Intrinsics for Integer Bit Rotation 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_rol_epi32, _mm512_mask_rol_epi32, _mm512_maskz_rol_epi32

Rotates bits of int32 source elements left by specified count.

VPROLD

_mm512_rol_epi64, _mm512_mask_rol_epi64, _mm512_maskz_rol_epi64

Rotates bits of int64 source elements left by specified count.

VPROLQ

_mm512_rolv_epi32, _mm512_mask_rolv_epi32, _mm512_maskz_rolv_epi32

Rotates bits of int32 source elements left by specified count.

VPROLVD

_mm512_rolv_epi64, _mm512_mask_rolv_epi64, _mm512_maskz_rolv_epi64

Rotates bits of int64 source elements left by specified count.

VPROLVQ

_mm512_ror_epi32, _mm512_mask_ror_epi32, _mm512_maskz_ror_epi32

Rotates bits of int32 source elements right by specified count.

VPRORD

_mm512_ror_epi64, _mm512_mask_ror_epi64, _mm512_maskz_ror_epi64

Rotates bits of int64 source elements right by specified count.

VPRORQ

_mm512_rorv_epi32, _mm512_mask_rorv_epi32, _mm512_maskz_rorv_epi32

Rotates bits of int32 source elements right by specified count.

VPRORVD

_mm512_rorv_epi64, _mm512_mask_rorv_epi64, _mm512_maskz_rorv_epi64

Rotates bits of int64 source elements right by specified count.

VPRORVQ


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

8-bit immediate integer specifies offset for destination


_mm512_rol_epi32

extern __m512i __cdecl _mm512_rol_epi32(__m512i a, const int imm);

Rotates bits in each packed int32 element in a to the left by the number of bits specified in imm, and stores the results.


_mm512_mask_rol_epi32

extern __m512i __cdecl _mm512_mask_rol_epi32(__m512i src, __mmask16 k, __m512i a, const int imm);

Rotates bits in each packed int32 element in a to the left by the number of bits specified in imm, and stores the results using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_rol_epi32

extern __m512i __cdecl _mm512_maskz_rol_epi32(__mmask16 k, __m512i a, const int imm);

Rotates bits in each packed int32 element in a to the left by the number of bits specified in imm, and stores the results using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_rol_epi64

extern __m512i __cdecl _mm512_rol_epi64(__m512i a, const int imm);

Rotates bits in each packed int64 element in a to the left by the number of bits specified in imm, and stores the results.


_mm512_mask_rol_epi64

extern __m512i __cdecl _mm512_mask_rol_epi64(__m512i src, __mmask8 k, __m512i a, const int imm);

Rotates bits in each packed int64 element in a to the left by the number of bits specified in imm, and stores the results using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_rol_epi64

extern __m512i __cdecl _mm512_maskz_rol_epi64(__mmask8 k, __m512i a, const int imm);

Rotates bits in each packed int64 element in a to the left by the number of bits specified in imm, and stores the results using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_rolv_epi32

extern __m512i __cdecl _mm512_rolv_epi32(__m512i a, __m512i b);

Rotates bits in each packed int32 element in a to the left by the number of bits specified in the corresponding element of b, and stores the results.


_mm512_mask_rolv_epi32

extern __m512i __cdecl _mm512_mask_rolv_epi32(__m512i src, __mmask16 k, __m512i a, __m512i b);

Rotates bits in each packed int32 element in a to the left by the number of bits specified in the corresponding element of b, and stores the results using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_rolv_epi32

extern __m512i __cdecl _mm512_maskz_rolv_epi32(__mmask16 k, __m512i a, __m512i b);

Rotates bits in each packed int32 element in a to the left by the number of bits specified in the corresponding element of b, and stores the results using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_rolv_epi64

extern __m512i __cdecl _mm512_rolv_epi64(__m512i a, __m512i b);

Rotates bits in each packed int64 element in a to the left by the number of bits specified in the corresponding element of b, and stores the results.


_mm512_mask_rolv_epi64

extern __m512i __cdecl _mm512_mask_rolv_epi64(__m512i src, __mmask8 k, __m512i a, __m512i b);

Rotates bits in each packed int64 element in a to the left by the number of bits specified in the corresponding element of b, and stores the results using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_rolv_epi64

extern __m512i __cdecl _mm512_maskz_rolv_epi64(__mmask8 k, __m512i a, __m512i b);

Rotates bits in each packed int64 element in a to the left by the number of bits specified in the corresponding element of b, and stores the results using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_ror_epi32

extern __m512i __cdecl _mm512_ror_epi32(__m512i a, int imm);

Rotates bits in each packed int32 element in a to the right by the number of bits specified in imm, and stores the results.


_mm512_mask_ror_epi32

extern __m512i __cdecl _mm512_mask_ror_epi32(__m512i src, __mmask16 k, __m512i a, int imm);

Rotates bits in each packed int32 element in a to the right by the number of bits specified in imm, and stores the results using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_ror_epi32

extern __m512i __cdecl _mm512_maskz_ror_epi32(__mmask16 k, __m512i a, int imm);

Rotates bits in each packed int32 element in a to the right by the number of bits specified in imm, and stores the results using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_ror_epi64

extern __m512i __cdecl _mm512_ror_epi64(__m512i a, int imm);

Rotates bits in each packed int64 element in a to the right by the number of bits specified in imm, and stores the results.


_mm512_mask_ror_epi64

extern __m512i __cdecl _mm512_mask_ror_epi64(__m512i src, __mmask8 k, __m512i a, int imm);

Rotates bits in each packed int64 element in a to the right by the number of bits specified in imm, and stores the results using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_ror_epi64

extern __m512i __cdecl _mm512_maskz_ror_epi64(__mmask8 k, __m512i a, int imm);

Rotates bits in each packed int64 element in a to the right by the number of bits specified in imm, and stores the results using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_rorv_epi32

extern __m512i __cdecl _mm512_rorv_epi32(__m512i a, __m512i b);

Rotates bits in each packed int32 element in a to the right by the number of bits specified in the corresponding element of b, and stores the results.


_mm512_mask_rorv_epi32

extern __m512i __cdecl _mm512_mask_rorv_epi32(__m512i src, __mmask16 k, __m512i a, __m512i b);

Rotates bits in each packed int32 element in a to the right by the number of bits specified in the corresponding element of b, and stores the results using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_rorv_epi32

extern __m512i __cdecl _mm512_maskz_rorv_epi32(__mmask16 k, __m512i a, __m512i b);

Rotates bits in each packed int32 element in a to the right by the number of bits specified in the corresponding element of b, and stores the results using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_rorv_epi64

extern __m512i __cdecl _mm512_rorv_epi64(__m512i a, __m512i b);

Rotates bits in each packed int64 element in a to the right by the number of bits specified in the corresponding element of b, and stores the results.


_mm512_mask_rorv_epi64

extern __m512i __cdecl _mm512_mask_rorv_epi64(__m512i src, __mmask8 k, __m512i a, __m512i b);

Rotates bits in each packed int64 element in a to the right by the number of bits specified in the corresponding element of b, and stores the results using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_rorv_epi64

extern __m512i __cdecl _mm512_maskz_rorv_epi64(__mmask8 k, __m512i a, __m512i b);

Rotates bits in each packed int64 element in a to the right by the number of bits specified in the corresponding element of b, and stores the results using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



Para obtener información más completa sobre las optimizaciones del compilador, consulte nuestro Aviso de optimización.