Developer Guide and Reference

Contents

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.
To use these intrinsics, include the
immintrin.h
file as follows:
#include <immintrin.h>
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_pd

extern __m128d _mm_undefined_pd(void);
Returns a vector of two double precision floating point elements. The content of the vector is not specified.

_mm_undefined_si128

extern __m128i _mm_undefined_si128(void);
Returns a vector of four packed doubleword integer elements. The content of the vector is not specified.

Product and Performance Information

1

Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.

Notice revision #20110804