Function _mm_shldi_epi32 

pub fn _mm_shldi_epi32(a: __m128i, b: __m128i, const IMM8: i32) -> __m128i

Available on x86-64 and target feature avx512vbmi2 and target feature avx512vl only.

Concatenate packed 32-bit integers in a and b producing an intermediate 64-bit result. Shift the result left by imm8 bits, and store the upper 32-bits in dst.

Intel’s documentation