Function core_arch::x86::_MM_TRANSPOSE4_PS

pub unsafe fn _MM_TRANSPOSE4_PS(
    row0: &mut __m128, 
    row1: &mut __m128, 
    row2: &mut __m128, 
    row3: &mut __m128
)

This is supported on x86 and target feature sse only.

Transpose the 4x4 matrix formed by 4 rows of __m128 in place.

Intel's documentation