Function _mm256_insertf128_ps

#[target_feature(enable = "avx")]
pub const fn _mm256_insertf128_ps(a: __m256, b: __m128, IMM1: i32) -> __m256

Copies a to result, then inserts 128 bits (composed of 4 packed single-precision (32-bit) floating-point elements) from b into result at the location specified by imm8.

Intel's documentation