Intel® C++ Compiler Classic Developer Guide and Reference

ID 767249
Date 7/13/2023
Public
Document Table of Contents

Intrinsics for Integer Pack and Unpack Operations

The prototypes for Intel® Advanced Vector Extensions 512 (Intel® AVX-512) intrinsics are located in the zmmintrin.h header file.

To use these intrinsics, include the immintrin.h file as follows:

#include <immintrin.h>


Intrinsic Name

Operation

Corresponding
Intel® AVX-512 Instruction

_mm512_unpackhi_epi32, _mm512_mask_unpackhi_epi32, _mm512_maskz_unpackhi_epi32

Unpacks and interleaves high packed int32 values.

VPUNPCKHQD, VUNPCKHQD, UNPCKHQD

_mm512_unpackhi_epi64, _mm512_mask_unpackhi_epi64, _mm512_maskz_unpackhi_epi64

Unpacks and interleaves high packed int64 values.

VPUNPCKHQDQ, VUNPCKHQDQ, UNPCKHQDQ

_mm512_unpacklo_epi32, _mm512_mask_unpacklo_epi32, _mm512_maskz_unpacklo_epi32

Unpacks and interleaves low packed int32 values.

VPUNPCKLQD, VUNPCKLQD, UNPCKLQD

_mm512_unpacklo_epi64, _mm512_mask_unpacklo_epi64, _mm512_maskz_unpacklo_epi64

Unpacks and interleaves low packed int64 values.

VPUNPCKLQDQ, VUNPCKLQDQ, UNPCKLQDQ


variable definition
k

writemask used as a selector

a

first source vector element

b

second source vector element

src

source element to use based on writemask result


_mm512_unpackhi_epi32

extern __m512i __cdecl _mm512_unpackhi_epi32(__m512i a, __m512i b);

Unpacks and interleaves int32 elements from the high half of each 128-bit lane in a and b, and stores the result.


_mm512_mask_unpackhi_epi32

extern __m512i __cdecl _mm512_mask_unpackhi_epi32(__m512i src, __mmask16 k, __m512i a, __m512i b);

Unpacks and interleaves int32 elements from the high half of each 128-bit lane in a and b, and stores the result using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_unpackhi_epi32

extern __m512i __cdecl _mm512_maskz_unpackhi_epi32(__mmask16 k, __m512i a, __m512i b);

Unpacks and interleaves int32 elements from the high half of each 128-bit lane in a and b, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_unpackhi_epi64

extern __m512i __cdecl _mm512_unpackhi_epi64(__m512i a, __m512i b);

Unpacks and interleaves int64 elements from the high half of each 128-bit lane in a and b, and stores the result.


_mm512_mask_unpackhi_epi64

extern __m512i __cdecl _mm512_mask_unpackhi_epi64(__m512i src, __mmask8 k, __m512i a, __m512i b);

Unpacks and interleaves int64 elements from the high half of each 128-bit lane in a and b, and stores the result using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_unpackhi_epi64

extern __m512i __cdecl _mm512_maskz_unpackhi_epi64(__mmask8 k, __m512i a, __m512i b);

Unpacks and interleaves int64 elements from the high half of each 128-bit lane in a and b, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_unpacklo_epi32

extern __m512i __cdecl _mm512_unpacklo_epi32(__m512i a, __m512i b);

Unpacks and interleaves int32 elements from the low half of each 128-bit lane in a and b, and stores the result.


_mm512_mask_unpacklo_epi32

extern __m512i __cdecl _mm512_mask_unpacklo_epi32(__m512i src, __mmask16 k, __m512i a, __m512i b);

Unpacks and interleaves int32 elements from the low half of each 128-bit lane in a and b, and stores the result using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_unpacklo_epi32

extern __m512i __cdecl _mm512_maskz_unpacklo_epi32(__mmask16 k, __m512i a, __m512i b);

Unpacks and interleaves int32 elements from the low half of each 128-bit lane in a and b, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_unpacklo_epi64

extern __m512i __cdecl _mm512_unpacklo_epi64(__m512i a, __m512i b);

Unpacks and interleaves int64 elements from the low half of each 128-bit lane in a and b, and stores the result.


_mm512_mask_unpacklo_epi64

extern __m512i __cdecl _mm512_mask_unpacklo_epi64(__m512i src, __mmask8 k, __m512i a, __m512i b);

Unpacks and interleaves int64 elements from the low half of each 128-bit lane in a and b, and stores the result using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_unpacklo_epi64

extern __m512i __cdecl _mm512_maskz_unpacklo_epi64(__mmask8 k, __m512i a, __m512i b);

Unpacks and interleaves int64 elements from the low half of each 128-bit lane in a and b, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).