CUDA and OpenGl

Accelerated Computing CUDA CUDA Programming and Performance
1

Hy,
I created a cuda program processing a RF data frame ( a frame composed of vectors composed of samples) and I am working on using the data on the GPU memory to screen it. I discovered the CUDA OpenGL working pipeline and I think I can use it. Is it possible to use this pipeline to screen the data staying in the GPU memory?

I have these functions

cudaGLRegisterBufferObject(GLuint bufferObj);
registers the buffer object of ID bufferObj for access by CUDA. This function must be called before CUDA can map the buffer object. While it is registered, the buffer object cannot be used by any OpenGL commands except as a data source for OpenGL drawing commands.

cudaMapBufferObject(void** devPtr,unsigned int* size,GLuint bufferObj);
maps the buffer object of ID bufferObj into the address space of CUDA and returns in *devPtr and *size the base pointer and size of the resulting mapping.

How can I use it?
I suposed I will use Opengl pixel buffer object.

Many thanks

2

It sounds like you understand the basics. Have you looked at the simpleGL sample in the SDK?

3

Yes I ve looked at it already but it’s about the coordonates changes and I want to modify the texture (aka I would like to create an image with the datat stocked on the GPU memory).