Function vld1q_u32_x2_

src/cpu/kernels/CpuTransposeKernel.cpp:377–381

#ifdef __aarch64__
inline uint32x4x2_t vld1q_u32_x2_(const uint32_t *ptr)
{
    // gcc-7 doesn't support vld1q_u32_x2 instruction
    return {vld1q_u32(ptr), vld1q_u32(ptr + 4)};
}

inline void vst1q_u32_x2_(const uint32_t *ptr, const uint32x4x2_t &val)
{