AMD OpenCL Emu Documentation

Quote

OpenCL Emu is a set of effective tools for the OpenCL software development designed for AMD GPUs
without the explicit need of GPU hardware. It allows developing and debugging an OpenCL kernel as a
C++ procedure inside your MS Visual Studio application while providing an easy switch between CPU,
GPU or GPU-emulator at the backend.

This tool would enable programmers to start developing using OpenCL language instantly without having
to learn the intricacies of the OpenCL run-time, saving them time to concentrate more on developing
parallel algorithms and making the shift to OpenCL a step easier.

Source : http://www.geeks3d.com/forums/index.php/topic,2065.0.html

Ati Stream becomes AMD Accelerated Parallel Processing (APP) SDK

"AMD has renamed its wellknown OpenCL SDK, called ATI Stream SDK, in AMD APP SDK. APP stands for Accelerated Parallel Processing."

What is AMD APP Technology?

AMD APP technology is a set of advanced hardware and software technologies that enable AMD graphics processing cores (GPU), working in concert with the system’s x86 cores (CPU), to accelerate many applications beyond just graphics. This enables better balanced platforms capable of running demanding computing tasks faster than ever, and sets software developers on the path to optimize for AMD Accelerated Processing Units (APUs).

What is the AMD APP Software Development Kit?

The AMD APP Software Development Kit (SDK) is a complete development platform created by AMD to allow you to quickly and easily develop applications accelerated by AMD APP technology. The SDK allows you to develop your applications in a high-level language, OpenCL™ (Open Computing Language).

What is OpenCL™?

OpenCL™ is the first truly open and royalty-free programming standard for general-purpose computations on heterogeneous systems. OpenCL™ allows programmers to preserve their expensive source code investment and easily target both multi-core CPUs and the latest GPUs, such as those from AMD.

Developed in an open standards committee with representatives from major industry vendors, OpenCL™ gives users what they have been demanding: a cross-vendor, non-proprietary solution for accelerating their applications on their CPU and GPU cores.

To learn more, see the OpenCL Zone.

To get the AMD APP SDK with OpenCL Support, download here. 

Source : Ozone3D and  AMD

CUDA-Surf

In computer vision we always want something fast... This implementation of SURF rely on CUDA on so work on GPU.

We do not have any information about the timings...

http://www.mis.tu-darmstadt.de/surf

DirectCompute Lecture Series

Some DirectCompute lecture series are available on the web : here

"DirectCompute Expert Roundtable Discussion
Robert Hess has a roundtable discussion with industry experts to help you understand exactly what DirectCompute is and the kinds of software problems that you can apply DirectCompute to leaverage the GPU for computation."

GPU PRO code available

GPU PRO : Advanced rendering technique book make the source code of the articles available on the web.

From Geeks3d.com :
"To compile many of the examples you will need to install the DirectX August 2009 SDK
together with Visual Studio 2008. In the zipped file, the directory structure closely follows
the book structure by using the chapter number as the name of the subdirectory.

General System Requirements

To use all of the files, you will need:

* The DirectX August 2009 SDK
* OpenGL 1.5-compatible graphics card
* A DirectX 9.0 or 10-compatible graphics card
* Windows XP with the latest service pack; some require VISTA or Windows 7
* Visual C++ .NET 2008
* 2048 MB RAM
* The latest graphics card drivers"

 For Image processing the following topics are covered

Section 5 Image Space
5.1 Anisotropic Kuwahara Filtering on the GPU by Jan Eric Kyprianidis, Henry Kang and Jürgen Döllner
5.2 Edge Anti-aliasing by Post-Processing by Hugh Malan
5.3 Environment Mapping with Floyd-Steinberg Halftoning by Laszlo Szirmay-Kalos, Laszlo Szecsi, and
Anton Penzov
5.4 Hierarchical Item Buffers for Granular Occlusion Culling by Thomas Engelhardt and Carsten Dachsbacher
5.5 Realistic Depth-of-Field in Post-Production by David Illes and Peter Horvath
5.6 Real-Time Screen Space Cloud Lighting by Kaori Kubota
5.7 Screen-Space Subsurface Scattering by Jorge Jimenez and Diego Gutierrez

ATI Stream Profiler v1.3 available

ATI Stream Profiler is a Microsoft® Visual Studio® integrated runtime profiler that gathers performance data from the GPU as your OpenCL™ application runs. This information can then be used by developers to discover where the bottlenecks are in their OpenCL™ application and find ways to optimize their application's performance.

What's New in Version 1.3

* Support data transfer for image objects.
* Added five new performance counters: FetchMem, L1CacheHit, LDSFetch, LDSWrite, and LDSBankConflictAccess.
* Added three shader compiler statistics: GPR, scratch register, and flow control stack size used by the kernel.
* Added support to view the CL kernel source in the CodeViewer panel.
* Added support to view the x86 assembly for CPU device in the CodeViewer panel.
* Temporary files are now stored in the ProfilerOutput directory.
* Improved Counter Selection Window.
* Improved results for ATI Radeon™ HD5770 and ATI Radeon™ HD5570 graphics cards.
* Report the API name for the data transfer operations and updated the unit from bytes to kilobytes.
* The kernel name is now appended with the kernel handle to differentiate kernel dispatches for kernel with the same name but different contents.

GPGPU Architecture Comparison of NVIDIA and ATI Gpus

A good overview of ATI/Nvidia GPGPU recent architecture. Here

 http://www.microway.com/pdfs/GPGPU_Architecture_and_Performance_Comparison.pdf

Here the "Octoputer"  purposed by Microway for  $32000...

Source : Microway

HLSL quésako ?

You have some questions in mind :

What does HLSL stand for? Why was it created? How does an HLSL effect file look like? What can you do with HLSL?

This article is for you : Crash course in HLSL.

OpenCL debugger

Graphic Remedy announce the future release of gDEBugger for OpenCL™.

Beta subscription here

Selected Features
gDEBugger CL enables OpenCL developers to:
• Locate parallel computing performance bottlenecks
• Edit and continue OpenCL kernels "on the fly"
• Break on OpenCL errors, function calls, memory leaks and more
• View the application's OpenCL memory consumption
• View OpenCL images and buffers data as an image or as "raw data"
• View OpenCL command queues activities and timing measurements
• View the OpenCL calls history
• Display OpenCL and OpenGL interoperability shared objects
• And much more...

The debugger is multi platform as usual ;)

Source : Here

Visual System on GPU

The MIT and Harvard researchers try to simulate a Visual System with GPU. They demonstrate a better way for computers to ‘see’ through encoding the Visual System physiology (Brain area V1,V2,V4) as black box encoded numerically.

It remember me my engineer courses on Visual System physiology... 

So the GPU "Eye" is bigger than ours... and composed of 16 GPU...

A video explaning the biological stuff conversion to machine engineering...

Finding a better way for computers to "see" from Cox Lab @ Rowland Institute on Vimeo.

Source : link

CUDA Toolkit 3.0 beta released, now with public downloads

Nvidia have released to public the CUDA Toolkit 3.0.

I will not list all the Highlight.... they list because is too long.

But the most important point (related to image processing and OpenGL application are the following points) Support for all the OpenCL features in the latest R195.39 beta driver:
Double Precision
OpenGL Interoperability, for interactive high performance visualization
OpenCL Images support, for better/faster image filtering
32-bit Atomics for fast, convenient data manipulation
Byte Addressable Stores, for faster video/image processing and compression algorithms
Support for the latest OpenCL spec revision 48 and latest official Khronos OpenCL headers as of 11/1/2009

OpenCL Tutorials

AMD/ATI have a great page related to his "ATI Stream" tech. You can have access to "Developer Articles & Publications.

Notice that you have two tutorial on OPENCL.

Image convolution,

N-Body Simulation.

I'm quite impatient to test OpenCL for real.