Sharing textures with OpenCL (on NVidia) (avoiding glFinish/clFinish)

Accelerated Computing CUDA CUDA Programming and Performance
1

Currently to pass a texture (or renderbuffer) to OpenCL for some fast crunching on the GPU, and to pass the result back to OpenGL on NVidia, I’m doing:

[list=1]

[*] << generate with OpenGL >>

[*] glFinish()

[*] clEnqueueAcquireGLObjects()

[*] << crunch with OpenCL >>

[*] clEnqueueReleaseGLObjects()

[*] clFinish()

[*] << process with OpenGL >>

Is there a faster method of synchronization than glFinish()/clFinish() currently supported on NVidia?

Any word on when ARB_cl_event will be supported on NVidia?

(Usage example: here on Slide 37)

Thanks.

2

That is how I read it. I am interested if people know better