Intel® C++ Compiler Classic Developer Guide and Reference

ID 767249
Date 3/31/2023
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents

Intrinsics for Integer Shuffle 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_shuffle_epi32, _mm512_mask_shuffle_epi32, _mm512_maskz_shuffle_epi32

Shuffle int32 vectors within 128-bit lanes using control value.

VPSHUFD

_mm512_shuffle_i32x4, _mm512_mask_shuffle_i32x4, _mm512_maskz_shuffle_i32x4

Shuffle four int32 values by specified value.

VSHUFI32X4

_mm512_shuffle_i64x2, _mm512_mask_shuffle_i64x2, _mm512_maskz_shuffle_i64x2

Shuffle two int64 values by specified value.

VSHUFI64X2


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

imm

control value for shuffle operation


_mm512_shuffle_epi32

extern __m512i _cdecl __m512_shuffle_epi32(__m512i a, _MM_PERM_ENUM imm);

Shuffles int32 in a within 128-bit lanes using the control in imm, and stores the result.

_mm512_mask_shuffle_epi32

extern __m512i _cdecl __m512_mask_shuffle_epi32(__m512i src, __mmask16 k, __m512i a, _MM_PERM_ENUM imm);

Shuffles int32 in a within 128-bit lanes using the control in imm, and stores the result using writemask k (elements are copied from src when the corresponding mask bit is not set).

_mm512_maskz_shuffle_epi32

extern__m512i _cdecl __m512_maskz_shuffle_epi32(__mmask16 k, __m512i a, _MM_PERM_ENUM imm);

Shuffles int32 in a within 128-bit lanes using the control in imm, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).

_mm512_shuffle_i32x4

extern __m512i _cdecl __m512_shuffle_i32x4(__m512i a, __m512i b, _MM_PERM_ENUM imm);

Shuffles 128-bits (composed of four int32) selected by imm from a and b, and stores the result.

_mm512_mask_shuffle_i32x4

extern __m512i _cdecl __m512_mask_shuffle_i32x4(__m512i src, __mmask16 k, __m512i a, __m512i b, _MM_PERM_ENUM imm);

Shuffles 128-bits (composed of four int32) selected by imm from 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_shuffle_i32x4

extern __m512i _cdecl __m512_maskz_shuffle_i32x4(__mmask16 k, __m512i a, __m512i b, _MM_PERM_ENUM imm);

Shuffles 128-bits (composed of four int32) selected by imm from a and b, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).

_mm512_shuffle_i64x2

extern __m512i _cdecl __m512_shuffle_i64x2(__m512i a, __m512i b, _MM_PERM_ENUM imm);

Shuffles 128-bits (composed of two int64) selected by imm from a and b, and stores the result.

_mm512_mask_shuffle_i64x2

extern __m512i _cdecl __m512_mask_shuffle_i64x2(__m512i src, __mmask8 k, __m512i b, __m512i b, _MM_PERM_ENUM imm);

Shuffles 128-bits (composed of two int64) selected by imm from 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_shuffle_i64x2

extern __m512i _cdecl __m512_maskz_shuffle_i64x2(__mmask8 k, __m512i a, __m512i b, _MM_PERM_ENUM imm);

Shuffles 128-bits (composed of two int64) selected by imm from a and b, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).