Sign in to follow this  
RavNaz

performance question regarding when to call DIP

Recommended Posts

Say you have a model, composed of multiple meshes. Is it better for performance to either: a) Upload the vert/index info to the VB and IB's and DIP straightaway or b) Upload all vert/index info to the VB and IB's, and DIP after everything has been processed?

Share this post


Link to post
Share on other sites
If I understand the question correctly, then I'd prefer option A. That way, the GPU can go to work on the data you've sent it while you work on the new data for it in parallel.

Share this post


Link to post
Share on other sites
Option (A) is better.
You want the CPU and GPU running at the same time if possible. You can upload vertex and index data to the GPU while it is drawing if you are careful with your lock flags, etc.

I don't completely understand your question though... if you have a mesh, its VB and IB should already in video memory? Unless you are using those silly managed resources :)

But the standard rule of thumb always applies: it depends on too many factors, the only way to be sure is testing and benchmarks. It could very easily be different for different vid. cards as well.

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

Sign in to follow this