ashvardanian/StringZilla: 10x faster string search, split, sort, and shuffle for long strings and multi-gigabyte files in Python and C, leveraging SIMD with Arm Neon and x86 AVX2 & AVX-512 intrinsics
StringZilla uses a heuristic so simple it's almost stupid... but it works. It matches the first few letters of words with hyper-scalar code to achieve speeds. The implementation fits into a single C 99 header file and uses different SIMD flavors and SWAR on older platforms.