모두의 코드
VFMADD132PD, VFMADD213PD, VFMADD231PDs (Intel x86/64 assembly instruction)

작성일 : 2020-09-01 이 글은 712 번 읽혔습니다.

VFMADD132PD, VFMADD213PD, VFMADD231PD

Fused Multiply-Add of Packed Double-Precision Floating-Point Values

참고 사항

아래 표를 해석하는 방법은 x86-64 명령어 레퍼런스 읽는 법 글을 참조하시기 바랍니다.

Opcode/
Instruction

Op/
En

64/32
bit Mode
Support

CPUID
Feature
Flag

Description

VEX.NDS.128.66.0F38.W1 98 /r
VFMADD132PD xmm1 xmm2 xmm3/m128

RVM

V/V

FMA

Multiply packed double-precision floating-point values from xmm1 and xmm3/mem, add to xmm2 and put result in xmm1.

VEX.NDS.128.66.0F38.W1 A8 /r
VFMADD213PD xmm1 xmm2 xmm3/m128

RVM

V/V

FMA

Multiply packed double-precision floating-point values from xmm1 and xmm2, add to xmm3/mem and put result in xmm1.

VEX.NDS.128.66.0F38.W1 B8 /r
VFMADD231PD xmm1 xmm2 xmm3/m128

RVM

V/V

FMA

Multiply packed double-precision floating-point values from xmm2 and xmm3/mem, add to xmm1 and put result in xmm1.

VEX.NDS.256.66.0F38.W1 98 /r
VFMADD132PD ymm1 ymm2 ymm3/m256

RVM

V/V

FMA

Multiply packed double-precision floating-point values from ymm1 and ymm3/mem, add to ymm2 and put result in ymm1.

VEX.NDS.256.66.0F38.W1 A8 /r
VFMADD213PD ymm1 ymm2 ymm3/m256

RVM

V/V

FMA

Multiply packed double-precision floating-point values from ymm1 and ymm2, add to ymm3/mem and put result in ymm1.

VEX.NDS.256.66.0F38.W1 B8 /r
VFMADD231PD ymm1 ymm2 ymm3/m256

RVM

V/V

FMA

Multiply packed double-precision floating-point values from ymm2 and ymm3/mem, add to ymm1 and put result in ymm1.

EVEX.NDS.128.66.0F38.W1 98 /r
VFMADD132PD xmm1 {k1}{z} xmm2 xmm3/m128/m64bcst

RVM

V/V

AVX512VL
AVX512F

Multiply packed double-precision floating-point values from xmm1 and xmm3/m128/m64bcst, add to xmm2 and put result in xmm1.

EVEX.NDS.128.66.0F38.W1 A8 /r
VFMADD213PD xmm1 {k1}{z} xmm2 xmm3/m128/m64bcst

FV

V/V

AVX512VL
AVX512F

Multiply packed double-precision floating-point values from xmm1 and xmm2, add to xmm3/m128/m64bcst and put result in xmm1.

EVEX.NDS.128.66.0F38.W1 B8 /r
VFMADD231PD xmm1 {k1}{z} xmm2 xmm3/m128/m64bcst

FV

V/V

AVX512VL
AVX512F

Multiply packed double-precision floating-point values from xmm2 and xmm3/m128/m64bcst, add to xmm1 and put result in xmm1.

EVEX.NDS.256.66.0F38.W1 98 /r
VFMADD132PD ymm1 {k1}{z} ymm2 ymm3/m256/m64bcst

FV

V/V

AVX512VL
AVX512F

Multiply packed double-precision floating-point values from ymm1 and ymm3/m256/m64bcst, add to ymm2 and put result in ymm1.

EVEX.NDS.256.66.0F38.W1 A8 /r
VFMADD213PD ymm1 {k1}{z} ymm2 ymm3/m256/m64bcst

FV

V/V

AVX512VL
AVX512F

Multiply packed double-precision floating-point values from ymm1 and ymm2, add to ymm3/m256/m64bcst and put result in ymm1.

EVEX.NDS.256.66.0F38.W1 B8 /r
VFMADD231PD ymm1 {k1}{z} ymm2 ymm3/m256/m64bcst

FV

V/V

AVX512VL
AVX512F

Multiply packed double-precision floating-point values from ymm2 and ymm3/m256/m64bcst, add to ymm1 and put result in ymm1.

EVEX.NDS.512.66.0F38.W1 98 /r
VFMADD132PD zmm1 {k1}{z} zmm2 zmm3/m512/m64bcst{er}

FV

V/V

AVX512F

Multiply packed double-precision floating-point values from zmm1 and zmm3/m512/m64bcst, add to zmm2 and put result in zmm1.

EVEX.NDS.512.66.0F38.W1 A8 /r
VFMADD213PD zmm1 {k1}{z} zmm2 zmm3/m512/m64bcst{er}

FV

V/V

AVX512F

Multiply packed double-precision floating-point values from zmm1 and zmm2, add to zmm3/m512/m64bcst and put result in zmm1.

EVEX.NDS.512.66.0F38.W1 B8 /r
VFMADD231PD zmm1 {k1}{z} zmm2 zmm3/m512/m64bcst{er}

FV

V/V

AVX512F

Multiply packed double-precision floating-point values from zmm2 and zmm3/m512/m64bcst, add to zmm1 and put result in zmm1.

Instruction Operand Encoding

Op/En

Operand 1

Operand 2

Operand 3

Operand 4

RVM

ModRM:reg (r, w)

VEX.vvvv (r)

ModRM:r/m (r)

NA

FV

ModRM:reg (r, w)

EVEX.vvvv (r)

ModRM:r/m (r)

NA

Description

Performs a set of SIMD multiply-add computation on packed double-precision floating-point values using three source operands and writes the multiply-add results in the destination operand. The destination operand is also the first source operand. The second operand must be a SIMD register. The third source operand can be a SIMD register or a memory location.

VFMADD132PD: Multiplies the two, four or eight packed double-precision floating-point values from the first source operand to the two, four or eight packed double-precision floating-point values in the third source operand, adds the infinite precision intermediate result to the two, four or eight packed double-precision floating-point values in the second source operand, performs rounding and stores the resulting two, four or eight packed double-precision floating-point values to the destination operand (first source operand).

VFMADD213PD: Multiplies the two, four or eight packed double-precision floating-point values from the second source operand to the two, four or eight packed double-precision floating-point values in the first source operand, adds the infinite precision intermediate result to the two, four or eight packed double-precision floating-point values in the third source operand, performs rounding and stores the resulting two, four or eight packed double-precision floating-point values to the destination operand (first source operand).

VFMADD231PD: Multiplies the two, four or eight packed double-precision floating-point values from the second source to the two, four or eight packed double-precision floating-point values in the third source operand, adds the infinite precision intermediate result to the two, four or eight packed double-precision floating-point values in the first source operand, performs rounding and stores the resulting two, four or eight packed double-precision floating-point values to the destination operand (first source operand).

EVEX encoded versions: The destination operand (also first source operand) is a ZMM register and encoded in regfield. The second source operand is a ZMM register and encoded in EVEX.vvvv. The third source operand is a ZMM register, a 512-bit memory location, or a 512-bit vector broadcasted from a 64-bit memory location. The destination operand is conditionally updated with write mask k1.

VEX.256 encoded version: The destination operand (also first source operand) is a YMM register and encoded in regfield. The second source operand is a YMM register and encoded in VEX.vvvv. The third source operand is a YMM register or a 256-bit memory location and encoded in rmfield.

VEX.128 encoded version: The destination operand (also first source operand) is a XMM register and encoded in regfield. The second source operand is a XMM register and encoded in VEX.vvvv. The third source operand is a XMM register or a 128-bit memory location and encoded in rmfield. The upper 128 bits of the YMM destination register are zeroed.

Operation

VFMADD132PD DEST, SRC2, SRC3 (VEX encoded version)

IF (VEX.128) THEN 
    MAXNUM <- 2
ELSEIF (VEX.256)
    MAXNUM <-  4
FI
For i = 0 to MAXNUM-1 {
    n <-  64*i;
    DEST[n+63:n] <-  RoundFPControl_MXCSR(DEST[n+63:n]*SRC3[n+63:n] + SRC2[n+63:n])
}
IF (VEX.128) THEN
    DEST[MAX_VL-1:128] <-  0
ELSEIF (VEX.256)
    DEST[MAX_VL-1:256] <-  0
FI

VFMADD213PD DEST, SRC2, SRC3 (VEX encoded version)

IF (VEX.128) THEN 
    MAXNUM <- 2
ELSEIF (VEX.256)
    MAXNUM <-  4
FI
For i = 0 to MAXNUM-1 {
    n <-  64*i;
    DEST[n+63:n] <-  RoundFPControl_MXCSR(SRC2[n+63:n]*DEST[n+63:n] + SRC3[n+63:n])
}
IF (VEX.128) THEN
    DEST[MAX_VL-1:128] <-  0
ELSEIF (VEX.256)
    DEST[MAX_VL-1:256] <-  0
FI

VFMADD231PD DEST, SRC2, SRC3 (VEX encoded version)

IF (VEX.128) THEN 
    MAXNUM <- 2
ELSEIF (VEX.256)
    MAXNUM <-  4
FI
For i = 0 to MAXNUM-1 {
    n <-  64*i;
    DEST[n+63:n] <-  RoundFPControl_MXCSR(SRC2[n+63:n]*SRC3[n+63:n] + DEST[n+63:n])
}
IF (VEX.128) THEN
    DEST[MAX_VL-1:128] <-  0
ELSEIF (VEX.256)
    DEST[MAX_VL-1:256] <-  0
FI

VFMADD132PD DEST, SRC2, SRC3 (EVEX encoded version, when src3 operand is a register)

(KL, VL) = (2, 128), (4, 256), (8, 512)
IF (VL = 512) AND (EVEX.b = 1)
    THEN
          SET_RM(EVEX.RC);
    ELSE 
          SET_RM(MXCSR.RM);
FI;
FOR j <-  0 TO KL-1
    i <-  j * 64
    IF k1[j] OR *no writemask*
          THEN DEST[i+63:i] <-  
                RoundFPControl(DEST[i+63:i]*SRC3[i+63:i] + SRC2[i+63:i])
          ELSE 
                IF *merging-masking* ; merging-masking
                      THEN *DEST[i+63:i] remains unchanged*
                      ELSE  ; zeroing-masking
                            DEST[i+63:i] <-  0
                FI
    FI;
ENDFOR
DEST[MAX_VL-1:VL] <-  0

VFMADD132PD DEST, SRC2, SRC3 (EVEX encoded version, when src3 operand is a memory source)

(KL, VL) = (2, 128), (4, 256), (8, 512)
FOR j <-  0 TO KL-1
    i <-  j * 64
    IF k1[j] OR *no writemask*
          THEN 
                IF (EVEX.b = 1) 
                      THEN
                            DEST[i+63:i] <-  
                RoundFPControl_MXCSR(DEST[i+63:i]*SRC3[63:0] + SRC2[i+63:i])
                      ELSE 
                            DEST[i+63:i] <-  
                RoundFPControl_MXCSR(DEST[i+63:i]*SRC3[i+63:i] + SRC2[i+63:i])
                FI;
          ELSE 
                IF *merging-masking* ; merging-masking
                      THEN *DEST[i+63:i] remains unchanged*
                      ELSE  ; zeroing-masking
                            DEST[i+63:i] <-  0
                FI
    FI;
ENDFOR
DEST[MAX_VL-1:VL] <-  0

VFMADD213PD DEST, SRC2, SRC3 (EVEX encoded version, when src3 operand is a is a register)

(KL, VL) = (2, 128), (4, 256), (8, 512)
IF (VL = 512) AND (EVEX.b = 1)
    THEN
          SET_RM(EVEX.RC);
    ELSE 
          SET_RM(MXCSR.RM);
FI;
FOR j <-  0 TO KL-1
    i <-  j * 64
    IF k1[j] OR *no writemask*
          THEN DEST[i+63:i] <-  
                RoundFPControl(SRC2[i+63:i]*DEST[i+63:i] + SRC3[i+63:i])
          ELSE 
                IF *merging-masking* ; merging-masking
                      THEN *DEST[i+63:i] remains unchanged*
                      ELSE  ; zeroing-masking
                            DEST[i+63:i] <-  0
                FI
    FI;
ENDFOR
DEST[MAX_VL-1:VL] <-  0

VFMADD213PD DEST, SRC2, SRC3 (EVEX encoded version, when src3 operand is a memory source)

(KL, VL) = (2, 128), (4, 256), (8, 512)
FOR j <-  0 TO KL-1
    i <-  j * 64
    IF k1[j] OR *no writemask*
          THEN 
                IF (EVEX.b = 1) 
                      THEN
                            DEST[i+63:i] <-  
                RoundFPControl_MXCSR(SRC2[i+63:i]*DEST[i+63:i] + SRC3[63:0])
                      ELSE 
                            DEST[i+63:i] <-  
                RoundFPControl_MXCSR(SRC2[i+63:i]*DEST[i+63:i] + SRC3[i+63:i])
                FI;
          ELSE 
                IF *merging-masking* ; merging-masking
                      THEN *DEST[i+63:i] remains unchanged*
                      ELSE  ; zeroing-masking
                            DEST[i+63:i] <-  0
                FI
    FI;
ENDFOR
DEST[MAX_VL-1:VL] <-  0

VFMADD231PD DEST, SRC2, SRC3 (EVEX encoded version, when src3 operand is a register)

(KL, VL) = (2, 128), (4, 256), (8, 512)
IF (VL = 512) AND (EVEX.b = 1)
    THEN
          SET_RM(EVEX.RC);
    ELSE 
          SET_RM(MXCSR.RM);
FI;
FOR j <-  0 TO KL-1
    i <-  j * 64
    IF k1[j] OR *no writemask*
          THEN DEST[i+63:i] <-  
                RoundFPControl(SRC2[i+63:i]*SRC3[i+63:i] + DEST[i+63:i])
          ELSE 
                IF *merging-masking* ; merging-masking
                      THEN *DEST[i+63:i] remains unchanged*
                      ELSE  ; zeroing-masking
                            DEST[i+63:i] <-  0
                FI
    FI;
ENDFOR
DEST[MAX_VL-1:VL] <-  0

VFMADD231PD DEST, SRC2, SRC3 (EVEX encoded version, when src3 operand is a memory source)

(KL, VL) = (2, 128), (4, 256), (8, 512)
FOR j <-  0 TO KL-1
    i <-  j * 64
    IF k1[j] OR *no writemask*
          THEN 
                IF (EVEX.b = 1) 
                      THEN
                            DEST[i+63:i] <-  
                RoundFPControl_MXCSR(SRC2[i+63:i]*SRC3[63:0] + DEST[i+63:i])
                      ELSE 
                            DEST[i+63:i] <-  
                RoundFPControl_MXCSR(SRC2[i+63:i]*SRC3[i+63:i] + DEST[i+63:i])
                FI;
          ELSE 
                IF *merging-masking* ; merging-masking
                      THEN *DEST[i+63:i] remains unchanged*
                      ELSE  ; zeroing-masking
                            DEST[i+63:i] <-  0
                FI
    FI;
ENDFOR
DEST[MAX_VL-1:VL] <-  0

Intel C/C++ Compiler Intrinsic Equivalent

VFMADDxxxPD __m512d _mm512_fmadd_pd(__m512d a, __m512d b, __m512d c);
VFMADDxxxPD __m512d _mm512_fmadd_round_pd(__m512d a, __m512d b, __m512d c,
                                          int r);
VFMADDxxxPD __m512d _mm512_mask_fmadd_pd(__m512d a, __mmask8 k, __m512d b,
                                         __m512d c);
VFMADDxxxPD __m512d _mm512_maskz_fmadd_pd(__mmask8 k, __m512d a, __m512d b,
                                          __m512d c);
VFMADDxxxPD __m512d _mm512_mask3_fmadd_pd(__m512d a, __m512d b, __m512d c,
                                          __mmask8 k);
VFMADDxxxPD __m512d _mm512_mask_fmadd_round_pd(__m512d a, __mmask8 k, __m512d b,
                                               __m512d c, int r);
VFMADDxxxPD __m512d _mm512_maskz_fmadd_round_pd(__mmask8 k, __m512d a,
                                                __m512d b, __m512d c, int r);
VFMADDxxxPD __m512d _mm512_mask3_fmadd_round_pd(__m512d a, __m512d b, __m512d c,
                                                __mmask8 k, int r);
VFMADDxxxPD __m256d _mm256_mask_fmadd_pd(__m256d a, __mmask8 k, __m256d b,
                                         __m256d c);
VFMADDxxxPD __m256d _mm256_maskz_fmadd_pd(__mmask8 k, __m256d a, __m256d b,
                                          __m256d c);
VFMADDxxxPD __m256d _mm256_mask3_fmadd_pd(__m256d a, __m256d b, __m256d c,
                                          __mmask8 k);
VFMADDxxxPD __m128d _mm_mask_fmadd_pd(__m128d a, __mmask8 k, __m128d b,
                                      __m128d c);
VFMADDxxxPD __m128d _mm_maskz_fmadd_pd(__mmask8 k, __m128d a, __m128d b,
                                       __m128d c);
VFMADDxxxPD __m128d _mm_mask3_fmadd_pd(__m128d a, __m128d b, __m128d c,
                                       __mmask8 k);
VFMADDxxxPD __m128d _mm_fmadd_pd(__m128d a, __m128d b, __m128d c);
VFMADDxxxPD __m256d _mm256_fmadd_pd(__m256d a, __m256d b, __m256d c);

SIMD Floating-Point Exceptions

Overflow, Underflow, Invalid, Precision, Denormal

Other Exceptions

VEX-encoded instructions, see Exceptions Type 2.

EVEX-encoded instructions, see Exceptions Type E2.

첫 댓글을 달아주세요!
프로필 사진 없음
강좌에 관련 없이 궁금한 내용은 여기를 사용해주세요

    댓글을 불러오는 중입니다..