I don't know why you insist that much on bandwidth.

Alright I ran your numbers, you've convinced me it isn't as big an issue as I thought it to be... but I'm hazy on one figure of yours.

edit - also didn't you forget to take into account the Hi-Z buffer bandwidth for per triangle depth culling?

Yes I did. I don't know the exact memory footprint, but 33.33% overhead (like in mipmapping) sounds like a reasonable estimate.

How did you get the 309MB per frame figure? When I did it I'm getting completely different numbers.
edit - specifically the 305MB number.

Thanks for pointing it out.

1.000.000 * 32 bytes = 30.51MB... dammit I added a 0 and considered 10 million vertices.
The 305MB came from 10 million vertices, not 1 million.
Well... crap.

For 10 million vertices it's 35MB of index data, not 3.5MB. But for 1 million vertices, it's 30.51 MB, not 305.5MB

It only makes it easier to prove. Like I said, at 1920x1080 there shouldn't be much more than 2 million vertices (since there would be one vertex per pixel). Maybe 3 million? Profiling would be needed
So if you provide a massive amount of input vertices (such as 10 million vertices), the culler will end up discarding a lot of vertices.

Yes I did. I don't know the exact memory footprint, but 33.33% overhead (like in mipmapping) sounds like a reasonable estimate.

Are you talking about the generation of the Hi-Z buffer or the per triangle fetch.from the Hi-z buffer? The generation I presume... the per triangle lookup is 32bytes minimum.

edit - might be wrong about that, might be 16bytes per.

It only makes it easier to prove.

I know, that's why I came around to thinking bandwidth wouldn't be a problem except in like you said earlier games with tons of geometry.

Like I said, at 1920x1080 there shouldn't be much more than 2 million vertices (since there would be one vertex per pixel)

2 million tops visible... but overlapping geometry... it all depends how much coarse culling you're doing.

Thanks again I had a knee jerk reaction, running the numbers grounded me.

For those interested it looks like AMD has updated their GeometryFX compute triangle filtering library with cluster based culling as well. FYI it uses AMD's proprietary AGS (AMD GPU Services) library so its platform specific. But its a nice source to learn from if interested.

edit - forgot link - https://github.com/GPUOpen-Effects/GeometryFX/

and just in case http://gpuopen.com/gaming-product/geometryfx/