fnmul
Floating-Point Negated Multiply (Scalar)
FNMUL <Hd|Sd|Dd>, <Hn|Sn|Dn>, <Hm|Sm|Dm>
Calculates -(Vn * Vm).
Details
Floating-Point Negated Multiply computes the negation of the product of two floating-point values: -(Vn × Vm), writing the result to Vd. Supports half-precision (type=0, 16-bit), single-precision (type=1, 32-bit), and double-precision (type=2, 64-bit) operands. FPSR exception flags may be set based on invalid, inexact, or overflow conditions. This instruction executes only in AArch64 state.
Pseudocode Operation
if type == 0:
Vd ← -(Vn_float16 × Vm_float16)
else if type == 1:
Vd ← -(Vn_float32 × Vm_float32)
else if type == 2:
Vd ← -(Vn_float64 × Vm_float64)
Example
FNMUL Dd, Dn, Dm
Encoding
Binary Layout
0
0
0
11110
00
1
Rm
1
00010
Rn
Rd
Operands
-
Vd
Destination SIMD/FP vector register -
Vn
First source SIMD/FP vector register -
Vm
Second source SIMD/FP vector register
Reference (Arm A64 ISA)
Instruction Forms
| Encoding | Instruction | ISA | Bit pattern | ||
|---|---|---|---|---|---|
| 0x1EE08800 | FNMUL <Hd>, <Hn>, <Hm> | A64 | 0 | 0 | 0 | 11110 | 11 | 1 | Rm | 1 | 00010 | Rn | Rd | ||
| 0x1E208800 | FNMUL <Sd>, <Sn>, <Sm> | A64 | 0 | 0 | 0 | 11110 | 00 | 1 | Rm | 1 | 00010 | Rn | Rd | ||
| 0x1E608800 | FNMUL <Dd>, <Dn>, <Dm> | A64 | 0 | 0 | 0 | 11110 | 01 | 1 | Rm | 1 | 00010 | Rn | Rd |
Description
Floating-point Multiply-Negate (scalar). This instruction multiplies the floating-point values of the two source SIMD&FP registers, and writes the negation of the result to the destination SIMD&FP register.
This instruction can generate a floating-point exception. Depending on the settings in FPCR, the exception results in either a flag being set in FPSR, or a synchronous exception being generated. For more information, see Floating-point exception traps.
Depending on the settings in the CPACR_EL1, CPTR_EL2, and CPTR_EL3 registers, and the current Security state and Exception level, an attempt to execute the instruction might be trapped.
Operation
CheckFPEnabled64(); bits(esize) operand1 = V[n, esize]; bits(esize) operand2 = V[m, esize]; boolean merge = IsMerging(FPCR); bits(128) result = if merge then V[n, 128] else Zeros(128); bits(esize) product = FPMul(operand1, operand2, FPCR); product = FPNeg(product, FPCR); Elem[result, 0, esize] = product; V[d, 128] = result;