On Wednesday, 3 August 2016 at 22:22:19 UTC, Johan Engelen wrote:
On Wednesday, 3 August 2016 at 20:53:59 UTC, Ilya Yaroshenko
Dot Product:

       ndReduce vectorized = 3 ms, 314 μs
                  ndReduce = 14 ms, 767 μs

**That's** the difference with or without fastmath??

The first one is with @fastmath and addition execution branch for iteration in case of stride equal to 1.

Reply via email to