Parapply

200 ms ± 83.5 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
---- Doing length: 5000000.0 ----
pd Series performance:

The slowest run took 4.05 times longer than the fastest. This could mean that an intermediate result is being cached.
175 ms ± 110 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
---- Doing length: 1000000.0 ----
pd Series performance:
188 ms ± 4.48 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
parapply [4, 8, 16, 24, 48] performance:
227 ms ± 2.43 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
81 ms ± 1.83 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)

The slowest run took 5.55 times longer than the fastest. This could mean that an intermediate result is being cached.
143 ms ± 118 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
---- Doing length: 100000.0 ----
pd Series performance: