Show Posts

This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.

Topics - Stefan

Pages: 1 ... 104 105 [106] 107 108 ... 145
3D-Tech News Around The Web / CUDA VisionWorkbench v
« on: July 04, 2010, 05:29:56 AM »
CUDA VisionWorkbench v is already built against CUDA 3.1
Also they benchmarked Tesla C2050

Oscar analyzes the features of Stream SDK 2.2 and 2.3

Also he points to the talk about "Addition of early version of GPU support for cloth/softbody simulation" in Bullet.
2 CPU cores hogged and 40% GPU usage - that's why it reads "early version" i assume...

The latest released version of VLC, 1.1.0, that was out a week ago, and has been downloaded half-a-dozen millions times so far, has added GPU acceleration for HD decoding under Linux and Windows. On Windows, as already stated, the code isn't working correctly with AMD Radeon cards.
Therefore, we have been working with AMD on this topic and after common work, we are going to release a new version of VLC, versionned as 1.1.1, that will work with the upcoming ATI Catalyst 10.7 driver. AMD did provide us a beta of this driver and we have verified successfully that GPU acceleration works.


Changes between 1.1.0 and 1.1.1:

 * Support for the new capabilities: libvlc_adjust_Enable, libvlc_adjust_Contrast,
   libvlc_adjust_Brightness, libvlc_adjust_Hue, libvlc_adjust_Saturation, libvlc_adjust_Gamma
 * Various fixes and crash preventions, especially when video functions were called early

Stream output:
 * Fix h264 streaming in ts

Windows and Mac port:
 * Fix mod files support

 * Fix performance issues with GPU decoding using DxVA2 using ATI graphic cards
   You NEED ATI Catalyst 10.7

 * Interface and crash fixes

I also noticed that the GPU accelerated post-processing stopped crashing on my rig, even with 1080p at six-fold speed   :)

Brown Deer Technology accelerates scientific and engineering applications using the most powerful many-core processors ever created combined with industry standard programming interfaces.

Download open source samples
Download whitepaper Presentation: GPU-Accelerated Computing for Chemistry and Material Simulations Using ATI Stream Technology (Brown Deer Technology)

3D-Tech News Around The Web / eyeon's Fusion 6.1 now supports OpenCL
« on: July 02, 2010, 01:27:15 PM »
eyeon unveils the next generation of the GPU Supercomputing  framework in Fusion® 6.1. This is not just an acceleration technology; this is unprecedented productivity advancement.

Exploiting the power of low cost GPU graphics cards with hundreds of cores, coupled with an expanded feature set, makes this release much more productive. The need for network rendering becomes greatly reduced, keeping the studio's infrastructure manageable and cost effective.

3D scene importing via FBX has been greatly expanded, streamlining the process between 3D animation and rendering to directly have the same assets working in Fusion. Produce passes and layers on the fly directly on the GPU at breath-taking speed. Cutting reliance on other applications and departments simplifies the production process.

Fusion 6.1 accelerates from the starting line with astounding GPU optimizations, local file caches and particle solution caching. The creative horizon expands with new tools for managing grain, color correction and handling metadata. Scripters will rejoice at the inclusion of native python support, and everyone benefits from the many enhancements to particles.

Fusion 6.1 now supports the OpenCL language, which allows tools to take advantage of the GPU in modern NVidia and ATI graphics cards to achieve blazing speed increases. How fast? We are seeing improvements as much as 1000% on some of the most processor intensive tools in Fusion (e.g. Defocus, Noise generators). Insert OpenCL code directly into Fuse tools to create your own GPU-accelerated tools.

OpenCL’s open computing language is a framework that utilizes the massively parallel operations of GPU's for general computing. Instead of just doing 3D OpenGL rendering on graphics cards, more general processing can be achieved at orders of magnitude faster than possible with just CPU's.


In recent years, the use of GP-GPUs for HPC has sparked quite a bit of interest. ... While there were more entries in the field (Cell and Larabee), the GP-GPU market has tuned into a two horse race with NVidia and AMD/ATI leading the way. From an HPC perspective, the GP-GPU can be considered a SIMD parallel co-processor (Single Instruction Multiple Data) Indeed, graphic processing is by its nature a SIMD process and it makes sense to borrow the hardware for other SIMD applications like those in HPC.

Full story at Linux magazine

Supercomputers that mix CPUs with graphics processors made their mark on the Green500 list of top energy-efficient supercomputers released on Wednesday.

Full story at PC World

3D-Tech News Around The Web / SmallLuxGPU v1.6 (OpenCL)
« on: July 02, 2010, 01:10:03 PM »
SmallLuxGPU is a LuxRays demo and a LuxRender v0.8 "proof of concept".

Real-time sequences were recorded on a i7 860 + HD5870 + HD5850 at the resolution of 800x450.
Off-line sequences were rendered with a i7 860 + HD5870 + HD5850 at the resolution of 1280x720.

SmallLuxGPU and LuxRays are released under GPL license and the sources are available here.
Precompiled binaries are available on LuxRender forums (check the section dedicated to GPU acceleration).

I like their philosophy: "CPU Vs GPU ? No, thanks, CPU + GPU + Network rendering is better"

AMD’s ATI Radeon HD 5800 series was launched just over nine months ago. Since then, AMD has been true to its word releasing new driver updates every month. Our question is, "Have we seen driver performance improve since launch?" Certainly drivers updates and performance increases have traditionally gone hand in hand, and we have seen some mighty performance boosts with the latest NVIDIA drivers. Now we want to see how far along the Radeon HD 5870 has come since its first install into our PCIe slots.

Today’s testing is simple, we are going to take six games and compare different driver versions in an apples-to-apples comparison. We are using three different drivers. The first is the actual launch driver we used on September 22nd, 2009, when the Radeon HD 5870 launched. We will then compare that to the first official WHQL release for the Radeon HD 5800 series which is Catalyst 9.10 WHQL. Finally, these will be compared to the current Catalyst 10.6 WHQL driver to see if performance has improved over these last nine months. All testing below is done with a single stock Radeon HD 5870 1GB.

Full story at HardOCP

Graphic Remedy is proud to announce the release of gDEBugger Version 5.6 for Windows, Linux, Mac OS X, iPhone and iPad.

This version introduces iPhone and iPad on-device debugging and profiling abilities, letting developers optimize their App, in real-time, on the actual iPhone and iPad hardware, while viewing invaluable inside information such as device's GPU, CPU, graphic driver and operating system performance counters.

gDEBugger, an OpenGL, OpenGL ES and OpenCL debugger and profiler, traces application activity on top of the OpenGL API, lets programmers see what is happening within the graphic system implementation to find bugs and optimize OpenGL application performance. gDEBugger runs on Windows, Mac OS X, iPhone and Linux operating systems.

3D-Tech News Around The Web / TechPowerUp GPU-Z v0.4.4
« on: July 01, 2010, 05:56:50 PM »
GPU-Z is a lightweight utility designed to give you all information about your video card and GPU.

Please note: Some versions of McAfee Antivirus report a "Generic!Artemis" infection. This is a McAfee specific false positive, GPU-Z is not infected with any virus/trojan.

Revision History

    * Added support for NVIDIA GeForce GTX 460, GT 330, GT 315, GT216 based ION
    * Added support for AMD HD 5670 (Juniper), Mobility HD 5430, Mobility 4200, Mobility 4100
    * Added PowerColor hardware giveaway
    * Added die size measurement for NVIDIA GF100
    * Added option to GPU-Z's system menu to show temperatures in °F
    * Fix for BIOS reading on ATI
    * Fixed decimal points in ADT7473 reading
    * Fixed crash on GeForce 8300 IGP
    * Added clock monitoring for RS780 variants
    * Improved clock monitoring for ATI R6xx architecture

The June 2010 release of SlimDX focused on filling in existing APIs and adding missing functionality. In addition to implementing most of DirectWrite and ensuring that Direct3D 11 support was feature complete, the June 2010 release also refactored shared shader and effect functionality into a common D3DCompiler namespace. Several new samples were added to showcase advanced interop features, and a .NET 4.0 build was added, along with VS 2010 support. On top of these additions, the usual array of bug fixes and feature enhancements were made to continue improving the stability of the SlimDX library.

SlimDX has been out of beta for almost two years now. Since first released, the team has tried to keep breaking changes to an absolute minimum. This has led to a number of desired changes being postponed in favor of backwards compatibility. During the past few months the SlimDX team has been doing initial design work and planning for a tentatively named "SlimDX 2.0" version, which will incorporate numerous breaking changes and enhancements to the library's core design. This "2.0" version is currently slated for a late 2010 release, making June 2010 one of the last "1.x" releases.

Quad-core processors are common, and eight-core chips are gaining. With the latest parallel software development tools, there's nothing standing between your apps and the blistering speed of parallel processing.

Here's one dashing way to pick up the latest techniques for parallelizing your apps: get the new issue of Intel's The Parallel Universe magazine.

•         Parallelism Full Steam Ahead! James Reinders, Intel® Software Development Products director, explores the convergence of multicore processors and mature development tools that is propelling parallelism and industry leader adoption.
•         Enhancing Productivity and Achieving High Performance. MPI developers work smarter with new usability and productivity features in our latest Cluster Toolkit Compiler to crank up app performance. Scale to up to tens of thousands of cores. Wow!
•         Increase Productivity and Performance with IncrediBuild* and Intel® Parallel Composer. Zip through application build time up to 20X faster and accelerate run times with this combo of tools.
•         Optimizations for MSC.Software SimXpert*. Glean the best practices of MSC. Software engineers' phased threading approach in taking advantage of speedy multiprocessor architectures.

Bunkspeed has announced the release of Bunkspeed SHOT, a completely redesigned 'interactive photograph for 3D data' software application.

Full story here

Demo here

The Desktop Graphics Card Comparison Guide

These days, there are so many graphics card models that it has become quite impossible to keep up with the different configurations. Therefore, we decided to compile this guide to provide an easy reference for those who are interested in comparing the specifications of the various desktop GPUs in the market as well as those already obsolescent or obsolete.

Currently covering 422 desktop graphics cards, this comprehensive comparison will allow you to easily compare 20 different specifications for each and every card. We hope it will prove to be a useful reference. We will keep this guide updated regularly, so do check back for the latest updates.

To make it easy to compare the specifications, we split it up into three sections for your convenience. Just click on Split List to access them. However, if you prefer to compare all the graphics cards for each company in a single table, we also have a single list which can be accessed by clicking on Full List. Just click on the company and the type of list you prefer.

For mobile and workstation GPUs, please refer to our Mobile GPU Comparison Guide and Workstation Graphics Card Comparison Guide.

Stonetrip, a leading 3D engine company for games and 3D applications, today announced a new community website that will provide more resources for ShiVa developers and those interested in developing games and apps on the leading engine. ... To support the expanding group of ShiVa 3D developers and fans, Stonetrip has responded with a new community website, located at:

Full PR here

Download Shiva3D player here and check out their demos, especially "The Hunt"


First of all: Brigade is a research project. It is designed to facilitate the production of 'proof-of-concept' games that use path tracing as the primary rendering algorithm, as opposed to rasterization, which is what GPUs normally do. Path tracing uses ray tracing, and extends basic ray tracing by supporting indirect lighting and soft shadows. More complex effects, such as caustics, are also supported, but suffer from noise. Brigade does not aim to produce photo-realistic images using complex scenes and materials. The emphasis is first of all on speed, and getting the highest possible quality within a strict time budget. Higher quality graphics are the goal, but never at the expense of interactivity.

Performance is achieved by employing state-of-the-art algorithms, often based on very recent research. Besides this, engineering and optimization obviously plays an important role. The greatest gains however are obtained by using not just a GPU or CPU but both: Brigade splits the rendering task seamlessly over available compute units. Depending on your configuration, Brigade will render using the CPU only, or mostly on the GPU, or anything inbetween. This balance is reconsidered per frame. The plan is to add support for multiple GPUs as well as network rendering. Multiple CPUs are already supported, and all your cores will be put to work optimally.

Brigade is the successor to the Arauna real-time ray tracer, which has been used for a large number of student projects at the 'International Game Architecture & Design' program of the NHTV University of Applied Sciences, Breda, The Netherlands. As such, Brigade mimicks the Arauna API to ease the transition to a new rendering engine. If you are familiar with Arauna, you will feel right at home.


Brigade implements a basic path tracer, with a fixed shading path. This path supports diffuse materials with textures, as well as specular and dielectric materials (metal, glass). Dielectrics may have absorption, and an adjustable index of refraction. Lighting is entirely done using area lights, of which an unlimited amount may be specified. For Brigade, a light is simply a polygon with a material that is named 'emm0-9'. This way, entire meshes can be turned into light sources.

Brigade aims to offer a simple API to the developer. To facilitate this, the initial scene is loaded using a text file, named scene.txt. In this file, you can specify resolution, number of samples per pixel, wether or not GPU rendering should be used and so on. Thanks to this you can experiment with the path tracer without ever looking at the source code. Check scene.txt to see how to add more planes to the demo scene, for exmaple.

Internally, Brigade uses a BVH that is constructed per-frame from BVHs that are built per scene graph object. The per-object BVHs are updated as needed, for optimal performance. The BVH is then synchronized with the version on the GPU, and also converted to other structures that are needed for optimal CPU rendering. Because of the intention to use Brigade for games, fast support for animated scenes is a priority.


Brigade currently requires a recent NVidia card to run (although you may be able to run using the CPU only by altering scene.txt). Your GPU must support CUDA. Two executables are provided: One is optimized for GTX2xx class devices, the other one targets Fermi devices specifically. The first one will obviously work on a broader range of hardware, but the Fermi version is optimal for that architecture and should be used if possible. A version of Brigade that automatically detects supported features will be released at a later date.

This is yet another application that is nuked by NVIDIA driver branch 256+  :(
In case of crash (or using an ATI GPU), disable GPU usage in scene.txt


If you want to try WebGL, get the latest Firefox builds here, i found no changelog  ???

Also available is Firefox 3.6.6 which hopefully fixes the crashing crash fix protection introduced in FF 3.6.4  ::)

Pages: 1 ... 104 105 [106] 107 108 ... 145