Intel® C++ Compiler Classic Developer Guide and Reference

ID 767249
Date 12/16/2022
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A newer version of this document is available.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 FP Subtraction 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_sub_pd, _mm512_mask_sub_pd, _mm512_maskz_sub_pd

_mm512_sub_round_pd, _mm512_mask_sub_round_pd, _mm512_maskz_sub_round_pd

Subtracts float64 vectors.

VSUBPD

_mm512_sub_ps, _mm512_mask_sub_ps, _mm512_maskz_sub_ps

_mm512_sub_round_ps, _mm512_mask_sub_round_ps, _mm512_maskz_sub_round_ps

Subtracts float32 vectors.

VSUBPS

_mm_mask_sub_sd, _mm_maskz_sub_sd

_mm_sub_round_sd, _mm_mask_sub_round_sd, _mm_maskz_sub_round_sd

Subtracts float64 vectors.

VSUBSD

_mm_mask_sub_ss, _mm_maskz_sub_ss

_mm_sub_round_ss, _mm_mask_sub_round_ss, _mm_maskz_sub_round_ss

Subtracts float32 vectors.

VSUBSS

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

round

Rounding control values; these can be one of the following (along with the sae suppress all exceptions flag):

  • _MM_FROUND_TO_NEAREST_INT - rounds to nearest even
  • _MM_FROUND_TO_NEG_INF - rounds to negative infinity
  • _MM_FROUND_TO_POS_INF - rounds to positive infinity
  • _MM_FROUND_TO_ZERO - rounds to zero
  • _MM_FROUND_CUR_DIRECTION - rounds using default from MXCSR register


_mm512_sub_pd

extern __m512d __cdecl _mm512_sub_pd(__m512d a, __m512d b);

Subtracts packed float64 elements in vector b from vector a, and stores the result.


_mm512_mask_sub_pd

extern __m512d __cdecl _mm512_mask_sub_pd(__m512d src, __mmask8 k, __m512d a, __m512d b);

Subtracts packed float64 elements in b from packed float64 elements in a, and stores the result using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_sub_pd

extern __m512d __cdecl _mm512_maskz_sub_pd(__mmask8 k, __m512d a, __m512d b);

Subtracts packed float64 elements in b from packed float64 elements in a, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_sub_round_pd

extern __m512d __cdecl _mm512_sub_round_pd(__m512d a, __m512d b, int round);

Subtracts packed float64 elements in b from packed float64 elements in ausing rounding control round, and stores the result.


_mm512_mask_sub_round_pd

extern __m512d __cdecl _mm512_mask_sub_round_pd(__m512d src, __mmask8 k, __m512d a, __m512d b, int round);

Subtracts packed float64 elements in b from packed float64 elements in a using rounding control round, and stores the result using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_sub_round_pd

extern __m512d __cdecl _mm512_maskz_sub_round_pd(__mmask8 k, __m512d a, __m512d b, int round);

Subtracts packed float64 elements in b from packed float64 elements in a using rounding control round, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_sub_ps

extern __m512 __cdecl _mm512_sub_ps(__m512 a, __m512 b);

Subtracts packed float32 elements in b from packed float32 elements in a, and stores the result.


_mm512_mask_sub_ps

extern __m512 __cdecl _mm512_mask_sub_ps(__m512 src, __mmask16 k, __m512 a, __m512 b);

Subtracts packed float32 elements in b from packed float32 elements in a, and stores the result using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_sub_ps

extern __m512 __cdecl _mm512_maskz_sub_ps(__mmask16 k, __m512 a, __m512 b);

Subtracts packed float32 elements in b from packed float32 elements in a, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_sub_round_ps

extern __m512 __cdecl _mm512_sub_round_ps(__m512 a, __m512 b, int round);

Subtracts packed float32 elements in b from packed float32 elements in a, and stores the result.


_mm512_mask_sub_round_ps

extern __m512 __cdecl _mm512_mask_sub_round_ps(__m512 src, __mmask16 k, __m512 a, __m512 b, int round);

Subtracts packed float32 elements in b from packed float32 elements in a, and stores the result using writemask k (elements are copied from src when the corresponding mask bit is not set).


_mm512_maskz_sub_round_ps

extern __m512 __cdecl _mm512_maskz_sub_round_ps(__mmask16 k, __m512 a, __m512 b, int round);

Subtracts packed float32 elements in b from packed float32 elements in a using rounding control round, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm_mask_sub_sd

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

Subtracts the lower float64 element in b from the lower float64 element in a, stores the result in the lower destination element using writemask k (the element is copied from src when mask bit 0 is not set), and copies the upper element from a to the upper destination element.


_mm_maskz_sub_sd

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

Subtracts the lower float64 element in b from the lower float64 element in a, stores the result in the lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and copies the upper element from a to the upper destination element.



_mm_sub_round_sd

extern __m128d __cdecl _mm_sub_round_sd(__m128d a, __m128d b, int round);

Subtracts the lower float64 element in b from the lower float64 element in a, stores the result in the lower destination element, and copies the upper element from a to the upper destination element.


_mm_mask_sub_round_sd

extern __m128d __cdecl _mm_mask_sub_round_sd(__m128d src, __mmask8 k, __m128d a, __m128d b, int round);

Subtracts the lower float64 element in b from the lower float64 element in a using rounding control round, stores the result in the lower destination element using writemask k (the element is copied from src when mask bit 0 is not set), and copies the upper element from a to the upper destination element.


_mm_maskz_sub_round_sd

extern __m128d __cdecl _mm_maskz_sub_round_sd(__mmask8 k, __m128d a, __m128d b, int round);

Subtracts the lower float64 element in b from the lower float64 element in a, stores the result in the lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and copies the upper element from a to the upper destination element.



_mm_sub_round_ss

extern __m128 __cdecl _mm_sub_round_ss(__m128 a, __m128 b, int round);

Subtracts the lower float32 element in b from the lower float32 element in a, stores the result in the lower destination element, and copies the upper three packed elements from a to the upper destination elements.


_mm_mask_sub_round_ss

extern __m128 __cdecl _mm_mask_sub_round_ss(__m128 src, __mmask8 k, __m128 a, __m128 b, int round);

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


_mm_maskz_sub_round_ss

extern __m128 __cdecl _mm_maskz_sub_round_ss(__mmask8 k, __m128 a, __m128 b, int round);

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



_mm_mask_sub_ss

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

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


_mm_maskz_sub_ss

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

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



_mm_sub_round_ss

extern __m128 __cdecl _mm_sub_round_ss(__m128 a, __m128 b, int round);

Subtracts the lower float32 element in b from the lower float32 element in a, stores the result in the lower destination element, and copy the upper three packed elements from a to the upper destination elements.


_mm_mask_sub_round_ss

extern __m128 __cdecl _mm_mask_sub_round_ss(__m128 src, __mmask8 k, __m128 a, __m128 b, int round);

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


_mm_maskz_sub_round_ss

extern __m128 __cdecl _mm_maskz_sub_round_ss(__mmask8 k, __m128 a, __m128 b, int round);

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