https://bugs.freedesktop.org/show_bug.cgi?id=37142
--- Comment #4 from Pierre-Eric Pelloux-Prayer pelloux@gmail.com 2011-05-12 13:27:09 PDT --- (In reply to comment #2)
(In reply to comment #0)
What do you think ?
You can't optimize the uploads because the sizes of all buffers are not known when glLockArraysEXT is called. The only things you've got are pointers to the buffers.
Sure, but I was thinking to something more like : - glLockArraysEXT does nothing more than curently - uploading a vertex buffer is done as before except in one case : when trying to upload the same buffer AND glLock is enabled => the uploading is skipped as data is already in GPU memory (which is the case shown in the attached trace file)