I am using Centos 6.7, kernel 2.6.32-573.3.1.el6.x86_64, OFED 3.18-1.
I have a __m512d intrinsic vector and I need sum of his elements. Is there any easy way to do this? I am concentrated on a performance of computation, so i need to do this operation quickly.
I have purchased 3x Xeon Phi 3120P.
In the last couple of months we have captured a number of Black Belts on video.