inline xsimd::batch maddw()

in gemmology.h [673:677]

• 5 lines of code
• 1 McCabe index (conditional complexity)

inline xsimd::batch<int32_t, Arch> maddw(xsimd::batch<uint8_t, Arch> x,
                                         xsimd::batch<int8_t, Arch> y
                                         ) {
  return kernel::maddw(x, y, Arch{});
}