views:

25

answers:

1

Hello everybody, I have a technical question for the experts in here:

I am developing an OpenGL application for iPhone using openGL 1.x . When i render a big item on the device it become obviously slower and that's seem quite normal to me. But i would have expected an increase of framerate when the object is highly zoomed in as the majority of the vertexes are outside the viewport's bounds.

I also try with glEnable(GL_SCISSOR_TEST)/glScissor(0,0,320,480) but the result is always the same? This is really driving me crazy!

Why the not shown triangles are always computed(or why the speed remain the same while drawing a smaller portion of the object)? There is a way to avoid this and subsequently increase the framerate?

Thank you in advance. Greetings.

Peppe.

+2  A: 

The triangles have to be transformed into screen space (vertex shader), before the GPU can determine if they are visible. Use view frustum culling to test the visibility of chunks of geometry on the CPU.

eile