Recent Posts

Pages: [1] 2 3 ... 10
1
"A large amount of numerically-oriented code is written and is being written in legacy languages. Much of this code could, in principle, make good use of data-parallel throughput-oriented computer architectures. Loo.py, a transformation-based programming system targeted at GPUs and general data-parallel architectures, provides a mechanism for user-controlled transformation of array programs. This transformation capability is designed to not just apply to programs written specifically for Loo.py, but also those imported from other languages such as Fortran. It eases the trade-off between achieving high performance, portability, and programmability by allowing the user to apply a large and growing family of transformations to an input program. These transformations are expressed in and used from Python and may be applied from a variety of settings, including a pragma-like manner from other languages."

http://hgpu.org/?p=13791

http://documen.tician.de/loopy/
2
3D-Tech News Around The Web / Kingston unveils high-speed HyperX Predator PCIe SSD
« Last post by gyg on March 29, 2015, 11:20:54 AM »
"Kingston's new HyperX Predator PCIe SSD is an upgrade part that brings read speeds of up to 1400MB/s and write speeds hitting 1000MB/s to desktop and notebook systems."

http://www.zdnet.com/article/kingston-unveils-high-speed-hyperx-predator-pcie-ssd/
3
3D-Tech News Around The Web / GNU Nano Gets New Stable Release
« Last post by gyg on March 29, 2015, 11:18:11 AM »
GNU Nano 2.4.0 has been released as the first stable update to this UNIX command line text editor in a number of years. The release codenamed "Lizf" brings a wide variety of changes: full undo system, Vim-compatible file locking, linter support, formatter support, flexible syntax highlighting, and random bugfixes.

http://www.phoronix.com/scan.php?page=news_item&px=GNU-Nano-2.4.0-Released

https://lists.gnu.org/archive/html/nano-devel/2015-03/msg00068.html
4
3D-Tech News Around The Web / Microsoft - The Zombie DirectX SDK
« Last post by Stefan on March 29, 2015, 07:17:40 AM »
Quote
Over the past five years, I've devoted significant time and effort to explaining the state of affairs with the legacy DirectX SDK. Developers can of course continue to use the legacy DirectX SDK (once they apply the workaround for the existing installation problems) with the Windows 8.0 SDK or later which comes with VS 2012 / 2013 / 2015 per the instructions on MSDN. This allows existing projects that still use deprecated D3DX9/D3DX10/D3DX11, XAudio 2.7, XInput 1.3, or XACT to build but still gain access to the latest Windows headers/libraries. You should in general rely on other methods for obtaining the latest debug device layer, tools, utility libraries, samples, Effects 11, DXUT11, and HLSL Compiler.
There is, however, one case that I've not addressed to date: A number of developers actually "checked in" the legacy DirectX SDK headers and libraries into their source control.

Read on...
5
3D-Tech News Around The Web / Clustered Shading demo links
« Last post by JeGX on March 27, 2015, 05:15:39 PM »
6
3D-Tech News Around The Web / Humus' Clustered Shading demo
« Last post by Stefan on March 27, 2015, 04:52:40 PM »
Quote
Clustered Shading is a technique for efficient lighting on modern GPUs ...
The main motivation for Clustered Shading is performance, flexibility, and simplicity. It normally out-performs competing techniques, such as tiled shading, and in particular the worst-case performance, which is what matters most...

Runs fine on old AMD Zacate APU.
Clustered shading is twice as fast as deferred shading.
7
English forum / GLSL Hacker 0.8.2.2 available
« Last post by JeGX on March 27, 2015, 04:40:23 PM »
I just uploaded a new version of GLSL Hacker that brings minors bugfixes. The version 0.8.2.2 is available for all platforms: Windows 64-bit, Linux 64-bit, Mac OSX and Raspberry Pi.

All demos for the Raspberry Pi are now in the official code sample pack in the opengl_es_20/ sub-folder .

DOWNLOAD: http://www.geeks3d.com/glslhacker/download/

Changelog: http://www.geeks3d.com/glslhacker/changelog/
8
General Discussion / stars shader
« Last post by mireazma on March 27, 2015, 02:57:24 PM »
Hello there.

Can you guys give me a direction where to get assistance about making a specific shader?

I want to make a starry night sky from 2 separate textures: 1 for the sky background + 1 for the stars. The stars texture is 90% empty, as in RGBA(0, 0, 0, 0) and only have scattered white points or little blobs as stars.
I need an idea about how to make a shader for the stars texture to draw a cross for each star (horizontal/vertical spikes). The idea here is whenever camera is rotated the crosses stay unrotated.
One alternate way is to just have a pre-crossed star texture and draw it multiple times at different locations over the already rotated background. But with 1000 stars I'm afraid it's not going to be very economical. And I want to take advantage of the shader parallelism.

The shader would probably be something like the simple blur shader. I'm saying this because I guess it should "smudge" the points (original stars) upwards, downwards, left and right.

But I have no clue as to where to begin. Seeing those amazing Geeks3D shaders I thought what I want is doable relatively simply.
9
3D-Tech News Around The Web / Rasterization: A Practical Implementation
« Last post by JeGX on March 27, 2015, 11:17:30 AM »
Quote
The rasterization rendering technique is surely the most commonly used technique to render images of 3D scenes, and yet, that is probably the least understood and the least properly documented technique of all (especially compared to ray-tracing).

Why this is so, depends on different factors. First, it's a technique from the past. We don't mean to say the technique is obsolete, quite the contrary, but that most of the techniques that are used to produce an image with this algorithm, were developed somewhere between the 1960s and the early 1980s. In the world of computer graphics, this is middle-ages and the knowledge about the papers in which these techniques were developed tends to be lost. Rasterization is also the technique used by GPUs to produce 3D graphics. Hardware technology changed a lot since GPUs were first invented, but the fondamental techniques they implement to produce images haven't changed much since the early 1980s (the hardware changed, but the underlying pipeline by which an image is formed hasn't). In fact these techniques are so fondamental and consequently so deeply integrated within the hardware architecture, that no one pays attention to them anymore (only people designing GPUs can tell what they really do, and this is far from being a trivial task; but designing a GPU and understanding the principle of the rasterization algorithm are two different things; thus explaining the latter should actually not be that hard!).

Regardless, we thought it was urgent and important to correct this situation. With this lesson, we believe to be the first ressource that provides a clear and complete picture of the algorithm as well as a complete and full practical implementation of the technique. If you found in this lesson the answers you have been desperately looking for anywhere else, please consider making a donation! This work is provided to you for free and requires many hours of hard work.

Link: http://www.scratchapixel.com/lessons/3d-basic-rendering/rasterization-practical-implementation
10
3D-Tech News Around The Web / C++11 in CUDA: Variadic Templates
« Last post by JeGX on March 27, 2015, 11:16:10 AM »
Quote
CUDA 7 adds C++11 feature support to nvcc, the CUDA C++ compiler. This means that you can use C++11 features not only in your host code compiled with nvcc, but also in device code. In my post “The Power of C++11 in CUDA 7” I covered some of the major new features of C++11, such as lambda functions, range-based for loops, and automatic type deduction (auto). In this post, I’ll cover variadic templates.

Link: http://devblogs.nvidia.com/parallelforall/cplusplus-11-in-cuda-variadic-templates/
Pages: [1] 2 3 ... 10