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_load_pd, _mm512_mask_load_pd, _mm512_maskz_load_pd

_mm512_store_pd, _mm512_mask_store_pd

Load/store aligned float64 values from memory.

MOVAPD

_mm512_load_ps, _mm512_mask_load_ps, _mm512_maskz_load_ps

_mm512_store_ps, _mm512_mask_store_ps

Load/store aligned float32 values from memory.

MOVAPS

_mm_mask_load_sd, _mm_maskz_load_sd

_mm_mask_store_sd

Load/store lower float64 values from memory.

VMOVSD

_mm_mask_load_ss, _mm_maskz_load_ss

_mm_mask_store_ss

Load/store lower float32 values from memory.

VMOVSS

_mm512_loadu_pd, _mm512_mask_loadu_pd, _mm512_maskz_loadu_pd

_mm512_storeu_pd, _mm512_mask_storeu_pd

Load/store unaligned float64 values from memory.

VMOVUPD

_mm512_loadu_ps , _mm512_mask_loadu_ps, _mm512_maskz_loadu_ps

_mm512_storeu_ps, _mm512_mask_storeu_ps

Load/store unaligned float32 values from memory.

VMOVUPS

_mm512_stream_pd

Store float64 values using non-temporal hint.

VMOVNTPD

_mm512_stream_ps

Store float32 values using non-temporal hint.

VMOVNTPS


variable definition
k

writemask used as a selector

a

first source vector element

src

source element to use based on writemask result

mem_addr

pointer to base address in memory


_mm512_load_pd

extern __m512d __cdecl _mm512_load_pd(void const* mem_addr);

Loads 512-bits (composed of eight packed float64 elements) from mem_addr into destination.

mem_addr must be aligned on a 64-byte boundary or a general-protection exception will be generated.


_mm512_mask_load_pd

extern __m512d __cdecl _mm512_mask_load_pd(__m512d src, __mmask8 k, void const* mem_addr);

Loads packed float64 elements from mem_addr into destination using writemask k (elements are copied from src when the corresponding mask bit is not set).

mem_addr must be aligned on a 64-byte boundary or a general-protection exception will be generated.


_mm512_maskz_load_pd

extern __m512d __cdecl _mm512_maskz_load_pd(__mmask8 k, void const* mem_addr);

Loads packed float64 elements from mem_addr into destination using zeromask k (elements are zeroed out when the corresponding mask bit is not set).

mem_addr must be aligned on a 64-byte boundary or a general-protection exception will be generated.



_mm512_load_ps

extern __m512 __cdecl _mm512_load_ps(void const* mem_addr);

Loads 512-bits (composed of sixteen packed float32 elements) from mem_addr into destination.

mem_addr must be aligned on a 64-byte boundary or a general-protection exception will be generated.


_mm512_mask_load_ps

extern __m512 __cdecl _mm512_mask_load_ps(__m512 src, __mmask16 k, void const* mem_addr);

Loads packed float32 elements from mem_addr into destination using writemask k (elements are copied from src when the corresponding mask bit is not set).

mem_addr must be aligned on a 64-byte boundary or a general-protection exception will be generated.


_mm512_maskz_load_ps

extern __m512 __cdecl _mm512_maskz_load_ps(__mmask16 k, void const*  mem_addr);

Loads packed float32 elements from mem_addr into destination using zeromask k (elements are zeroed out when the corresponding mask bit is not set).

mem_addr must be aligned on a 64-byte boundary or a general-protection exception will be generated.



_mm_mask_load_sd

extern __m128d __cdecl _mm_mask_load_sd(__m128d src, __mmask8 k, const double* mem_addr);

Loads float64 element from mem_addr into lower element of destination using writemask k (the element is copied from src when mask bit 0 is not set), and sets upper destination element to zero.

mem_addr must be aligned on a 16-byte boundary or a general-protection exception will be generated.


_mm_maskz_load_sd

extern __m128d __cdecl _mm_maskz_load_sd(__mmask8 k, const double* mem_addr);

Loads a float64 element from mem_addr into lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and sets upper destination elements to zero.

mem_addr must be aligned on a 16-byte boundary or a general-protection exception will be generated.


_mm_mask_load_ss

extern __m128 __cdecl _mm_mask_load_ss(__m128 src, __mmask8 k, const float* mem_addr);

Loads float32 element from mem_addr into lower destination element using writemask k (the element is copied from src when mask bit 0 is not set), and sets upper destination elements to zero.

mem_addr must be aligned on a 16-byte boundary or a general-protection exception will be generated.


_mm_maskz_load_ss

extern __m128 __cdecl _mm_maskz_load_ss(__mmask8 k, const float* mem_addr);

Loads float32 element from mem_addr into lower element of destination using zeromask k (the element is zeroed out when mask bit 0 is not set), and sets upper destination elements to zero.

mem_addr must be aligned on a 16-byte boundary or a general-protection exception will be generated.



_mm512_loadu_pd

extern __m512d __cdecl _mm512_loadu_pd(void const* mem_addr);

Loads 512-bits (composed of eight packed float64 elements) from mem_addr into destination.

mem_addr does not need to be aligned on any particular boundary.


_mm512_mask_loadu_pd

extern __m512d __cdecl _mm512_mask_loadu_pd(__m512d src, __mmask8 k, void const* mem_addr);

Loads packed float64 elements from mem_addr into destination using writemask k (elements are copied from src when the corresponding mask bit is not set).

mem_addr does not need to be aligned on any particular boundary.


_mm512_maskz_loadu_pd

extern __m512d __cdecl _mm512_maskz_loadu_pd(__mmask8 k, void const* mem_addr);

Loads packed float64 elements from mem_addr into destination using zeromask k (elements are zeroed out when the corresponding mask bit is not set).

mem_addr does not need to be aligned on any particular boundary.



_mm512_loadu_ps

extern __m512 __cdecl _mm512_loadu_ps(void const* mem_addr);

Loads 512-bits (composed of sixteen packed float32 elements) from mem_addr into destination.


_mm512_mask_loadu_ps

extern __m512 __cdecl _mm512_mask_loadu_ps(__m512 src, __mmask16 k, void const* mem_addr);

Loads packed float32 elements from mem_addr into destination using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_loadu_ps

extern __m512 __cdecl _mm512_maskz_loadu_ps(__mmask16 k, void const* mem_addr);

Loads packed float32 elements from mem_addr into destination using zeromask k (elements are zeroed out when the corresponding mask bit is not set).

mem_addr does not need to be aligned on any particular boundary.



_mm512_store_pd

extern void __cdecl _mm512_store_pd(void* mem_addr, __m512d a);

Stores 512-bits (composed of eight packed float64 elements) from a into mem_addr.


_mm512_mask_store_pd

extern void __cdecl _mm512_mask_store_pd(void* mem_addr, __mmask8 k, __m512d a);

Stores packed float64 elements from a into mem_addr using writemask k.

mem_addr must be aligned on a 64-byte boundary or a general-protection exception will be generated.



_mm512_store_ps

extern void __cdecl _mm512_store_ps(void* mem_addr, __m512 a);

Store 512-bits (composed of sixteen packed float32 elements) from a into mem_addr.

mem_addr must be aligned on a 64-byte boundary or a general-protection exception will be generated.



_mm512_mask_store_ps

extern void __cdecl _mm512_mask_store_ps(void* mem_addr, __mmask16 k, __m512 a);

Store packed float32 elements from a into mem_addr using writemask k.

mem_addr must be aligned on a 64-byte boundary or a general-protection exception will be generated.



_mm512_stream_pd

extern void __cdecl _mm512_stream_pd(void* mem_addr, __m512d a);

Stores 512-bits (composed of eight packed float64 elements) from a into mem_addr using a non-temporal memory hint.


_mm512_stream_ps

extern void __cdecl _mm512_stream_ps(void* mem_addr, __m512 a);

Stores 512-bits (composed of sixteen packed float32 elements) from a into mem_addr using a non-temporal memory hint.



_mm_mask_store_sd

extern void __cdecl _mm_mask_store_sd(double* mem_addr, __mmask8 k, __m128d a);

Stores lower float64 element from a into mem_addr using writemask k.

mem_addr must be aligned on a 16-byte boundary or a general-protection exception will be generated.



_mm_mask_store_ss

extern void __cdecl _mm_mask_store_ss(float* mem_addr, __mmask8 k, __m128 a);

Stores lower float32 element from a into mem_addr using writemask k.

mem_addr must be aligned on a 16-byte boundary or a general-protection exception will be generated.



_mm512_storeu_pd

extern void __cdecl _mm512_storeu_pd(void* mem_addr, __m512d a);

Stores 512-bits (composed of eight packed float64 elements) from a into mem_addr.

mem_addr does not need to be aligned on any particular boundary.


_mm512_mask_storeu_pd

extern void __cdecl _mm512_mask_storeu_pd(void* mem_addr, __mmask8 k, __m512d a);

Stores packed float64 elements from a into mem_addr using writemask k.

mem_addr does not need to be aligned on any particular boundary.



_mm512_storeu_ps

extern void __cdecl _mm512_storeu_ps(void* mem_addr, __m512 a);

Stores 512-bits (composed of sixteen packed float32 elements) from a into mem_addr.

mem_addr does not need to be aligned on any particular boundary.


_mm512_mask_storeu_ps

extern void __cdecl _mm512_mask_storeu_ps(void* mem_addr, __mmask16 k, __m512 a);

Stores packed float32 elements from a into mem_addr using writemask k.



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