libdivide - optimization of integer division

libdivide is an C math library which optimizes integer division if the divisor is known at compile time.

libdivide's scalar code is up to 16 times faster for powers of 2, 10 times faster for non-powers of 2, compared to naive hardware division. Optimized vector code is a further 2-3 times faster.

Pretty cool to see these things still happening.