Wolfgang Straßer's PhD thesis: isgwww.cs.uni-magdeburg.de/graphics/mis... (in German),
Beginning of computer graphics in Germany: ohiostate.pressbooks.pub/app/uploads/...
Ed Catmull's PhD thesis: ohiostate.pressbooks.pub/app/uploads/... 4/4

More recently, with programmable pipelines, hi-z and early-z modes were added that do the z-testing and hidden surface elimination per tile and per pixel, before the pixel shader is executed, that actually reduce the cost of rendering and make polygon sorting important again. 3/4

It requires no polygon sorting like previous methods for correct rendering, but in a brute force fashion stores a per pixel minimum distance to the camera to compare new pixels' depth against. As it was meant for correctness and not performance it was done at the end of the pipeline. 2/4

Thanks Alex, I haven't seen that paper, thanks for sharing!

VRS does free up GPU resources though (SM and VGPR), and in such cases, we could run an async compute job over the gbuffer pass to make use of it. 3/3

The reason for not doing 75% less work (the 2x2 rate implies) is that VRS always reverts to full rate on geometry edges to preserve them, so it's efficiency depends on triangle size on screen. For that particular pass screenpipe throughput doesn't improve and it's only ~11% faster in the end. 2/3

Don't be nervous, that you got an interview means they saw something they like in your CV. Whatever your experience, make sure that you can talk confidently about it and reason about any choices. Even if you get a Q you can't answer that'll likely be fine, it's the whole presentation that matters.