MOVSD — Move or Merge Scalar Double Precision Floating-Point Value

Opcode/Instruction Op / En 64/32 bit Mode Support CPUID Feature Flag Description
F2 0F 10 /r MOVSD xmm1, xmm2 A V/V SSE2 Move scalar double precision floating-point value from xmm2 to xmm1 register.
F2 0F 10 /r MOVSD xmm1, m64 A V/V SSE2 Load scalar double precision floating-point value from m64 to xmm1 register.
F2 0F 11 /r MOVSD xmm1/m64, xmm2 C V/V SSE2 Move scalar double precision floating-point value from xmm2 register to xmm1/m64.
VEX.LIG.F2.0F.WIG 10 /r VMOVSD xmm1, xmm2, xmm3 B V/V AVX Merge scalar double precision floating-point value from xmm2 and xmm3 to xmm1 register.
VEX.LIG.F2.0F.WIG 10 /r VMOVSD xmm1, m64 D V/V AVX Load scalar double precision floating-point value from m64 to xmm1 register.
VEX.LIG.F2.0F.WIG 11 /r VMOVSD xmm1, xmm2, xmm3 E V/V AVX Merge scalar double precision floating-point value from xmm2 and xmm3 registers to xmm1.
VEX.LIG.F2.0F.WIG 11 /r VMOVSD m64, xmm1 C V/V AVX Store scalar double precision floating-point value from xmm1 register to m64.
EVEX.LLIG.F2.0F.W1 10 /r VMOVSD xmm1 {k1}{z}, xmm2, xmm3 B V/V AVX512F Merge scalar double precision floating-point value from xmm2 and xmm3 registers to xmm1 under writemask k1.
EVEX.LLIG.F2.0F.W1 10 /r VMOVSD xmm1 {k1}{z}, m64 F V/V AVX512F Load scalar double precision floating-point value from m64 to xmm1 register under writemask k1.
EVEX.LLIG.F2.0F.W1 11 /r VMOVSD xmm1 {k1}{z}, xmm2, xmm3 E V/V AVX512F Merge scalar double precision floating-point value from xmm2 and xmm3 registers to xmm1 under writemask k1.
EVEX.LLIG.F2.0F.W1 11 /r VMOVSD m64 {k1}, xmm1 G V/V AVX512F Store scalar double precision floating-point value from xmm1 register to m64 under writemask k1.

Instruction Operand Encoding

Op/En Tuple Type Operand 1 Operand 2 Operand 3 Operand 4
A N/A ModRM:reg (r, w) ModRM:r/m (r) N/A N/A
B N/A ModRM:reg (w) VEX.vvvv (r) ModRM:r/m (r) N/A
C N/A ModRM:r/m (w) ModRM:reg (r) N/A N/A
D N/A ModRM:reg (w) ModRM:r/m (r) N/A N/A
E N/A ModRM:r/m (w) EVEX.vvvv (r) ModRM:reg (r) N/A
F Tuple1 Scalar ModRM:reg (r, w) ModRM:r/m (r) N/A N/A
G Tuple1 Scalar ModRM:r/m (w) ModRM:reg (r) N/A N/A

Description

Moves a scalar double precision floating-point value from the source operand (second operand) to the destination operand (first operand). The source and destination operands can be XMM registers or 64-bit memory locations. This instruction can be used to move a double precision floating-point value to and from the low quadword of an XMM register and a 64-bit memory location, or to move a double precision floating-point value between the low quadwords of two XMM registers. The instruction cannot be used to transfer data between memory locations.

Legacy version: When the source and destination operands are XMM registers, bits MAXVL:64 of the destination operand remains unchanged. When the source operand is a memory location and destination operand is an XMM

registers, the quadword at bits 127:64 of the destination operand is cleared to all 0s, bits MAXVL:128 of the destination operand remains unchanged.

VEX and EVEX encoded register-register syntax: Moves a scalar double precision floating-point value from the second source operand (the third operand) to the low quadword element of the destination operand (the first operand). Bits 127:64 of the destination operand are copied from the first source operand (the second operand). Bits (MAXVL-1:128) of the corresponding destination register are zeroed.

VEX and EVEX encoded memory store syntax: When the source operand is a memory location and destination operand is an XMM registers, bits MAXVL:64 of the destination operand is cleared to all 0s.

EVEX encoded versions: The low quadword of the destination is updated according to the writemask.

Note: For VMOVSD (memory store and load forms), VEX.vvvv and EVEX.vvvv are reserved and must be 1111b, otherwise instruction will #UD.

Operation

VMOVSD (EVEX.LLIG.F2.0F 10 /r: VMOVSD xmm1, m64 With Support for 32 Registers)

IF k1[0] or *no writemask*
    THEN DEST[63:0] := SRC[63:0]
    ELSE
        IF *merging-masking* ; merging-masking
            THEN *DEST[63:0] remains unchanged*
            ELSE ; zeroing-masking
                THEN DEST[63:0] := 0
        FI;
FI;
DEST[MAXVL-1:64] := 0

VMOVSD (EVEX.LLIG.F2.0F 11 /r: VMOVSD m64, xmm1 With Support for 32 Registers)

IF k1[0] or *no writemask*
    THEN DEST[63:0] := SRC[63:0]
    ELSE *DEST[63:0] remains unchanged* ; merging-masking
FI;

VMOVSD (EVEX.LLIG.F2.0F 11 /r: VMOVSD xmm1, xmm2, xmm3)

IF k1[0] or *no writemask*
    THEN DEST[63:0] := SRC2[63:0]
    ELSE
        IF *merging-masking* ; merging-masking
            THEN *DEST[63:0] remains unchanged*
            ELSE ; zeroing-masking
                THEN DEST[63:0] := 0
        FI;
FI;
DEST[127:64] := SRC1[127:64]
DEST[MAXVL-1:128] := 0

MOVSD (128-bit Legacy SSE Version: MOVSD xmm1, xmm2)

DEST[63:0] := SRC[63:0]
DEST[MAXVL-1:64] (Unmodified)

VMOVSD (VEX.128.F2.0F 11 /r: VMOVSD xmm1, xmm2, xmm3)

DEST[63:0] := SRC2[63:0]
DEST[127:64] := SRC1[127:64]
DEST[MAXVL-1:128] := 0

VMOVSD (VEX.128.F2.0F 10 /r: VMOVSD xmm1, xmm2, xmm3)

DEST[63:0] := SRC2[63:0]
DEST[127:64] := SRC1[127:64]
DEST[MAXVL-1:128] := 0

VMOVSD (VEX.128.F2.0F 10 /r: VMOVSD xmm1, m64)

DEST[63:0] := SRC[63:0]
DEST[MAXVL-1:64] := 0

MOVSD/VMOVSD (128-bit Versions: MOVSD m64, xmm1 or VMOVSD m64, xmm1)

DEST[63:0] := SRC[63:0]

MOVSD (128-bit Legacy SSE Version: MOVSD xmm1, m64)

DEST[63:0] := SRC[63:0]
DEST[127:64] := 0
DEST[MAXVL-1:128] (Unmodified)

Intel C/C++ Compiler Intrinsic Equivalent

VMOVSD __m128d _mm_mask_load_sd(__m128d s, __mmask8 k, double * p);
VMOVSD __m128d _mm_maskz_load_sd( __mmask8 k, double * p);
VMOVSD __m128d _mm_mask_move_sd(__m128d sh, __mmask8 k, __m128d sl, __m128d a);
VMOVSD __m128d _mm_maskz_move_sd( __mmask8 k, __m128d s, __m128d a);
VMOVSD void _mm_mask_store_sd(double * p, __mmask8 k, __m128d s);
MOVSD __m128d _mm_load_sd (double *p)
MOVSD void _mm_store_sd (double *p, __m128d a)
MOVSD __m128d _mm_move_sd ( __m128d a, __m128d b)

SIMD Floating-Point Exceptions

None.

Other Exceptions

Non-EVEX-encoded instruction, see Table 2-22, “Type 5 Class Exception Conditions,” additionally:

#UD If VEX.vvvv != 1111B.

EVEX-encoded instruction, see Table 2-58, “Type E10 Class Exception Conditions.”