Does swap buffer with vsynch guarantee synchronization?

1
votes

I was wondering if I could assume that all buffer related GPU operations such as:

  • glDrawElements
  • glBufferData
  • glSubBufferData
  • glUnmapBuffer

are guaranteed to be completed after swap buffer is performed (i.e. frame is finished) assuming vsync is on.

I'm confused as I've come across implementations of vertex streaming techniques such as rond robin vbo which imply that a vbo could still be in use during the next frame.

What I basically want to do is stream vertices through glMapBufferRange with GL_UNSYNCHRONIZED_BIT, managing the correct ranges myself so that writes and reads never overlap. This would work very well if I could just assume synchronization and reset the stream range index at the end of the frame.

In other words, does swap buffer with vsynch guarantee synchronization?

1
opengl

1 Answers

3
votes

glDrawElements glBufferData glSubBufferData glUnmapBuffer are guaranteed to be completed after swap buffer is performed (i.e. frame is finished) assuming vsync is on.

No; that would be terrible for performance. That would basically impose a full GPU/CPU synchronization simply because someone wants to display a new image. Even though both the production of that image and its display are GPU processes (or at least, not necessarily synchronous with your CPU thread/process).

The point of vsync is to ensure that the new image doesn't get swapped in until the vertical synchronization period, to avoid visual tearing of the image, where half of the display comes from the old and half from the new. This is not about ensuring that anything has actually completed on the GPU relative to CPU execution.

If you are streaming data into buffer objects via persistent mapping (which should be preferred over older "unsychronized" shenanigans), then you need to perform the synchronization yourself. Set a fence sync object after you have issued the rendering commands that will use data from the buffer region you wrote to. Then when it comes time to try to write to that buffer region again, check the fence sync and wait until its available. This also gives you the freedom to expand the number of such buffer regions you have if rendering is consistently delayed.