Intrinsics Returning Vectors of Undefined Values

These intrinsics generate vectors of undefined values. The result of the intrinsics is usually used as an argument to another intrinsic that requires all operands to be initialized, and when the content of a particular argument does not matter. These intrinsics are declared in the immintrin header file.

For example, you can use such an intrinsic when you need to calculate a sum of packed double-precision floating-point values located in the xmm register. To avoid unnecessary moves, you can use the following code to obtain the required result at the low 64 bits:

__m128d HILO	= doSomeWork();
__m128d HI 	= _mm_unpackhi_pd(HILO, _mm_undefined_pd());
__m128d result	= _mm_add_sd(HI, HILO);

_mm_undefined_ps()

This intrinsic returns a vector of four single precision floating point elements. The content of the vector is not specified.

Syntax

_mm_undefined_pd()

This intrinsic returns a vector of two double precision floating point elements. The content of the vector is not specified.

Syntax

_mm_undefined_si128()

This intrinsic returns a vector of four packed doubleword integer elements. The content of the vector is not specified.

Syntax