Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a` , and return the results. The maximum relative error for this approximation is less than 1.5*2^-12.
See Implementation
Compute the approximate reciprocal of packed single-precision (32-bit) floating-point elements in a` , and return the results. The maximum relative error for this approximation is less than 1.5*2^-12.