|Re: [eigen] Array of complex numbers|
[ Thread Index |
| More lists.tuxfamily.org/eigen Archives
I would never try to get gcc or clang vectorize efficiently a loop. I tend to only use Intel compilers when I want to get efficient vectorization without writing intrinsics.
> On 10 Jan 2019, at 23:33, Gael Guennebaud <gael.guennebaud@xxxxxxxxx> wrote:
> hm... actually that's not that bad as clang is able to move two of the three permutations out of the loop, we only have to pay for a single extra permutation per product. With gcc, the overhead is quite significant.