(1 * 5 * 9 * 13 * 17 * ...) * (2 * 6 * 10 * 14 * 18 * ...) * (3 * 7 * 11 * 15 * 19 * ...) * (4 * 8 * 12 * 16 * 20 * ...)

(it's not precisely that, but close enough)

It isn't optimal however, optimal code would be pre-computed results (signed integer overflow is undefined, so n <= 12 is defined)

(if signed integer overflow would be defined to be 2's complement overflow, you can still use a table, as n > 33 gives 0)

1. Turned from recursive form into iterative form 2. Unrolled heavily 3. Autovectorized (!)

The throughput will be substantially more than the simple version.

https://godbolt.org/g/ORsX5h

vs. what it does with 64-bit ints:

https://godbolt.org/g/2wBzn3

Can anybody explain the 32 bit version?