Intel® C++ Compiler Classic Developer Guide and Reference

ID 767249
Date 7/13/2023
Public
Document Table of Contents

Intrinsics for FP Fused Multiply-Add (FMA) 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_fmadd_pd, _mm512_mask3_fmadd_pd, _mm512_mask_fmadd_pd, _mm512_maskz_fmadd_pd

_mm512_fmadd_round_pd, _mm512_mask3_fmadd_round_pd, _mm512_mask_fmadd_round_pd, _mm512_maskz_fmadd_round_pd

Multiplies float64 element vector elements, then adds the intermediate result to float64 vector elements.

VFMADD132PD

_mm512_fmadd_ps, _mm512_mask3_fmadd_ps, _mm512_mask_fmadd_ps, _mm512_maskz_fmadd_ps

_mm512_fmadd_round_ps, _mm512_mask3_fmadd_round_ps, _mm512_mask_fmadd_round_ps, _mm512_maskz_fmadd_round_ps

Multiplies float32 element vector elements, then adds the intermediate result to float32 vector elements.

VFMADD132PS

_mm_mask3_fmadd_sd, _mm_mask_fmadd_sd, _mm_maskz_fmadd_sd

_mm_mask3_fmadd_round_sd, _mm_mask_fmadd_round_sd, _mm_maskz_fmadd_round_sd

Multiplies float64 element vector elements, then adds the intermediate result to float64 vector elements.

VFMADD132SD

_mm_mask3_fmadd_ss, _mm_mask_fmadd_ss, _mm_maskz_fmadd_ss

_mm_mask3_fmadd_round_ss, _mm_mask_fmadd_round_ss, _mm_maskz_fmadd_round_ss

Multiplies float32 element vector elements, then adds the intermediate result to float32 vector elements.

VFMADD132SS

_mm512_fmaddsub_pd, _mm512_mask3_fmaddsub_pd, _mm512_mask_fmaddsub_pd, _mm512_maskz_fmaddsub_pd

_mm512_fmaddsub_round_pd, _mm512_mask3_fmaddsub_round_pd, _mm512_mask_fmaddsub_round_pd, _mm512_maskz_fmaddsub_round_pd

Multiplies float64 element vector elements, then alternatively add and subtract to/from the intermediate result.

VFMADDSUB132PD

_mm512_fmaddsub_ps, _mm512_mask3_fmaddsub_ps, _mm512_mask_fmaddsub_ps, _mm512_maskz_fmaddsub_ps

_mm512_fmaddsub_round_ps, _mm512_mask3_fmaddsub_round_ps, _mm512_mask_fmaddsub_round_ps, _mm512_maskz_fmaddsub_round_ps

Multiplies float32 element vector elements, then alternatively add and subtract to/from the intermediate result.

VFMADDSUB132PS

_mm512_fmsub_pd, _mm512_mask3_fmsub_pd, _mm512_mask_fmsub_pd, _mm512_maskz_fmsub_pd

_mm512_fmsub_round_pd, _mm512_mask3_fmsub_round_pd, _mm512_mask_fmsub_round_pd, _mm512_maskz_fmsub_round_pd

Multiplies packed float64 element vector elements, then subtracts the intermediate result to float64 vector elements.

VFMSUB132PD

_mm512_fmsub_ps, _mm512_mask3_fmsub_ps, _mm512_mask_fmsub_ps, _mm512_maskz_fmsub_ps

_mm512_fmsub_round_ps, _mm512_mask3_fmsub_round_ps, _mm512_mask_fmsub_round_ps, _mm512_maskz_fmsub_round_ps

Multiplies packed float32 element vector elements, then subtracts the intermediate result to float32 vector elements.

VFMSUB132PS

_mm_mask3_fmsub_sd, _mm_mask_fmsub_sd, _mm_maskz_fmsub_sd

_mm_mask3_fmsub_round_sd, _mm_mask_fmsub_round_sd, _mm_maskz_fmsub_round_sd

Multiplies scalar float64 element vector elements, then subtracts the intermediate result to float64 vector elements.

VFMSUB132SD

_mm_mask3_fmsub_ss, _mm_mask_fmsub_ss, _mm_maskz_fmsub_ss

_mm_mask3_fmsub_round_ss, _mm_mask_fmsub_round_ss, _mm_maskz_fmsub_round_ss

Multiplies scalar float32 element vector elements, then subtracts the intermediate result to float32 vector elements.

VFMSUB132SS

_mm512_fmsubadd_pd, _mm512_mask3_fmsubadd_pd, _mm512_mask_fmsubadd_pd, _mm512_maskz_fmsubadd_pd

_mm512_fmsubadd_round_pd, _mm512_mask3_fmsubadd_round_pd, _mm512_mask_fmsubadd_round_pd, _mm512_maskz_fmsubadd_round_pd

Multiplies float64 element vector elements, then alternatively subtract and add to/from the intermediate result.

VFMSUBADD132PD

_mm512_fmsubadd_ps, _mm512_mask3_fmsubadd_ps, _mm512_mask_fmsubadd_ps, _mm512_maskz_fmsubadd_ps

_mm512_fmsubadd_round_ps, _mm512_mask3_fmsubadd_round_ps, _mm512_mask_fmsubadd_round_ps, _mm512_maskz_fmsubadd_round_ps

Multiplies float32 element vector elements, then alternatively subtract and add to/from the intermediate result.

VFMSUBADD132PS

_mm512_fnmadd_pd, _mm512_mask3_fnmadd_pd, _mm512_mask_fnmadd_pd, _mm512_maskz_fnmadd_pd

_mm512_fnmadd_round_pd, _mm512_mask3_fnmadd_round_pd, _mm512_mask_fnmadd_round_pd, _mm512_maskz_fnmadd_round_pd

Multiplies packed float64 element vector elements, then adds the negated intermediate result to float64 vector elements.

VFNMADD132PD

_mm512_fnmadd_ps, _mm512_mask3_fnmadd_ps, _mm512_maskz_fnmadd_ps, _mm512_mask_fnmadd_ps

_mm512_fnmadd_round_ps, , _mm512_mask3_fnmadd_round_ps, _mm512_mask_fnmadd_round_ps, _mm512_maskz_fnmadd_round_ps

Multiplies packed float32 element vector elements, then adds the negated intermediate result to float32 vector elements.

VFNMADD132PS

_mm_mask3_fnmadd_round_sd, _mm_mask_fnmadd_round_sd, _mm_maskz_fnmadd_round_sd

_mm_maskz_fnmadd_sd, _mm_mask_fnmadd_sd, _mm_mask3_fnmadd_sd

Multiplies scalar float64 element vector elements, then adds the negated intermediate result to float64 vector elements.

VFNMADD132SD

_mm_mask3_fnmadd_ss, _mm_mask_fnmadd_ss, _mm_maskz_fnmadd_ss

_mm_mask3_fnmadd_round_ss, _mm_mask_fnmadd_round_ss, _mm_maskz_fnmadd_round_ss

Multiplies scalar float32 element vector elements, then adds the negated intermediate result to float32 vector elements.

VFNMADD132SS

_mm512_fnmsub_pd, _mm512_mask3_fnmsub_pd, _mm512_mask_fnmsub_pd, _mm512_maskz_fnmsub_pd

_mm512_fnmsub_round_pd, _mm512_mask3_fnmsub_round_pd, _mm512_mask_fnmsub_round_pd, _mm512_maskz_fnmsub_round_pd

Multiplies packed float64 element vector elements, then subtracts the negated intermediate result to float64 vector elements.

VFNMSUB132PD

_mm512_fnmsub_ps, _mm512_mask3_fnmsub_ps, _mm512_maskz_fnmsub_ps, _mm512_mask_fnmsub_ps

_mm512_fnmsub_round_ps, _mm512_mask3_fnmsub_round_ps, _mm512_maskz_fnmsub_round_ps, _mm512_mask_fnmsub_round_ps

Multiplies packed float32 element vector elements, then subtracts the negated intermediate result to float32 vector elements.

VFNMSUB132PS

_mm_maskz_fnmsub_round_sd, _mm_mask_fnmsub_round_sd, _mm_mask3_fnmsub_round_sd

_mm_mask_fnmsub_sd, _mm_mask3_fnmsub_sd, _mm_maskz_fnmsub_sd

Multiplies scalar float64 element vector elements, then subtracts the negated intermediate result to float64 vector elements.

VFNMSUB132SD

_mm_maskz_fnmsub_round_ss, _mm_mask_fnmsub_round_ss, _mm_mask3_fnmsub_round_ss

_mm_mask_fnmsub_ss, _mm_maskz_fnmsub_ss, _mm_mask3_fnmsub_ss

Multiplies scalar float32 element vector elements, then subtracts the negated intermediate result to float32 vector elements.

VFNMSUB132SS


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_fmadd_pd

extern __m512d __cdecl _mm512_fmadd_pd(__m512d a, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, adds the intermediate result to packed elements in c, and stores the result.



_mm512_mask_fmadd_pd

extern __m512d __cdecl _mm512_mask_fmadd_pd(__m512d a, __mmask8 k, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmadd_pd

extern __m512d __cdecl _mm512_mask3_fmadd_pd(__m512d a, __m512d b, __m512d c, __mmask8 k);

Multiplies packed float64 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmadd_pd

extern __m512d __cdecl _mm512_maskz_fmadd_pd(__mmask8 k, __m512d a, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fmadd_round_pd

extern __m512d __cdecl _mm512_fmadd_round_pd(__m512d a, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, adds the intermediate result to packed elements in c, and stores the result.



_mm512_mask_fmadd_round_pd

extern __m512d __cdecl _mm512_mask_fmadd_round_pd(__m512d a, __mmask8 k, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmadd_round_pd

extern __m512d __cdecl _mm512_mask3_fmadd_round_pd(__m512d a, __m512d b, __m512d c, __mmask8 k, int round);

Multiplies packed float64 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmadd_round_pd

extern __m512d __cdecl _mm512_maskz_fmadd_round_pd(__mmask8 k, __m512d a, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fmadd_round_ps

extern __m512 __cdecl _mm512_fmadd_round_ps(__m512 a, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, adds the intermediate result to packed elements in c, and stores the result.



_mm512_mask_fmadd_round_ps

extern __m512 __cdecl _mm512_mask_fmadd_round_ps(__m512 a, __mmask16 k, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmadd_round_ps

extern __m512 __cdecl _mm512_mask3_fmadd_round_ps(__m512 a, __m512 b, __m512 c, __mmask16 k, int round);

Multiplies packed float32 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmadd_round_ps

extern __m512 __cdecl _mm512_maskz_fmadd_round_ps(__mmask16 k, __m512 a, __m512 b, __m512 c, const int round);

Multiplies packed float32 elements in a and b, adds the intermediate result to packed elements in c, and stores the result a using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fmadd_ps

extern __m512 __cdecl _mm512_fmadd_ps(__m512 a, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, adds the intermediate result to packed elements in c, and stores the result.



_mm512_mask_fmadd_ps

extern __m512 __cdecl _mm512_mask_fmadd_ps(__m512 a, __mmask16 k, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmadd_ps

extern __m512 __cdecl _mm512_mask3_fmadd_ps(__m512, __m512 b, __m512 c, __mmask16 k);

Multiplies packed float32 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmadd_ps

extern __m512 __cdecl _mm512_maskz_fmadd_ps(__mmask16 k, __m512 a, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fmadd_round_ps

extern __m512 __cdecl _mm512_fmadd_round_ps(__m512 a, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, adds the intermediate result to packed elements in c, and stores the result.



_mm512_mask_fmadd_round_ps

extern __m512 __cdecl _mm512_mask_fmadd_round_ps(__m512 a, __mmask16 k, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmadd_round_ps

extern __m512 __cdecl _mm512_mask3_fmadd_round_ps(__m512 a, __m512 b, __m512 c, __mmask16 k, int round);

Multiplies packed float32 elements in a and b, adds the intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmadd_round_ps

extern __m512 __cdecl _mm512_maskz_fmadd_round_ps(__mmask16 k, __m512 a, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, adds the intermediate result to packed elements in c, and stores the result a using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm_mask_fmadd_sd

extern __m128d __cdecl _mm_mask_fmadd_sd(__m128d a, __mmask8 k, __m128d b, __m128d c);

Multiplies lower float64 elements in a and b, and adds the intermediate result to lower element in c. Stores the result in lower destination element using writemask k (the element is copied from a when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask3_fmadd_sd

extern __m128d __cdecl _mm_mask3_fmadd_sd(__m128d a, __m128d b, __m128d c, __mmask8 k);

Multiplies lower float64 elements in a and b, and adds the intermediate result to lower element in c. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_maskz_fmadd_sd

extern __m128d __cdecl _mm_maskz_fmadd_sd(__mmask8 k, __m128d a, __m128d b, __m128d c);

Multiplies lower float64 elements in a and b, and adds the intermediate result to lower element in c. Stores the result in lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask_fmadd_round_sd

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

Multiplies lower float64 elements in a and b, and adds the intermediate result to lower element in c. Stores the result in lower destination element using writemask k (the element is copied from a when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask3_fmadd_round_sd

extern __m128d __cdecl _mm_mask3_fmadd_round_sd(__m128d a, __m128d b, __m128d c, __mmask8 k, int round);

Multiplies lower float64 elements in a and b, and adds the intermediate result to lower element in c. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_maskz_fmadd_round_sd

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

Multiplies lower float64 elements in a and b, and adds the intermediate result to lower element in c. Stores the result in lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask_fmadd_ss

extern __m128 __cdecl _mm_mask_fmadd_ss(__m128 a, __mmask8 k, __m128 b, __m128 c);

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



_mm_mask3_fmadd_ss

extern __m128 __cdecl _mm_mask3_fmadd_ss(__m128 a, __m128 b, __m128 c, __mmask8 k);

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



_mm_maskz_fmadd_ss

extern __m128 __cdecl _mm_maskz_fmadd_ss(__mmask8 k, __m128 a, __m128 b, __m128 c);

Multiplies lower float32 elements in a and b, and adds the intermediate result to lower element in c. Stores the result in 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.



_mm_mask_fmadd_round_ss

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

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



_mm_mask3_fmadd_round_ss

extern __m128 __cdecl _mm_mask3_fmadd_round_ss(__m128 a, __m128 b, __m128 c, __mmask8 k, int round);

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



_mm_maskz_fmadd_round_ss

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

Multiplies lower float32 elements in a and b, and adds the intermediate result to lower element in c. Stores the result in 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.



_mm512_fmaddsub_pd

extern __m512d __cdecl _mm512_fmaddsub_pd(__m512d a, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result.



_mm512_mask_fmaddsub_pd

extern __m512d __cdecl _mm512_mask_fmaddsub_pd(__m512d, __mmask8 k, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmaddsub_pd

extern __m512d __cdecl _mm512_mask3_fmaddsub_pd(__m512d a, __m512d k, __m512d b, __mmask8 c);

Multiplies packed float64 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmaddsub_pd

extern __m512d __cdecl _mm512_maskz_fmaddsub_pd(__mmask8 k, __m512d a, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fmaddsub_round_pd

extern __m512d __cdecl _mm512_fmsubadd_round_pd(__m512d a, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result.



_mm512_mask_fmaddsub_round_pd

extern __m512d __cdecl _mm512_mask_fmsubadd_round_pd(__m512d a, __mmask8 k, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmaddsub_round_pd

extern __m512d __cdecl _mm512_mask3_fmsubadd_round_pd(__m512d a, __m512d b, __m512d c, __mmask8 k, int round);

Multiplies packed float64 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmaddsub_round_pd

extern __m512d __cdecl _mm512_maskz_fmsubadd_round_pd(__mmask8 k, __m512d a, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fmaddsub_ps

extern __m512 __cdecl _mm512_fmaddsub_ps(__m512 a, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result.



_mm512_mask_fmaddsub_ps

extern __m512 __cdecl _mm512_mask_fmaddsub_ps(__m512 a, __mmask16 k, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmaddsub_ps

extern __m512 __cdecl _mm512_mask3_fmaddsub_ps(__m512 a, __m512 b, __m512 c, __mmask16 k);

Multiplies packed float32 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmaddsub_ps

extern __m512 __cdecl _mm512_maskz_fmaddsub_ps(__mmask16 k, __m512 a, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fmaddsub_round_ps

extern __m512 __cdecl _mm512_fmaddsub_round_ps(__m512 a, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result.



_mm512_mask_fmaddsub_round_ps

extern __m512 __cdecl _mm512_mask_fmaddsub_round_ps(__m512 a, __mmask16 k, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmaddsub_round_ps

extern __m512 __cdecl _mm512_mask3_fmaddsub_round_ps(__m512 a, __m512 b, __m512 c, __mmask16 k, int round);

Multiplies packed float32 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmaddsub_round_ps

extern __m512 __cdecl _mm512_maskz_fmaddsub_round_ps(__mmask16 k, __m512 a, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, alternatively add and subtract packed elements in c to/from the intermediate result, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fmsub_pd

extern __m512d __cdecl _mm512_fmsub_pd(__m512d a, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, subtracts packed elements in c from the intermediate result, and stores the result.



_mm512_mask_fmsub_pd

extern __m512d __cdecl _mm512_mask_fmsub_pd(__m512d a, __mmask8 k, __m512d b, __m512d c);

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



_mm512_mask3_fmsub_pd

extern __m512d __cdecl _mm512_mask3_fmsub_pd(__m512d a, __m512d b, __m512d c, __mmask8 k);

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



_mm512_maskz_fmsub_pd

extern __m512d __cdecl _mm512_maskz_fmsub_pd(__mmask8 k, __m512d a, __m512d b, __m512d c);

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



_mm512_fmsub_round_pd

extern __m512d __cdecl _mm512_fmsub_round_pd(__m512d a, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, subtracts packed elements in c from the intermediate result, and stores the result.



_mm512_mask_fmsub_round_pd

extern __m512d __cdecl _mm512_mask_fmsub_round_pd(__m512d a, __mmask8 k, __m512d b, __m512d c, int round);

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



_mm512_mask3_fmsub_round_pd

extern __m512d __cdecl _mm512_mask3_fmsub_round_pd(__m512d a, __m512d b, __m512d c, __mmask8 k, int round);

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



_mm512_maskz_fmsub_round_pd

extern __m512d __cdecl _mm512_maskz_fmsub_round_pd(__mmask8 k, __m512d a, __m512d b, __m512d c, int round);

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



_mm512_fmsub_ps

extern __m512 __cdecl _mm512_fmsub_ps(__m512 a, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, subtracts packed elements in c from the intermediate result, and stores the result.



_mm512_mask_fmsub_ps

extern __m512 __cdecl _mm512_mask_fmsub_ps(__m512 a, __mmask16 k, __m512 b, __m512 c);

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



_mm512_mask3_fmsub_ps

extern __m512 __cdecl _mm512_mask3_fmsub_ps(__m512 a, __m512 b, __m512 c, __mmask16 k);

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



_mm512_maskz_fmsub_ps

extern __m512 __cdecl _mm512_maskz_fmsub_ps(__mmask16 k, __m512 a, __m512 b, __m512 c);

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



_mm512_fmsub_round_ps

extern __m512 __cdecl _mm512_fmsub_round_ps(__m512 a, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, subtracts packed elements in c from the intermediate result, and stores the result.



_mm512_mask_fmsub_round_ps

extern __m512 __cdecl _mm512_mask_fmsub_round_ps(__m512 a, __mmask16 k, __m512 b, __m512 c, int round);

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



_mm512_mask3_fmsub_round_ps

extern __m512 __cdecl _mm512_mask3_fmsub_round_ps(__m512 a, __m512 b, __m512 c, __mmask16 k, int round);

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



_mm512_maskz_fmsub_round_ps

extern __m512 __cdecl _mm512_maskz_fmsub_round_ps(__mmask16 k, __m512 a, __m512 b, __m512 c, int round);

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



_mm_mask_fmsub_sd

extern __m128d __cdecl _mm_mask_fmsub_sd(__m128d a, __mmask8 k, __m128d b, __m128d c);

Multiplies lower float64 elements in a and b, and subtracts lower element in c from the intermediate result. Stores the result in lower destination element using writemask k (the element is copied from a when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask3_fmsub_sd

extern __m128d __cdecl _mm_mask3_fmsub_sd(__m128d a, __m128d b, __m128d c, __mmask8 k);

Multiplies lower float64 elements in a and b, and subtracts lower element in c from the intermediate result. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_maskz_fmsub_sd

extern __m128d __cdecl _mm_maskz_fmsub_sd(__mmask8 k, __m128d a, __m128d b, __m128d c);

Multiplies lower float64 elements in a and b, and subtracts lower element in c from the intermediate result. Stores the result in lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask_fmsub_round_sd

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

Multiplies lower float64 elements in a and b, and subtracts lower element in c from the intermediate result. Stores the result in lower destination element using writemask k (the element is copied from a when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask3_fmsub_round_sd

extern __m128d __cdecl _mm_mask3_fmsub_round_sd(__m128d a, __m128d b, __m128d c, __mmask8 k, int round);

Multiplies lower float64 elements in a and b, and subtracts lower element in c from the intermediate result. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_maskz_fmsub_round_sd

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

Multiplies lower float64 elements in a and b, and subtracts lower element in c from the intermediate result. Stores the result in lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask_fmsub_ss

extern __m128 __cdecl _mm_mask_fmsub_ss(__m128 a, __mmask8 k, __m128 b, __m128 c);

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



_mm_mask3_fmsub_ss

extern __m128 __cdecl _mm_mask3_fmsub_ss(__m128 a, __m128 b, __m128 c, __mmask8 k);

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



_mm_maskz_fmsub_ss

extern __m128 __cdecl _mm_maskz_fmsub_ss(__mmask8 k, __m128 a, __m128 b, __m128 c);

Multiplies lower float32 elements in a and b, and subtracts lower element in c from the intermediate result. Stores the result in 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.



_mm_mask_fmsub_round_ss

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

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



_mm_mask3_fmsub_round_ss

extern __m128 __cdecl _mm_mask3_fmsub_round_ss(__m128 a, __m128 b, __m128 c, __mmask8 k, int round);

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



_mm_maskz_fmsub_round_ss

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

Multiplies lower float32 elements in a and b, and subtracts lower element in c from the intermediate result. Stores the result in 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.



_mm512_fmsubadd_pd

extern __m512d __cdecl _mm512_fmsubadd_pd(__m512d a, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result.



_mm512_mask_fmsubadd_pd

extern __m512d __cdecl _mm512_mask_fmsubadd_pd(__m512d a, __mmask8 k, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmsubadd_pd

extern __m512d __cdecl _mm512_mask3_fmsubadd_pd(__m512d a, __m512d b, __m512d c, __mmask8 k);

Multiplies packed float64 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmsubadd_pd

extern __m512d __cdecl _mm512_maskz_fmsubadd_pd(__mmask8 k, __m512d a, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result destination using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fmsubadd_round_pd

extern __m512d __cdecl _mm512_fmaddsub_round_pd(__m512d a, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result.



_mm512_mask_fmsubadd_round_pd

extern __m512d __cdecl _mm512_mask_fmaddsub_round_pd(__m512d a, __mmask8 k, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmsubadd_round_pd

extern __m512d __cdecl _mm512_mask3_fmaddsub_round_pd(__m512d a, __m512d b, __m512d c, __mmask8 k, int round);

Multiplies packed float64 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmsubadd_round_pd

extern __m512d __cdecl _mm512_maskz_fmaddsub_round_pd(__mmask8 k, __m512d a, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fmsubadd_ps

extern __m512 __cdecl _mm512_fmsubadd_ps(__m512 a, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result.



_mm512_mask_fmsubadd_ps

extern __m512 __cdecl _mm512_mask_fmsubadd_ps(__m512 a, __mmask16 k, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmsubadd_ps

extern __m512 __cdecl _mm512_mask3_fmsubadd_ps(__m512 a, __m512 b, __m512 c, __mmask16 k);

Multiplies packed float32 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmsubadd_ps

extern __m512 __cdecl _mm512_maskz_fmsubadd_ps(__mmask16 k, __m512 a, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fmsubadd_round_ps

extern __m512 __cdecl _mm512_fmsubadd_round_ps(__m512 a, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result.



_mm512_mask_fmsubadd_round_ps

extern __m512 __cdecl _mm512_mask_fmsubadd_round_ps(__m512 a, __mmask16 k, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fmsubadd_round_ps

extern __m512 __cdecl _mm512_mask3_fmsubadd_round_ps(__m512 a, __m512 b, __m512 c, __mmask16 k, int round);

Multiplies packed float32 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fmsubadd_round_ps

extern __m512 __cdecl _mm512_maskz_fmsubadd_round_ps(__mmask16 k, __m512 a, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, alternatively subtract and add packed elements in c from/to the intermediate result, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fnmadd_pd

extern __m512d __cdecl _mm512_fnmadd_pd(__m512d a, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result.



_mm512_mask_fnmadd_pd

extern __m512d __cdecl _mm512_mask_fnmadd_pd(__m512d a, __mmask8 k, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fnmadd_pd

extern __m512d __cdecl _mm512_mask3_fnmadd_pd(__m512d a, __m512d b, __m512d c, __mmask8 k);

Multiplies packed float64 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fnmadd_pd

extern __m512d __cdecl _mm512_maskz_fnmadd_pd(__mmask8 k, __m512d a, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fnmadd_round_pd

extern __m512d __cdecl _mm512_fnmadd_round_pd(__m512d a, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result.



_mm512_mask_fnmadd_round_pd

extern __m512d __cdecl _mm512_mask_fnmadd_round_pd(__m512d a, __mmask8 k, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fnmadd_round_pd

extern __m512d __cdecl _mm512_mask3_fnmadd_round_pd(__m512d a, __m512d b, __m512d c, __mmask8 k, int round);

Multiplies packed float64 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fnmadd_round_pd

extern __m512d __cdecl _mm512_maskz_fnmadd_round_pd(__mmask8 k, __m512d a, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fnmadd_ps

extern __m512 __cdecl _mm512_fnmadd_ps(__m512 a, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result.



_mm512_mask_fnmadd_ps

extern __m512 __cdecl _mm512_mask_fnmadd_ps(__m512 a, __mmask16 k, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fnmadd_ps

extern __m512 __cdecl _mm512_mask3_fnmadd_ps(__m512 a, __m512 b, __m512 c, __mmask16 k);

Multiplies packed float32 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fnmadd_ps

extern __m512 __cdecl _mm512_maskz_fnmadd_ps(__mmask16 k, __m512 a, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm512_fnmadd_round_ps

extern __m512 __cdecl _mm512_fnmadd_round_ps(__m512 a, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result.



_mm512_mask_fnmadd_round_ps

extern __m512 __cdecl _mm512_mask_fnmadd_round_ps(__m512 a, __mmask16 k, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fnmadd_round_ps

extern __m512 __cdecl _mm512_mask3_fnmadd_round_ps(__m512 a, __m512 b, __m512 c, __mmask16 k, int round);

Multiplies packed float32 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fnmadd_round_ps

extern __m512 __cdecl _mm512_maskz_fnmadd_round_ps(__mmask16 k, __m512 a, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, adds the negated intermediate result to packed elements in c, and stores the result using zeromask k (elements are zeroed out when the corresponding mask bit is not set).



_mm_mask_fnmadd_sd

extern __m128d __cdecl _mm_mask_fnmadd_sd(__m128d a, __mmask8 k, __m128d b, __m128d c);

Multiplies lower float64 elements in a and b, and adds the negated intermediate result to lower element in c. Stores the result in lower destination element using writemask k (the element is copied from a when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask3_fnmadd_sd

extern __m128d __cdecl _mm_mask3_fnmadd_sd(__m128d a, __m128d b, __m128d c, __mmask8 k);

Multiplies lower float64 elements in a and b, and adds the negated intermediate result to lower element in c. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_maskz_fnmadd_sd

extern __m128d __cdecl _mm_maskz_fnmadd_sd(__mmask8 k, __m128d a, __m128d b, __m128d c);

Multiplies lower float64 elements in a and b, and adds the negated intermediate result to lower element in c. Stores the result in lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask_fnmadd_round_sd

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

Multiplies lower float64 elements in a and b, and adds the negated intermediate result to lower element in c. Stores the result in lower destination element using writemask k (the element is copied from a when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask3_fnmadd_round_sd

extern __m128d __cdecl _mm_mask3_fnmadd_round_sd(__m128d a, __m128d b, __m128d c, __mmask8 k, int round);

Multiplies lower float64 elements in a and b, and adds the negated intermediate result to lower element in c. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_maskz_fnmadd_round_sd

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

Multiplies lower float64 elements in a and b, and adds the negated intermediate result to lower element in c. Stores the result in lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask_fnmadd_ss

extern __m128 __cdecl _mm_mask_fnmadd_ss(__m128 a, __mmask8 k, __m128 b, __m128 c);

Multiplies lower float32 elements in a and b, and adds the negated intermediate result to lower element in c. Stores the result in lower destination element using writemask k (the element is copied from a when mask bit 0 is not set), and copies upper three packed elements from a to upper destination elements.



_mm_mask3_fnmadd_ss

extern __m128 __cdecl _mm_mask3_fnmadd_ss(__m128 a, __m128 b, __m128 c, __mmask8 k);

Multiplies lower float32 elements in a and b, and adds the negated intermediate result to lower element in c. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper three packed elements from a to upper destination elements.



_mm_maskz_fnmadd_ss

extern __m128 __cdecl _mm_maskz_fnmadd_ss(__mmask8 k, __m128 a, __m128 b, __m128 c);

Multiplies lower float32 elements in a and b, and adds the negated intermediate result to lower element in c. Stores the result in 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.



_mm_mask_fnmadd_round_ss

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

Multiplies lower float32 elements in a and b, and adds the negated intermediate result to lower element in c. Stores the result in lower destination element using writemask k (the element is copied from a when mask bit 0 is not set), and copies upper three packed elements from a to upper destination elements.



_mm_mask3_fnmadd_round_ss

extern __m128 __cdecl _mm_mask3_fnmadd_round_ss(__m128 a, __m128 b, __m128 c, __mmask8 k, int round);

Multiplies lower float32 elements in a and b, and adds the negated intermediate result to lower element in c. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper three packed elements from a to upper destination elements.



_mm_maskz_fnmadd_round_ss

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

Multiplies lower float32 elements in a and b, and adds the negated intermediate result to lower element in c. Stores the result in 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.



_mm512_fnmsub_pd

extern __m512d __cdecl _mm512_fnmsub_pd(__m512d a, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, subtracts packed elements in c from the negated intermediate result, and stores the result.



_mm512_mask_fnmsub_pd

extern __m512d __cdecl _mm512_mask_fnmsub_pd(__m512d a, __mmask8 k, __m512d b, __m512d c);

Multiplies packed float64 elements in a and b, subtracts packed elements in c from the negated intermediate result, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fnmsub_pd

extern __m512d __cdecl _mm512_mask3_fnmsub_pd(__m512d a, __m512d b, __m512d c, __mmask8 k);

Multiplies packed float64 elements in a and b, subtracts packed elements in c from the negated intermediate result, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fnmsub_pd

extern __m512d __cdecl _mm512_maskz_fnmsub_pd(__mmask8 k, __m512d a, __m512d b, __m512d c);

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



_mm512_fnmsub_round_pd

extern __m512d __cdecl _mm512_fnmsub_round_pd(__m512d a, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, subtracts packed elements in c from the negated intermediate result, and stores the result.



_mm512_mask_fnmsub_round_pd

extern __m512d __cdecl _mm512_mask_fnmsub_round_pd(__m512d a, __mmask8 k, __m512d b, __m512d c, int round);

Multiplies packed float64 elements in a and b, subtracts packed elements in c from the negated intermediate result, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fnmsub_round_pd

extern __m512d __cdecl _mm512_mask3_fnmsub_round_pd(__m512d a, __m512d b, __m512d c, __mmask8 k, int round);

Multiplies packed float64 elements in a and b, subtracts packed elements in c from the negated intermediate result, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fnmsub_round_pd

extern __m512d __cdecl _mm512_maskz_fnmsub_round_pd(__mmask8 k, __m512d a, __m512d b, __m512d c, int round);

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



_mm512_fnmsub_ps

extern __m512 __cdecl _mm512_fnmsub_ps(__m512 a, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, subtracts packed elements in c from the negated intermediate result, and stores the result.



_mm512_mask_fnmsub_ps

extern __m512 __cdecl _mm512_mask_fnmsub_ps(__m512 a, __mmask16 k, __m512 b, __m512 c);

Multiplies packed float32 elements in a and b, subtracts packed elements in c from the negated intermediate result, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fnmsub_ps

extern __m512 __cdecl _mm512_mask3_fnmsub_ps(__m512 a, __m512 b, __m512 c, __mmask16 k);

Multiplies packed float32 elements in a and b, subtracts packed elements in c from the negated intermediate result, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fnmsub_ps

extern __m512 __cdecl _mm512_maskz_fnmsub_ps(__mmask16 k, __m512 a, __m512 b, __m512 c);

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



_mm512_fnmsub_round_ps

extern __m512 __cdecl _mm512_fnmsub_round_ps(__m512 a, __m512 b, __m512 c, int round);

Multiplies packed float32 elements in a and b, subtracts packed elements in c from the negated intermediate result, and stores the result.



_mm512_mask_fnmsub_round_ps

extern __m512 __cdecl _mm512_mask_fnmsub_round_ps(__m512 c, __mmask16 k, __m512 a, __m512 b, int round);

Multiplies packed float32 elements in a and b, subtracts packed elements in c from the negated intermediate result, and stores the result using writemask k (elements are copied from a when the corresponding mask bit is not set).



_mm512_mask3_fnmsub_round_ps

extern __m512 __cdecl _mm512_mask3_fnmsub_round_ps(__m512 a, __m512 b, __m512 c, __mmask16 k, int round);

Multiplies packed float32 elements in a and b, subtracts packed elements in c from the negated intermediate result, and stores the result using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm512_maskz_fnmsub_round_ps

extern __m512 __cdecl _mm512_maskz_fnmsub_round_ps(__mmask16 k, __m512 a, __m512 b, __m512 c, int round);

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



_mm_mask_fnmsub_sd

extern __m128d __cdecl _mm_mask_fnmsub_sd(__m128d c, __mmask8 k, __m128d a, __m128d b);

Multiplies lower float64 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask3_fnmsub_sd

extern __m128d __cdecl _mm_mask3_fnmsub_sd(__m128d a, __m128d b, __m128d c, __mmask8 k);

Multiplies lower float64 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_maskz_fnmsub_sd

extern __m128d __cdecl _mm_maskz_fnmsub_sd(__mmask8 k, __m128d a, __m128d b, __m128d c);

Multiplies lower float64 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask_fnmsub_ss

extern __m128 __cdecl _mm_mask_fnmsub_ss(__m128 c, __mmask8 k, __m128 a, __m128 b);

Multiplies lower float32 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper three packed elements from a to upper destination elements.



_mm_mask3_fnmsub_ss

extern __m128 __cdecl _mm_mask3_fnmsub_ss(__m128 a, __m128 b, __m128 c, __mmask8 k);

Multiplies lower float32 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result in lower destination element, and copies upper element from a to upper destination element using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm_maskz_fnmsub_ss

extern __m128 __cdecl _mm_maskz_fnmsub_ss(__mmask8 k, __m128 a, __m128 b, __m128 c);

Multiplies lower float32 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result in 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.



_mm_mask_fnmsub_round_ss

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

Multiplies lower float32 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper three packed elements from a to upper destination elements.



_mm_mask3_fnmsub_round_ss

extern __m128 __cdecl _mm_mask3_fnmsub_round_ss(__m128 a, __m128 b, __m128 c, __mmask8 k, int round);

Multiplies lower float32 elements in a and b, subtract lower element in c from the negated intermediate result, Stores the result in lower destination element, and copies upper element from a to upper destination element using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm_maskz_fnmsub_round_ss

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

Multiplies lower float32 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result in 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.



_mm_mask_fnmsub_round_sd

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

Multiplies lower float64 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask3_fnmsub_round_sd

extern __m128d __cdecl _mm_mask3_fnmsub_round_sd(__m128d a, __m128d b, __m128d c, __mmask8 k, int round);

Multiplies lower float64 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_maskz_fnmsub_round_sd

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

Multiplies lower float64 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result lower destination element using zeromask k (the element is zeroed out when mask bit 0 is not set), and copies upper element from a to upper destination element.



_mm_mask_fnmsub_ss

extern __m128 __cdecl _mm_mask_fnmsub_ss(__m128 a, __mmask8 k, __m128 b, __m128 c);

Multiplies lower float32 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result in lower destination element using writemask k (the element is copied from c when mask bit 0 is not set), and copies upper three packed elements from a to upper destination elements.



_mm_mask3_fnmsub_ss

extern __m128 __cdecl _mm_mask3_fnmsub_ss(__m128 a, __m128 b, __m128 c, __mmask8 k);

Multiplies lower float32 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result in lower destination element, and copies upper element from a to upper destination element using writemask k (elements are copied from c when the corresponding mask bit is not set).



_mm_maskz_fnmsub_ss

extern __m128 __cdecl _mm_maskz_fnmsub_ss(__mmask8 k, __m128 a, __m128 b, __m128 c);

Multiplies lower float32 elements in a and b, and subtracts lower element in c from the negated intermediate result. Stores the result in 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.