Re: [eigen] Matrix multiplication much slower on MSVC than on g++/clang

[ Thread Index | Date Index | More Archives ]

On 2/9/2018 3:16 AM, Gael Guennebaud wrote:

    That works! For detection, the documentation at
    <> suggests that
    perhaps this will work:

    #if defined(_MSC_VER) && defined(__AVX2__)
    #define __FMA__

To implement that we need to make sure that on all architectures AVX2 => FMA. This seems to be true for Intel's ones, but I'm not sure about AMD.

According to , all AMD processors which support AVX2 support FMA. Unfortunately, I couldn't easily confirm through official online resources. The wikipedia page on Advanced_Vector_Extensions notes that only AMD Excavactor processors (and up) support AVX2, and those definitely support FMA (double-checked at


Mail converted by MHonArc 2.6.19+