This content has not been validated; it was AI-generated following the x86-64 ISA Documentation generation process to maintain high quality. However, as no human has verified this data, errors may exist. If the accuracy of this data is critical, please consult the Intel SDM. The model used to generate this is gemma4:31b

VRCP14SD

Computes the reciprocal of a scalar double-precision floating-point value with a relative error of less than $2^{-14}$.

The table after the description covers what the source and destinations can be.

DO NOT support LOCK

This instruction is available only in 64-bit mode or compatibility mode. It requires CPUID.F5H.VEX extension support.

The instruction does not perform full IEEE 754 compliance; it provides an approximation. To achieve higher precision, the result MUST be used as an initial guess for a Newton-Raphson iteration. The instruction does not signal floating-point exceptions such as #Z, #D, #O, or #U. Only #P may be signaled depending on the precision of the approximation.