Recently I have been doing some work with OpenCL and i found myself messing up with old code and re-writing most of it . At first it was interesting and quite funny but no more, so, I thought it was time to make things easier for myself and just make things reusable by creating a wrapper which would wrap most of the boring and time-consuming parts. This would be a wrapper on OpenCL for Java and/or Processing. Well, a well known guy named Mehmet “Memo” Akten has done such a wrapper in C++ for the OpenFrameworks and Cinder libraries. I have ported it to Java.
There are some problems with reading/writing from/to GL textures. For some reason it crashes on me. I have been working with JavaCL‘s author, so hopefully it will be working soon.
I have recently done some experimental work in order to render mass amounts of cubes. I was moved by this video from Smash, i wanted to know how far i would be able to go on my NVidia GT240M (rendering side). My first choice was Geometry Shaders.
I quickly wrote an app that sent a list of points in space to the GPU and a geometry shader would generate a cube mesh for each one of the points. Tested it on 100.000 cubes and the framerate was bad(10fps or so). The time was now for optimization.
Next step was to optimize the cube generation by lowering from a 24 vertex cube to 14 vertex triangle strip. Things got better, but nothing close to my expectations. I was not satisfied, i mean, i had alot of cubes on screen (100K which was not that much) and that was it, nothing else. We’re talking about 20fps or so, for 100.000 cubes (around 1.2 million triangles per frame). Later on i added vertex normals to the geometry shader and started to work on some lighting/shadowing, but i ended up going back on the rendering side of the job. Meanwhile, i was speaking with a friend of mine about this idea and we were discussing ways to compute lighting but i couldn’t stop thinking about my real problem. So it came to me.
Previously, i have done some experiments with opengl hardware instancing, but never got to do much about it . What better time than now, so i grabbed the project and took it for a spin. After a few hours i had the same amount of cubes on screen with a much much better framerate. Quickly implemented some eye-candy (coloring, texturing, vertex lighting), some tweaking here and there and as i was listening to Mr. Peter Broderick (hi, i love you man) added some audio analysis to the feature list.
Last but not least, a kind of “Brownian Motion” was used to generate points in space, increased the cube count to 512*512 and watched it flow ( at 20fps ).
In conclusion, Hardware instancing was much easier to implement and performance seems much better at first sight. Above is a video of 262.144 audio-reactive cubes with GPU animation and basic lighting at around 20fps. For my video card i think that is very good. On a sidenote, i have not given up on the geometry shaders. I am not sure what will be my next step regarding the subject (back to geometry shaders?) but for now this is it. Hardware Instancing kicked Geometry Shaders in the ass.
This is the outside projection for Monologue Muet exhibition, a photography work by Sue Elie Andrade De.
Based on her video called The Rain, i have created the outside projection with response to physical properties, like doors and windows.
I have noticed that OpenCL4Java is on version 1.4beta by now and that my examples were crashing when running on a GPU device. Today i took the time to do something about it. I have downloaded the new version and have updated the examples to run with 1.4beta. Everything seems to work just fine now, if you have a different opinion, please do let me know.
Since Star Wars(tm) (so i’ve read), texture-based techniques have been used to improve the detail on planar and easily curved surfaces. The one i’m talking about here is called Greebles. Apply an heightmap texture on a surface and on a per-pixel basis, geometry is generated acoording to the pixel’s intensity. By doing it you get more detailed surfaces without having to model every little part by yourself, making things more interesting, realistic and much more appealing.
To achieve this i’ve picked Vertex Texture Fetch. It allows you to access texture data on the vertex shader. Pass a texture to the vertex shader and offset the surface vertices by the pixel’s intensity. To improve the looks, bump-mapping with multiple lights have been used. Everything presented here is generated on the GPU, even the objects. Runs nicely on a Nvidia 8200M. Lots of space for improvement.
