Loading...
Site Announcements
- Check out the gpucomputing.net documentation file.
- Join the GPU Computing Research Forum which meets via WebEx the 1st and 3rd Wednesdays of each month from 10 -11 AM Central Time beginning September 15.
- GPU Technology Conference (GTC 2010) - Sumit Schedule Available Online
_______________________________________________________________________________________________
GPU Computing General Topics
Welcome to The GPU Computing General Topics Community
This community will be a place to discuss topics relating to GPU computing which are more general in nature, and don't quite fit into the other specific communities. For examples topics can include where to find the CUDA and OpenCL.SDK's , discuss architectural differences between various GPU families and ask for programming tricks and tips.
This community will be a great place to discuss and discover the latest training or libraries releases - basically anything relating to computing on the GPU which is not specifically research domain specific.
I'm Nadeem , I work at NVIDIA and am responsible for helping developers and researchers like yourself. It is my privilege to be this community's champion - remember this community is to help you and its members best leverage the huge potential of GPU Computing by exchanging ideas, experiences and knowledge -and I'm here to help.
Welcome again and lets have fun changing the world together,
Nadeem Mohammad Director , CUDA Tech Marketing, NVIDIA Corp.
Featured Stories and Papers
NVIDIA Parallel Nsight 1.0 Rolls out !!
NVIDIA Parallel Nsight is finally released
This represents a major milestone in bringing seamless development and debugging of hetrogenous code - Multi-core CPU and Massively parallel GPU code can be debugged with powerful tools
Parallel Nsight is compatible with both CUDA C and OpenCL.
Find out all the details here:
http://www.nvidia.com/ParallelNsight
There is a powerful version available free of charge - and a professional version for a small additional fee.
Be the first to start using the full released version - download a copy today.
Read More
Stanford parallel programming course available online for free.
Standford School of Engineering has posted a full parallel programming course online.
Its a full 10 week course.
This is the link to the full press release: http://news.stanford.edu/news/2010/april/engineering-cuda-course-042210.html
Here is the course home page: http://code.google.com/p/stanford-cs193g-sp2010/
As it happens it also uses the new Kirk-Hwu book as the course text book.
Read More
MATLAB about to be GPU accelerated
The MathWorks, publisher of the popular MATLAB® & Simulink® products, have has announced an upcoming version of MATLAB with NVIDIA GPU acceleration. MATLAB is a high-level technical computing language and interactive environment for algorithm development, data visualization, data analysis, and numeric computation, with more than one million industry and academic users worldwide.
Those interested in the upcoming MathWorks beta should register here: www.mathworks.com/gpu_beta
The MathWorks has also authored a white paper on GPU acceleration in MATLAB located here: www.mathworks.com/gpu_paper
Read More
Help improve the Visual Profiler for CUDA and OpenCL
NVIDIA is looking at prioritizing some new features for Visual Profiler. Please help us prioritize these features by filling out this concise survey. Thanks everyone!
Read More
IEEE Software Special Issue: "Software for the Multiprocessor Desktop: Applications, Environments, Platforms"
IEEE SOFTWARE invites you to submit a paper to the special issue:
=========================================
"Software for the Multiprocessor Desktop:
Applications, Environments, Platforms"
=========================================
Guest Editors:
* Victor Pankratius (Karlsruhe Institute of Technology)
* Wolfram Schulte (Microsoft Research),
* Kurt Keutzer (Univ. California Berkeley)
Final submissions due: 1 July 2010
Publication date: January/February 2011
Multicore processors, like Nehalem or Opteron, and manycore processors, like Larrabee or GeForce, are becoming a de facto standard for every new desktop PC. Exploiting the full hardware potential of these processors will require parallel programming. Thus, many developers will need to parallelize desktop applications, ranging from browsers and business applications to media processors and domain-specific applications. This is likely to result in the largest rewrite of software in the history of the desktop. To be successful, systematic engineering principles must be applied to parallelize these applications and environments
MICPRO Journal Call for Papers on Exploitation of Hardware Accelerators
CALL FOR PAPERS
SPECIAL ISSUE ON EXPLOITATION OF HARDWARE ACCELERATORS
JOURNAL: Microprocessors and Microsystems -- Embedded Hardware Design
Guest Editors: Ramón Doallo, Margarita Amor, Basilio B. Fraguela (Universidade da Coruña, Spain)
The Elsevier Embedded Hardware Design (MICPRO) Journal seeks original manuscripts for a Special Issue on Exploitation of Hardware Accelerators scheduled to appear in the first half of 2011.
The importance of hardware accelerators (GPUs, Cell, FPGAs, ...) is increasing rapidly, especially in the computationally demanding disciplines such as realistic 3D computer graphics and high-performance scientific computing. The use of these accelerators for General-Purpose computation achieves speedups of orders of magnitude vs. optimized CPU implementations. They have become powerful, capable, and inexpensive coprocessors useful for a wide variety of computation.
This Special Issue is focused on issues related to experiences and knowledge in novel solutions exploiting and defining new trends in hardware accelerators, including hardware architecture, software tools, and applications. All authors who presented papers at WEHA 2010 are encouraged to submit an extended version of their paper to MICPRO for possible inclusion in this special issue. However, besides submissions based on WEHA 2010 papers, other high quality submissions within the scope of the special issue are also welcome. Each submission will be reviewed by at least three reviewers to ensure very high quality of selected papers for the special issue.
Read More
New 4 part Series of Deep Dive Webinars on Parallel Nsight
New Parallel Nsight Webinars
This new series of deep-dive webinars will help you learn how Parallel Nsight can speed up development. Topics include an overview of basic features, debugging of host and CUDA kernels, analysis of complex parallel applications, and graphics debugging and analysis.
Overview of Parallel Nsight 1.0 for Visual Studio
Aug. 20, 9am – https://www2.gotomeeting.com/register/832771459
Aug. 23, 8pm – https://www2.gotomeeting.com/register/935381498
Debugging Massively Parallel Applications with Parallel Nsight 1.0 and Microsoft Visual Studio
Aug. 25, 9:30am - https://www2.gotomeeting.com/register/431568810
Aug. 30, 8pm – https://www2.gotomeeting.com/register/320801507
Analyzing and Optimizing Massively Parallel Applications with Parallel Nsight 1.0 and Microsoft Visual Studio
Sept. 1, 9:30am – https://www2.gotomeeting.com/register/809022811
Sept. 7, 8pm – https://www2.gotomeeting.com/register/943671050
Debugging and Analyzing Graphics Applications with NVIDIA Parallel Nsight 1.0 and Microsoft Visual Studio
Sept. 8, 9:30am – https://www2.gotomeeting.com/register/436432658
Sept. 13,8pm – https://www2.gotomeeting.com/register/827311026
Read More
FREE GPU Computing Workshop in Adelaide, South Austrialia
eResearch SA, XENON Systems and NVIDIA invite you to attend a free workshop on GPU computing with CUDA. The workshop will be held at 1:00PM on Tuesday 10 August 2010 at Mawson Lakes, in the Mawson Centre Lecture Theatre MC1-02.
Register now by visiting: http://nvidia.eventbrite.com
Read More
AMD Research Seeks PhD Student Interns
AMD Research and Advanced Development Lab (RADL) is looking for talented PhD students for the fall internship. Good candidates are supposed to have an outstanding understanding of computer architecture and significant experience with simulation study. Interns are expected to work in one of the following areas:
- CPU/GPU heterogeneous workload analysis
- High bandwidth memory subsystem for heterogeneous computing
- large stacked memory management for heterogeneous computing
The internship will start from a negotiated date in September. The internship will last for about 3 months, but can be extended to 6 months if the intern and RADL agree. Openings are available in Bellevue/WA.
If you are interested, please email CV and contact information to Jaewoong Chung (Jaewoong.Chung@amd.com<mailto:Jaewoong.Chung@amd.com<mailto:Jaewoong.Chung@amd.com%3cmailto:Jaewoong.Chung@amd.com>>)
Read More
Are you a GPGPU developer? Participate in our UX study
Are you a GPGPU developer? Participate in our UX study
You know that I work on the parallel debugger in Visual Studio and I've talked about GPGPU before and I have also mentioned UX. Below is a request from my UX colleagues that pulls all of it together.
Get CUDA Certified
NVIDIA has launched its first CUDA Certification program.
Be one of the first Certified CUDA Programmers - find out the full details at www.nvidia.com/certification
This exam tests candidates CUDA C programming and optimization skills. This 3 hour test can be taken at over 6500 test centers in over 165 countries.
Discounts are available for companies planning to certify 6 engineers or more. General questions or applications for bulk discounts can be addressed to certification@nvidia.com
Read More
NVidia Recorded Seminars
CUDA C - An Introduction
CUDA C - Advanced 1
- Video (wmv format)
- Slides (pdf format)
Read MoreCUDA by Example: An Introduction to General-Purpose GPU Programming
Quick Links
- Buy now
- Read a sample chapter online (.pdf)
- Download source code for the book's examples (.zip)
- NOTE:Please read this license before downloading the software.
- Errata
CUDA by Example, written by two senior members of the CUDA software platform team, shows programmers how to employ this new technology. The authors introduce each area of CUDA development through working examples. After a concise introduction to the CUDA platform and architecture, as well as a quick-start guide to CUDA C, the book details the techniques and trade-offs associated with each key CUDA feature. You’ll discover when to use each CUDA C extension and how to write CUDA software that delivers truly outstanding performance.
Read More
Latest Stories and Papers
Latest Blog Posts
Latest Forum Posts
Latest Events
Latest Code Snippets and Repositories
Featured Events
CUDA course at Oxford, July 26-30
This is a 5-day hands-on course for students, postdocs, academics and others who want to learn how to develop applications to run on NVIDIA GPUs using the CUDA programming environment.
Read More
Read More
Read More
Featured Events
2010 International Workshop on GPUs and Scientific Applications (GPUScA 2010)
Read More
RSS Feeds
AMD, Nvidia and the century of graphics - TG Daily
DARPA doles out dosh to NVIDIA for high performance GPU computing systems - UberGizmo (blog)
Industry Leaders, Investors Line Up to See the Hottest New Technologies at ... - MarketWatch (press release)
NVIDIA Announces GeForce 400M Series Notebook GPUS - Notebooks.com
World-Renowned Robotics Visionary and Molecular-Simulation Pioneer to Headline ... - MarketWatch (press release)
LucidLogix Announces New "Unity" Multi-GPU Concept. - X-bit Labs
AMD Still Playing Catchup in GPU Computing Race - HPCwire
NVIDIA Names Georgia Institute of Technology a CUDA Center of Excellence - MarketWatch (press release)
EM Photonics, UD develop advanced algorithms for Air Force - University of Delaware
Earnings Scorecard: NVIDIA Corp. (NVDA) - Wall Street Pit (blog)
 PCR-online.biz | AMD, Nvidia and the century of graphics TG Daily But if they didn't do this they would always live as "second best," and with the massive move to GPU computing there is a chance that the new AMD could and ... Graphics Chips to Gain Horsepower and Programmability - Chief Scientist of Nvidia. |
 DailyTech | DARPA doles out dosh to NVIDIA for high performance GPU computing systems UberGizmo (blog) ... where the latter is supposed to come up with high performance GPU computing systems that will address a so-called "crisis in computing". ... DARPA 'exascale' supercomputer in the works Nvidia scores $25M Pentagon contract to develop 1000X faster supercomputers ... DARPA Selects Four To Develop Super Computer |
Industry Leaders, Investors Line Up to See the Hottest New Technologies at ... MarketWatch (press release) "Fundamental changes in computing are always enabled by new processors. The power of GPUs applied to computing could break open new markets over the next ... Small companies create new industries with innovative new approach to computing |
 Notebooks.com | NVIDIA Announces GeForce 400M Series Notebook GPUS Notebooks.com As part of the new GeForce 400M series NVIDIA has announced 7 new GPUS all of which support Optimus and CUDA for intelligent switching and GPU computing. ... |
World-Renowned Robotics Visionary and Molecular-Simulation Pioneer to Headline ... MarketWatch (press release) 23, unveiling how advances in GPU computing for computer vision will fundamentally advance self-driving, robotic technology for cars. ... |
LucidLogix Announces New "Unity" Multi-GPU Concept. X-bit Labs Graphics board vendors can increase the total market for multi-GPU computing from the low end to the high end. And as a consumer, why wouldn't you choose to ... |
AMD Still Playing Catchup in GPU Computing Race HPCwire AMD's acquisition of ATI in 2006, by chance or by design, coincided with the meteoric rise of general-purpose GPU (GPGPU) computing, especially in HPC. ... HPCWire Forecasts Mainstream Intel or AMD CPU-GPU chips in 2012 or 2013 |
NVIDIA Names Georgia Institute of Technology a CUDA Center of Excellence MarketWatch (press release) CUDA(TM) is NVIDIA's computing architecture that enables its GPUs to be programmed using industry standard programming languages and APIs, opening up their ... |
EM Photonics, UD develop advanced algorithms for Air Force University of Delaware The EM Photonics' GPU computing team is led by John Humphrey, who developed the GPU-accelerated math library CULAtools, and will be working closely with ... |
Earnings Scorecard: NVIDIA Corp. (NVDA) Wall Street Pit (blog) The company generated decent numbers from Quadro professional graphics, Tesla GPU computing and the Tegra system-on-a-chip business. On the other hand, ... |
Search
User login
Who's online
There are currently 5 users and 5 guests online.
Upcoming Events with Description
- Debugging /Analyzing Graphics Apps with Parallel Nsight 1.0/Microsoft Visual Studio
Starts on: 2010-09-08 at 09:30 - Second Workshop on Programming Models for Emerging Architectures (PMEA)
Starts on: 2010-09-11 at 00:00 - 2010 International Workshop on GPUs and Scientific Applications (GPUScA 2010)
Starts on: 2010-09-11 at 00:00 - Parallel Architectures and Compilation Techniques (PACT) 2010
Starts on: 2010-09-11 at 00:00 - GPU Technology Conference (GTC 2010)
Starts on: 2010-09-20 at 00:00 - ...more Events
BayWebSoft