The "Lenna" test image has been deprecated for several years at this
point in the computer graphics scientific community for being an
unauthorized, cropped scan of a Playboy magazine that is not only legally
problematic regarding redistribution (see #661) but also raises questions
about the appropriateness of using originally pornographic material in
scientific literature. **If scientific journals now find it unacceptable,
so should we, and we should do better**.
The image itself has been long gone from the repo itself following #661,
but it's still present in a screenshot attached to the documentation.
Although that resolved legal issues for Debian packaging, I think the
fundamental problem with the Lenna image remains unsolved, and over the
past 8 years the scientific consensus (and more importantly, the
sentiment from the model herself, Lena Forsén) has been very clear that
we shouldn't use this image in any shape or form now. So let's replace it
with something actually wholesome and thematically appropriate!
Instead, I've taken a screenshot of `gr.py`, but with Lenna replaced with
a photo of a friend's cat. I took the original photo myself and licensed
it under CC0 — no attribution is required, though it would certainly be
welcome. Some minor things about the composition have been changed, such
as the proportions of the images and the font used (sorry, I don't know
which font the original used, I'm using Iosevka here since it's my system
monospace font), but overall it shows off the capabilities of the
Graphics Protocol as well as the original.
Please let me know of any feedback regarding the image selection and the
composition, but I think this is a worthy step to take.
Optimise the AVX 2 implementation reducing number of operations per block
and also add an AVX-512 implementation used when the CPU supports it at
runtime.
Mostly comes from detecting the case of runs of ASCII printable
characters and using a special fast path for them. Improves benchmarks
as per benchmark.py by 15-30% for text heavy workloads
