MULSS - Multiply Scalar Single Precision Floating-Point Values

Opcode/ Instruction

Op / En

64/32 bit Mode Support

CPUID Feature Flag

Description

F3 0F 59 /r MULSS xmm1,xmm2/m32

A

V/V

SSE

Multiply the low single precision floating-point value in xmm2/m32 by the low single precision floating-point value in xmm1.

VEX.LIG.F3.0F.WIG 59 /r VMULSS xmm1,xmm2, xmm3/m32

B

V/V

AVX

Multiply the low single precision floating-point value in xmm3/m32 by the low single precision floating-point value in xmm2.

EVEX.LLIG.F3.0F.W0 59 /r VMULSS xmm1 {k1}{z}, xmm2, xmm3/m32 {er}

C

V/V

AVX512F

Multiply the low single precision floating-point value in xmm3/m32 by the low single precision floating-point value in xmm2.

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

Tuple1 Scalar

ModRM:reg (w)

EVEX.vvvv (r)

ModRM:r/m (r)

N/A

Description

Multiplies the low single precision floating-point value from the second source operand by the low single precision floating-point value in the first source operand, and stores the single precision floating-point result in the destina- tion operand. The second source operand can be an XMM register or a 32-bit memory location. The first source operand and the destination operands are XMM registers.

128-bit Legacy SSE version: The first source operand and the destination operand are the same. Bits (MAXVL- 1:32) of the corresponding YMM destination register remain unchanged.

VEX.128 and EVEX encoded version: The first source operand is an xmm register encoded by VEX.vvvv. The three high-order doublewords of the destination operand are copied from the first source operand. Bits (MAXVL-1:128) of the destination register are zeroed.

EVEX encoded version: The low doubleword element of the destination operand is updated according to the write- mask.

Software should ensure VMULSS is encoded with VEX.L=0. Encoding VMULSS with VEX.L=1 may encounter unpre- dictable behavior across different processor generations.

Operation

VMULSS (EVEX Encoded Version) 

IF (EVEX.b = 1) AND SRC2 *is a register*
   THEN
       SET_ROUNDING_MODE_FOR_THIS_INSTRUCTION(EVEX.RC);
   ELSE 
       SET_ROUNDING_MODE_FOR_THIS_INSTRUCTION(MXCSR.RC);
FI;
IF k1[0] or *no writemask*
   THEN    DEST[31:0] := SRC1[31:0] * SRC2[31:0]
   ELSE 
       IF *merging-masking*                ; merging-masking
            THEN *DEST[31:0] remains unchanged*
            ELSE                            ; zeroing-masking
                THEN DEST[31:0] := 0
            FI
   FI;
ENDFOR
DEST[127:32] := SRC1[127:32]
DEST[MAXVL-1:128] := 0

VMULSS (VEX.128 Encoded Version) 

DEST[31:0] := SRC1[31:0] * SRC2[31:0]
DEST[127:32] := SRC1[127:32]
DEST[MAXVL-1:128] := 0

MULSS (128-bit Legacy SSE Version) 

DEST[31:0] := DEST[31:0] * SRC[31:0]
DEST[MAXVL-1:32] (Unmodified)

Intel C/C++ Compiler Intrinsic Equivalent 

VMULSS __m128 _mm_mask_mul_ss(__m128 s, __mmask8 k, __m128 a, __m128 b);
VMULSS __m128 _mm_maskz_mul_ss( __mmask8 k, __m128 a, __m128 b);
VMULSS __m128 _mm_mul_round_ss( __m128 a, __m128 b, int);
VMULSS __m128 _mm_mask_mul_round_ss(__m128 s, __mmask8 k, __m128 a, __m128 b, int);
VMULSS __m128 _mm_maskz_mul_round_ss( __mmask8 k, __m128 a, __m128 b, int);
MULSS __m128 _mm_mul_ss(__m128 a, __m128 b)

SIMD Floating-Point Exceptions

Underflow, Overflow, Invalid, Precision, Denormal.

Other Exceptions

Non-EVEX-encoded instruction, see Table 2-20, "Type 3 Class Exception Conditions." EVEX-encoded instruction, see Table 2-47, "Type E3 Class Exception Conditions."