The talk at rubyconf mentioned that `string.scan` was 100% faster due to specialized string implementations in the Rust backend. I wonder if there are any performance gains from the actual runtime rather than from std optimizations?
MRI took 89ms/iter to scan for a regex pattern over 6.8MB of text, while Artichoke took 48ms/iter [0]
At least for me 100% faster does not mean the same as 100% less time was needed.