I can't tell from your GLSL if these would have forced FMAs for a lot of the intermediate product sums. That would probably be a non-trivial effect, particularly for your large anisotropy cases.
The Heckbert paper also describes the basic theory, but you would want to supplement with some of the offline rendering work that followed it. OpenImageIO (OIIO) is pretty widely used, and has gone through several iterations of bug fixing like https://github.com/AcademySoftwareFoundation/OpenImageIO/pul...
But for your purposes, you probably just need to find all the magic epsilons and sign checks to make it match.
Btw, in case you're not aware, the article is somewhat unreadable on mobile devices because the code blocks can't be scrolled horizontally, so half of the code just doesn't fit on the screen. Also, the long latex formula overflows the screen and causes the entire page to move horizontally.
Perfect blog post for HN IMO - any blog title involving "in too much detail" will probably do well! Great job with the post, the visualizations are fantastic.
This is great! Would've been really useful a couple months ago when I was refactoring Lavapipe's texture filtering. I worked off the Vulkan spec, which doesn't mention the elliptical transformation. I did notice that the spec says:
> The minimum and maximum scale factors (ρmin, ρmax) should be the minor and major axes of this ellipse.
Where "should" probably means some transformation can be applied (would be "must" otherwise).
Now I'm tempted to implement your visualizations so I can compare my work to your hardware references, and spend more hours getting it closer to actual hardware.
I have a hunch nvidia's mipmapping algorithm changes if you open nvidia control panel and change texture filtering to "high performance" vs "high quality"
Totally fantastic article. I don't do work that overlaps with this at all, but even after 37+ years as a C++ programmer, I found this enlightening, engaging and informative. Thank you very much.
I for one liked the article! Great visualisations.
There's a bit of nostalgia ;) Brought me back to the days where GL display lists were the fancy thing to do and any kind of non-ff shader were but a wild dream.
This is very relevant to what I'm doing. I'm trying to reproduce the MIP pipeline to get anti-aliased procedural details in fragment. specifically converting high frequency details into roughness.
I didn't even read what these circle images mean, but it's fun to see that AMD and Adreno look the same... because Adreno is AMD / ATI's old mobile architecture that was sold off a long time ago (and an anagram of Radeon).
Insane deep-dive! Framing texture sampling as "Ideally, we’d like to integrate over the projection of the screen pixel onto the texture" was enlightening for me. I particularly enjoyed the explanation of anisotropic filtering because it always seemed like magic to me, and in the context of aligning ellipses on textures it just makes sense :D
There simply isn't another way to access registers from one 'thread' on another thread without using an intrinsic. You need that to calculate finite differences. For a long time, the only option was ddx()/ddy(). Now we also wave intrinsics, which you couldn't implement yourself either.
You need to access the neighboring pixels (fragments) in a quad to compute d_dx and d_dy, but quads are an implementation detail not exposed to the programmer.
This isn't my specialty, and ultimately it really doesn't matter to the core point of this good submission about how the GPU chooses mipmap level to use, however the article gives the impression that we pre-calculate mipmap levels to improve distant aliasing, though the problem they demonstrate is solved with trivial texture filtering.
Mipmaps are a performance optimization[1]. You could just use a 4096x4096 brick texture across your entire game, and then use texture filtering to make it look good both close and far, but that means that rendering a distant wall polygon that might fill just a few pixels of the viewport needs to filter and apply a 16.7 million texel texture, redoing the filtering again and again and evicting everything else from caches just for that one texture. If instead it can apply a 32x32 pre-filtered texture to loads of distant objects, there are obviously massive performance ramifications. Which is why mipmaps are used, letting massive textures be used for those cases where the detail is valuable, without destroying performance when it's just some distant object.
And of course modern engines do the same thing with geometry now, where ideally there is hierarchy of differing level of detail geometry and it will choose the massive-vertices object when it fills the scene, and the tiny, super optimized one when it's just a few pixels.
[1] As one additional note, all major graphics platforms can automatically generate mipmaps for textures...but only if the root is uncompressed. Modern texture compression is hugely compute bound and yields major VRAM savings so almost all games pre-compute the mipmapping and then do the onerous compression in advance.
I agree that mipmapping is an optimization, but I also don't really consider it incorrect or misleading to call it a technique for mitigating aliasing - it's a practical technique for doing so. Fair point though, and perhaps I should have mentioned this.
reply