https://gcc.gnu.org/bugzilla/show_bug.cgi?id=93594
--- Comment #11 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
I know the missed optimization is fixed in GCC 10 at the RTL level.
But shouldn't these optimized at gimple level to similar to:
```
__m256i cvt_setr1(__m128i low)
{
return __builtin_shufflevector (low, _mm_setzero_si128(), 0, 1, 2, 3);
}
```
