Convert packed signed 32-bit integers in b to packed single-precision (32-bit) floating-point elements, store the results in the lower 2 elements, and copy the upper 2 packed elements from a to the upper elements of result.
See Implementation
Convert packed signed 32-bit integers in b to packed single-precision (32-bit) floating-point elements, store the results in the lower 2 elements, and copy the upper 2 packed elements from a to the upper elements of result.