drewcassidy/nvidia-texture-tools
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Edited wiki page through web user interface.

Browse Source
This commit is contained in:
castano 2007-07-17 00:57:18 +00:00
parent 1b30ac31da
commit d2060560ba
1 changed files with 11 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
wiki/RealTimeDXTCompression.wiki
View File

@ -2,21 +2,22 @@
The compressors available in the NVIDIA Texture Tools are not designed for real-time compression. If you need to compress textures in real-time, I'd recommend to look at the following sources:
J.M.P. van Waveren was the first one to describe a [http://www.intel.com/cd/ids/developer/asmo-na/eng/dc/index.htm real-time DXT compressor]. This compressor is part of the of [http://softwarecommunity.intel.com/UserFiles/en-us/Image/1221/Real-Time%20Texture%20Streaming%20&%20Decompression.pdf real-time texture streaming pipeline] used in some [http://www.idsoftware.com Id Software] games.
The same algorithm described there can also be adapted easily to the GPU. This is what Simon Green did in [http://developer.download.nvidia.com/SDK/10/opengl/samples.html#compress_DXT this OpenGL SDK example].
If you need higher quality, it's possible to use DXT5-YCoCg. More info coming soon.
However, if you cannot afford duplicating the memory consumption, you can try using a higher quality compressor.
ryg from [http://www.farbrausch.de Farbrausch] provides some code to do [https://mollyrocket.com/forums/viewtopic.php?t=392&start=0&postdays=0&postorder=asc&highlight= load time DXT compression] of procedural textures, as done in [http://www.pouet.net/prod.php?which=30244 this demo].
J.M.P. van Waveren was the first one to describe a [http://www.intel.com/cd/ids/developer/asmo-na/eng/dc/index.htm real-time DXT compressor]. This compressor is part of the of [http://softwarecommunity.intel.com/UserFiles/en-us/Image/1221/Real-Time%20Texture%20Streaming%20&%20Decompression.pdf real-time texture streaming pipeline] used in some [http://www.idsoftware.com Id Software] games. He obtains the following results with his SSE2 optimized implementation:
|| *CPU* || *DXT1* || *DXT5* ||
|| Intel 2.8 GHz Dual Core Xeon || 112.05 MP/s || 66.43 MP/s ||
|| Intel 2.9 GHz Core 2 Extreme || 200.62 MP/s || 127.55 MP/s ||
The same algorithm described by Waveren can also be adapted easily to the GPU. This is what Simon Green did in [http://developer.download.nvidia.com/SDK/10/opengl/samples.html#compress_DXT this OpenGL SDK example]. The performance on the GPU is much more impressive:
|| *GPU* || *DXT1* || *DXT5* ||
|| geForce 8800 GTX || 1,547 MP/s || - ||
|| geForce 8600 GTS || 461 MP/s || - ||
More info:
https://mollyrocket.com/forums/viewtopic.php?t=392&start=0&postdays=0&postorder=asc&highlight=