SUBSD — Subtract Scalar Double-Precision Floating-Point Value

Opcode/Instruction	Op / En	64/32 bit Mode Support	CPUID Feature Flag	Description
F2 0F 5C /r SUBSD xmm1, xmm2/m64	A	V/V	SSE2	Subtract the low double-precision floating-point value in xmm2/m64 from xmm1 and store the result in xmm1.
VEX.NDS.LIG.F2.0F.WIG 5C /r VSUBSD xmm1,xmm2, xmm3/m64	B	V/V	AVX	Subtract the low double-precision floating-point value in xmm3/m64 from xmm2 and store the result in xmm1.
EVEX.NDS.LIG.F2.0F.W1 5C /r VSUBSD xmm1 {k1}{z}, xmm2, xmm3/m64{er}	C	V/V	AVX512F	Subtract the low double-precision floating-point value in xmm3/m64 from xmm2 and store the result in xmm1 under writemask k1.

Instruction Operand Encoding ¶

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

Description ¶

Subtract the low double-precision floating-point value in the second source operand from the first source operand and stores the double-precision floating-point result in the low quadword of the destination operand.

The second source operand can be an XMM register or a 64-bit memory location. The first source and destination operands are XMM registers.

128-bit Legacy SSE version: The destination and first source operand are the same. Bits (MAXVL-1:64) of the corresponding destination register remain unchanged.

VEX.128 and EVEX encoded versions: Bits (127:64) of the XMM register destination are copied from corresponding bits in the first source operand. Bits (MAXVL-1:128) of the destination register are zeroed.

EVEX encoded version: The low quadword element of the destination operand is updated according to the writemask.

Software should ensure VSUBSD is encoded with VEX.L=0. Encoding VSUBSD with VEX.L=1 may encounter unpredictable behavior across different processor generations.

Operation ¶

VSUBSD (EVEX encoded version) ¶

IF (SRC2 *is register*) AND (EVEX.b = 1)
    THEN
        SET_RM(EVEX.RC);
    ELSE
        SET_RM(MXCSR.RM);
FI;
IF k1[0] or *no writemask*
    THEN DEST[63:0]←SRC1[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

VSUBSD (VEX.128 encoded version) ¶

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

SUBSD (128-bit Legacy SSE version) ¶

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

Intel C/C++ Compiler Intrinsic Equivalent ¶

VSUBSD __m128d _mm_mask_sub_sd (__m128d s, __mmask8 k, __m128d a, __m128d b);

VSUBSD __m128d _mm_maskz_sub_sd (__mmask8 k, __m128d a, __m128d b);

VSUBSD __m128d _mm_sub_round_sd (__m128d a, __m128d b, int);

VSUBSD __m128d _mm_mask_sub_round_sd (__m128d s, __mmask8 k, __m128d a, __m128d b, int);

VSUBSD __m128d _mm_maskz_sub_round_sd (__mmask8 k, __m128d a, __m128d b, int);

SUBSD __m128d _mm_sub_sd (__m128d a, __m128d b);

SIMD Floating-Point Exceptions ¶

Overflow, Underflow, Invalid, Precision, Denormal

Other Exceptions ¶

VEX-encoded instructions, see Exceptions Type 3.

EVEX-encoded instructions, see Exceptions Type E3.