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_broadcast_f32x4, _mm512_mask_broadcast_f32x4, _mm512_maskz_broadcast_f32x4

Broadcast float32 element to four destination locations.

VBROADCASTF32X4

_mm512_broadcast_f64x4, _mm512_mask_broadcast_f64x4, _mm512_maskz_broadcast_f64x4

Broadcast float64 element to four destination locations.

VBROADCASTF64X4

_mm512_broadcastsd_pd, _mm512_mask_broadcastsd_pd, _mm512_maskz_broadcastsd_pd

Broadcast packed float64 element to all destination locations.

VBROADCASTSD

_mm512_broadcastss_ps, _mm512_mask_broadcastss_ps, _mm512_maskz_broadcastss_ps

Broadcast packed float32 element to all destination locations.

VBROADCASTSS


variable definition
k

writemask used as a selector

a

first source vector element

src

source element to use based on writemask result


_mm512_broadcast_f32x4

extern __m512 __cdecl _mm512_broadcast_f32x4(__m128 a);

Broadcasts four packed float32 elements from a to all destination elements.



_mm512_mask_broadcast_f32x4

extern __m512 __cdecl _mm512_mask_broadcast_f32x4(__m512 src, __mmask16 k, __m128 a);

Broadcasts four packed float32 elements from a to all destination elements using writemask k (elements are copied from src when the corresponding mask bit is not set).



_mm512_maskz_broadcast_f32x4

extern __m512 __cdecl _mm512_maskz_broadcast_f32x4(__mmask16 k, __m128 a);

Broadcasts four packed float32 elements from a to all destination elements using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_broadcast_f64x4

extern __m512d __cdecl _mm512_broadcast_f64x4(__m256d a);

Broadcasts four packed float64 elements from a to all destination elements.



_mm512_mask_broadcast_f64x4

extern __m512d __cdecl _mm512_mask_broadcast_f64x4(__m512d src, __mmask8 k, __m256d a);

Broadcasts four packed float64 elements from a to all destination elements using writemask k (elements are copied from src when the corresponding mask bit is not set).



_mm512_maskz_broadcast_f64x4

extern __m512d __cdecl _mm512_maskz_broadcast_f64x4(__mmask8 k, __m256d a);

Broadcasts four packed float64 elements from a to all destination elements using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_broadcastsd_pd

extern __m512d __cdecl _mm512_broadcastsd_pd(__m128d a);

Broadcasts low float64 element from a to all destination elements.



_mm512_mask_broadcastsd_pd

extern __m512d __cdecl _mm512_mask_broadcastsd_pd(__m512d src, __mmask8 k, __m128d a);

Broadcasts low float64 element from a to all destination elements using writemask k (elements are copied from src when the corresponding mask bit is not set).



_mm512_maskz_broadcastsd_pd

extern __m512d __cdecl _mm512_maskz_broadcastsd_pd(__mmask8 k, __m128d a);

Broadcasts low float64 element from a to all destination elements using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_broadcastss_ps

extern __m512 __cdecl _mm512_broadcastss_ps(__m128 a);

Broadcasts low float32 element from a to all destination elements.



_mm512_mask_broadcastss_ps

extern __m512 __cdecl _mm512_mask_broadcastss_ps(__m512 src, __mmask16 k, __m128 a);

Broadcasts low float32 element from a to all destination elements using writemask k (elements are copied from src when the corresponding mask bit is not set).



_mm512_maskz_broadcastss_ps

extern __m512 __cdecl _mm512_maskz_broadcastss_ps(__mmask16 k, __m128 a);

Broadcasts low float32 element from a to all destination elements using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



Para obter informações mais completas sobre otimizações do compilador, consulte nosso aviso de otimização.