Intrinsics for FP Move Operations

Intel® C++ Compiler Classic Developer Guide and Reference

Download PDF

ID 767249

Date 12/16/2022

Version

Public

A newer version of this document is available.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

Visible to Intel only — GUID: GUID-A572F793-2E47-49DE-9605-4B76F6B0E0D5

View Details

Intrinsics for FP Move 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_mask_mov_pd`, `_mm512_maskz_mov_pd`	Moves packed float64 elements.	`VMOVAPD`
`_mm512_mask_mov_ps`, `_mm512_maskz_mov_ps`	Moves packed float32 elements.	`VMOVAPS`
`_mm_mask_move_sd`, `_mm_maskz_move_sd`	Moves scalar float64 elements.	`VMOVSD`
`_mm_mask_move_ss`, `_mm_maskz_move_ss`	Moves scalar float32 elements.	`VMOVSS`
`_mm512_movedup_pd`, `_mm512_mask_movedup_pd`, `_mm512_maskz_movedup_pd`	Duplicates even-indexed float64 elements.	`VMOVDDUP`
`_mm512_movehdup_ps`, `_mm512_mask_movehdup_ps`, `_mm512_maskz_movehdup_ps`	Duplicates odd-indexed float32 elements.	`VMOVSHDUP`
`_mm512_moveldup_ps`, `_mm512_mask_moveldup_ps`, `_mm512_maskz_moveldup_ps`	Moves lower float32 element.	`VMOVSLDUP`

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_mask_mov_pd

extern __m512d __cdecl _mm512_mask_mov_pd(__m512d src, __mmask8 k, __m512d a);

Moves packed float64 elements from a using writemask k (elements are copied from src when the corresponding mask bit is not set).

_mm512_maskz_mov_pd

extern __m512d __cdecl _mm512_maskz_mov_pd(__mmask8 k, __m512d a);

Moves packed float64 elements from a using zeromask k (elements are zeroed out when the corresponding mask bit is not set).

_mm512_mask_mov_ps

extern __m512 __cdecl _mm512_mask_mov_ps(__m512 src, __mmask16 k, __m512 a);

Moves packed float32 elements from a using writemask k (elements are copied from src when the corresponding mask bit is not set).

_mm512_maskz_mov_ps

extern __m512 __cdecl _mm512_maskz_mov_ps(__mmask16 k, __m512 a);

Moves packed float32 elements from a using zeromask k (elements are zeroed out when the corresponding mask bit is not set).

_mm512_movedup_pd

extern __m512d __cdecl _mm512_movedup_pd(__m512d a);

Duplicates even-indexed float64 elements from a, and stores the result.

_mm512_mask_movedup_pd

extern __m512d __cdecl _mm512_mask_movedup_pd(__m512d src, __mmask8 k, __m512d a);

Duplicates even-indexed float64 elements from a, and stores the result using writemask k (elements are copied from src when the corresponding mask bit is not set).

_mm512_maskz_movedup_pd

extern __m512d __cdecl _mm512_maskz_movedup_pd(__mmask8 k, __m512d a);

Duplicates even-indexed float64 elements from a, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).

_mm_mask_move_sd

extern __m128d __cdecl _mm_mask_move_sd(__m128d src, __mmask8 k, __m128d a, __m128d b);

Moves lower float64 element from b to lower destination element using writemask k (the element is copied from src when mask bit 0 is not set), and copy upper element from a to upper destination element.

_mm_maskz_move_sd

extern __m128d __cdecl _mm_maskz_move_sd(__mmask8 k, __m128d a, __m128d b);

Moves lower float64 element from b to lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and copy upper element from a to upper destination element.

_mm512_movehdup_ps

extern __m512 __cdecl _mm512_movehdup_ps(__m512 a);

Duplicates odd-indexed float32 elements from a, and stores the result.

_mm512_mask_movehdup_ps

extern __m512 __cdecl _mm512_mask_movehdup_ps(__m512 src, __mmask16 k, __m512 a);

Duplicates odd-indexed float32 elements from a, and store the result using writemask k (elements are copied from src when the corresponding mask bit is not set).

_mm512_maskz_movehdup_ps

extern __m512 __cdecl _mm512_maskz_movehdup_ps(__mmask16 k, __m512 a);

Duplicates odd-indexed float32 elements from a, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).

_mm512_moveldup_ps

extern __m512 __cdecl _mm512_moveldup_ps(__m512 a);

Duplicates even-indexed float32 elements from a, and stores the result.

_mm512_mask_moveldup_ps

extern __m512 __cdecl _mm512_mask_moveldup_ps(__m512 src, __mmask16 k, __m512 a);

Duplicates even-indexed float32 elements from a, and stores the result using writemask k (elements are copied from src when the corresponding mask bit is not set).

_mm512_maskz_moveldup_ps

extern __m512 __cdecl _mm512_maskz_moveldup_ps(__mmask16 k, __m512 a);

Duplicates even-indexed float32 elements from a, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).

_mm_mask_move_ss

extern __m128 __cdecl _mm_mask_move_ss(__m128 src, __mmask8 k, __m128 a, __m128 b);

Moves lower float32 element from b to lower destination element using writemask k (the element is copied from src when mask bit 0 is not set), and copies upper three packed elements from a to upper destination elements.

_mm_maskz_move_ss

extern __m128 __cdecl _mm_maskz_move_ss(__mmask8 k, __m128 a, __m128 b);

Moves lower float32 element from b to lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and copies upper three packed elements from a to upper destination elements.

Parent topic: Intrinsics for Move Operations

Select Your Language

Using Intel.com Search

Quick Links

Recent Searches

Advanced Search

Only search in

Intel® C++ Compiler Classic Developer Guide and Reference

Intrinsics for FP Move Operations