ly/9cLfnB
CUDA Power for Bunkspeed
Bunkspeed‚ a provider of rendering and visualization software‚ has selected iray rendering technology from mental images to power its next-generation photorealistic rendering application‚ called Bunkspeed SHOT. Bunkspeed SHOT´s integration with iray will exploit the parallel processing power of CUDA-enabled GPUs. See: http://is.gd/7TQU1
CUDA APPS
Adobe´s Mercury Playback Engine is Fast
In a recent nTersect blog entry‚ NVIDIA´s Mark Priscaro writes: “Adobe has redesigned their video rendering and playback engine to harness the CUDA parallel processing architecture of Quadro GPUs. The result is a fluid‚ real-time editing experience for adding additional effects‚ multiple layers‚ or ultra high resolution content. No more wasting time waiting for things like Encoding and Exporting progress bars to slowly fill the box.” Read more about the Adobe Mercury Playback Engine here: http://is.gd/86HRt
Kaspersky Labs Uses GPUs to Speed Virus Sorting
Tech pub VentureBeat recently covered Moscow-based Kaspersky Lab‚ writing: “Kaspersky‚ which entered the U.S. market in 2005‚ protects 250 million users from cyber threats. It has to analyze tens of thousands of files each day to figure out if they´re variants of known computer viruses. To help with the process‚ it started using CUDA to assist in the filtering.” See the article and video here: http://bit.ly/cKedjj
CUDA ZONE
New on CUDA Zone: Acceleration of Neural Network Computations Using the GPU
Neural networks‚ which are amazingly parallel‚ are used in pattern recognition‚ robotic controllers‚ and military applications‚ among others. For these networks to be useful they need to be trained; standard back-propagation is one of the common methods used to train them. In this study‚ CUDA is used to implement these algorithms on the GPU. Citation: A. Guzhva‚ S. Dolenko‚ I. Persiantse; Lomonosov Moscow State University. See: http://is.gd/885tF
Submit Your Work
Have a CUDA-related paper or research? Show it on CUDA Zone. Submission form: http://is.gd/6hxx2
CUDA Education
Call for Papers
- Dependable Multi-Core Computing Workshop‚ Caen‚ France. Papers due 2/15/10. See: http://is.gd/7JeNh
- Frontier of GPU Computing (FGC 2010) Workshop‚ UK. Paper deadline: 2/26/10. See: http://is.gd/7UlC9
- Call for Participation! Symposium on Chemical Computations on GPGPUs. Abstracts due 4/5/10. See: http://illinois.edu/lb/article/2101/33709
Workshop at Stanford
Molecular Dynamics Workshop Series‚ 3/01/10-3/02/10‚ at Stanford. For more info: http://simbios.stanford.edu/MDWorkshops.htm
CUDA and GPU Computing Courses
Over 305 universities are teaching CUDA and GPU Computing courses. See the list: http://www.nvidia.com/object/cuda_university_courses.html
Call for Participation: “GPU Computing Gems”
NVIDIA and Professor Wen-mei Hwu of the University of Illinois‚ Urbana-Champaign are accepting article submissions for “GPU Computing Gems.” More info: http://www.nvidia.com/object/io_1265140268552.html.
CUDA RESOURCES
Upcoming Webinars
GPU Computing using CUDA C – An Introduction
02/15/10‚ 9 pm pacific: https://www2.gotomeeting.com/register/679725883
02/18/10‚ 10 am pacific: https://www2.gotomeeting.com/register/762804771

GPU Computing using CUDA C – Advanced 1
02/15/10‚ 9 pm pacific: https://www2.gotomeeting.com/register/262218050
02/26/10‚ 10 am pacific: https://www2.gotomeeting.com/register/445062803

GPU Computing using CUDA C – Advanced 2
02/22/10‚ 9 pm pacific: https://www2.gotomeeting.com/register/981346954
03/05/10‚ 10 am pacific: https://www2.gotomeeting.com/register/141711034

GPU Computing and OpenCL – An Introduction
3/19/10‚ 10 am pacific: https://www2.gotomeeting.com/register/355834867

GPU Computing and OpenCL – Advanced 1
3/26/10‚ 10 am pacific: https://www2.gotomeeting.com/register/521523739
Par4All Open Source Environment
Par4All is a new open source environment enabling source-to-source transformations on C and Fortran programs on various targets‚ including CUDA C and OpenCL. See: http://www.par4all.org/
GPU Development Environment Update
NVIDIA´s new GPU development environment (codenamed Nexus) is now called “NVIDIA Parallel Nsight.” Register at http://developer.nvidia.com/nsight for access to the Beta program.
Parallel Processing Textbook
“Programming Massively Parallel Processors: A Hands-on Approach‚” co-written by Dr. David B. Kirk‚ NVIDIA Fellow‚ and Professor Wen-mei Hwu of the University of Illinois‚ is available at: Elsevier or Amazon.
CUDA Toolkit
Download the CUDA Toolkit 3.0 Beta here: http://is.gd/886cU.
CUDA ON THE WEB
- Follow CUDA & GPU Computing on Twitter: www.twitter.com/gpucomputing
- Network with other developers: www.gpucomputing.net
- Stayed tuned to GPGPU news and events: www.gpgpu.org
- Learn more about CUDA on CUDA Zone: www.nvidia.com/cuda
 
Copyright © 2010 NVIDIA Corporation. All rights reserved.

Brak komentarzy

Tygodniowy newsletter “CUDA: Week in Review.” – 05.02.2010

Napisany przez e-on w Aktualności dnia 17.02.2010

 

CUDA: Week in Review

Friday, February 5, 2010, Issue #7  
WELCOME
Welcome to this week’s issue of “CUDA: Week in Review.”
CUDA NEWS
Call for Participation: “GPU Computing Gems”
NVIDIA and Professor Wen-mei Hwu of the University of Illinois, Urbana-Champaign are accepting article submissions for “GPU Computing Gems,” a contribution-based book that will focus on practical techniques for GPU computing. This is a continuation of the popular “GPU Gems” series. More info: http://www.nvidia.com/object/io_1265140268552.html
National Science Foundation Grant for GPU Computing
Northeastern University and Mass General Hospital were awarded a $1.3 million grant from the National Science Foundation to develop a software platform based on GPUs for biomedical imaging applications. The new software libraries will enable radiologists to more quickly assess tissue images, which will allow clinicians to perform image-guided biopsies earlier than can be done now… Professor Dave Kaeli, who leads Northeastern’s parallel software development team, comments: “The implications for a patient’s mental health as well as cost of care for patients are huge.” Kaeli’s team is developing the software on GPU-based systems, with CUDA and OpenCL. See: http://is.gd/7JnO9
CUDA APPS
Siemens Healthcare Uses CUDA for 3D Ultrasounds of Babies in Utero
In the latest issue of VentureBeat, tech writer Dean Takahashi discusses a cool new application from Siemens Healthcare which was demoed this week at “CUDA Day” in San Francisco: “Siemens is using CUDA technology to create 3D ultrasounds of babies in utero and other medical applications… Physicians can see how a baby is doing in much better visual detail than a 2D ultrasound can deliver.” See Dean’s video interview with Roee Lazebnik, director of product development for radiology and ob/gyn, Siemens Healthcare:  http://is.gd/7Jcsc
CUDA ZONE
New on CUDA Zone: Massively-Parallel Simulation of Biochemical Systems
In this paper, a computational approach for massively parallel simulation of biological molecular networks was developed leveraging the computing power of modern graphics cards. The implementation on a GeForce GTX 280 was over 59 times faster than on a Xeon 2.66Ghz processor. Citation: J. Ackermann, P. Baecher, T. Franzel, M. Goesele, K. Hamacher; Technische Universitat Darmstadt. See it here: http://is.gd/7J9fD
Submit Your Work
Have a CUDA-related paper or research? Show it on CUDA Zone. Submission form: http://is.gd/6hxx2
CUDA Education
Workshop at Stanford
Molecular Dynamics Workshop Series, 3/01/10-3/02/10, at Stanford University. Intended for people interested in running MD simulations on GPUs and/or developing new MD algorithms that can be implemented and accelerated on GPUs. Registration is required and spaces are limited. For more info: http://simbios.stanford.edu/MDWorkshops.htm
Call for Papers
Many-Core/Reconfigurable Supercomputing Conference, Rome. Papers due: 2/12/10. See: http://www.mrsc2010.eu/

Dependable Multi-Core Computing Workshop, Caen, France. Papers due 2/15/10. See: http://is.gd/7JeNh/
CUDA and GPU Computing Courses
Over 300 universities are teaching CUDA and GPU Computing courses. See the list: http://www.nvidia.com/object/cuda_university_courses.html
Parallel Processing Textbook
“Programming Massively Parallel Processors: A Hands-on Approach” is co-written by Dr. David B. Kirk, NVIDIA Fellow, and Professor Wen-mei Hwu of the University of Illinois, Urbana-Champaign. The book utilizes CUDA C as well as OpenCL.  For more info, go to Elsevier or Amazon.
CUDA RESOURCES
Upcoming  Webinars
GPU Computing using CUDA C – An Introduction
2/08/10, 9 pm pacific: https://www2.gotomeeting.com/register/679725883

GPU Computing using CUDA C – Advanced 1
2/15/10, 9 pm pacific:  https://www2.gotomeeting.com/register/262218050

GPU Computing using CUDA C – Advanced 2
2/22/10, 9 pm pacific:  https://www2.gotomeeting.com/register/981346954

GPU Computing and OpenCL – An Introduction
3/19/10, 10 am pacific: https://www2.gotomeeting.com/register/355834867

GPU Computing and OpenCL – Advanced 1
3/26/10, 10 am pacific: https://www2.gotomeeting.com/register/521523739
GPU Development Environment Update
NVIDIA’s new GPU development environment, codenamed Nexus, has been officially christened “NVIDIA Parallel Nsight.”  Register at http://developer.nvidia.com/nsight for access to the Beta program.
CUDA Toolkit
Download the CUDA Toolkit 3.0 Beta here: http://www.nvidia.com/object/cuda_get.html
CUDA ON THE WEB
– Follow CUDA & GPU Computing on Twitter: www.twitter.com/gpucomputing
– Network with other developers: www.gpucomputing.net
– Stayed tuned to GPGPU news and events: www.gpgpu.org
– Learn more about CUDA on CUDA Zone: www.nvidia.com/cuda
 
Copyright © 2010 NVIDIA Corporation. All rights reserved.

Brak komentarzy

Bio Workbench – najnowsze aplikacje dla chemików i biofizyków na platformę NVIDIA CUDA.

Napisany przez e-on w Aktualności dnia 17.02.2010

Zachęcam do zapoznania się z nowymi przykładami aplikacji chemicznych i biofizycznych, zoptymalizowanych dla platformy NVIDIA CUDA.

NVIDIA ® Tesla ™ Bio Workbench umożliwia przesuwanie granic badań biofizycznych oraz biochemicznych, poprzez przekształcenie standardowego PC w “laboratorium obliczeniowe” zdolne do pracy nad skomplikowanymi kodami biologicznymi, takimi jak badania nad nowymi lekarstwami czy sekwencjonowanie DNA, ponad 10-20 razy szybciej dzięki wykorzystaniu GPU NVIDIA Tesla.

Wiecej materiałów można znaleźć na stronie:

http://www.nvidia.com/object/tesla_bio_workbench.html

 

Brak komentarzy

Seminaria internetowe NVIDIA GPU Computing – luty/marzec 2010

Napisany przez e-on w Aktualności dnia 17.02.2010

Zapraszamy do rejestracji na webowe seminaria NVIDIA GPU, które odbędą się w lutym i marcu 2010.

Seminaria obejmują wiele tematów, w tym wprowadzenie do architektury C++ CUDA, Open CLTM API i technik optymalizacji wydajności, przedstawione zostaną przez inżynierów firmy NVIDIA DevTech. W trakcie seminariów będzie możliwość zadania pytań online. 

 Prosimy stosować się do poniższych odnośników w celu rejestracji dla każdego seminarium, w którym chcieliby Państwo uczestniczyć.

Wcześniejsza rejestracja jest wymagana aby uczestniczyć w seminarium.

 Prosze uwzględnić iż podany czas prezentacji jest podany dla ”Pacific Time -8h”.

Wszystkie prezentacje będą w języku angielskim.

 GPU Computing z wykorzystaniem CUDA C – Wprowadzenie, 2h

 

19 luty, 10:00:          https://www2.gotomeeting.com/register/762804771

15 marzec, 9:00:      https://www2.gotomeeting.com/register/269261746

 

 GPU Computing z wykorzystaniem CUDA C – Dla zaawansowanych 1 , 2h

 

26 marzec, 10:00:     https://www2.gotomeeting.com/register/445062803

22 marzec, 9:00:       https://www2.gotomeeting.com/register/767133395

 

 GPU Computing z wykorzystaniem CUDA C – Dla zaawansowanych 2 , 2h

 

22 luty, 21:00:           https://www2.gotomeeting.com/register/981346954

5 marzec, 10:00:       https://www2.gotomeeting.com/register/141711034

29 marzec, 9:00:       https://www2.gotomeeting.com/register/215543547

 

GPU Computing and OpenCLTM – Wprowadzenie, 2h

 

19 marzec, 10:00:      https://www2.gotomeeting.com/register/355834867 

 

GPU Computing and OpenCLTM- Dla zaawansowanych, 2h

 

26 marzec, 10:00:      https://www2.gotomeeting.com/register/521523739

OpenCL jest znakiem zastrzeżonym Apple Inc. używane na podstawie licencji Khronos Group Inc.

Brak komentarzy