fdiv
Floating-Point Divide (Scalar)
FDIV <Hd|Sd|Dd>, <Hn|Sn|Dn>, <Hm|Sm|Dm>
Divides two floating-point values.
Details
Divides one scalar floating-point operand by another and writes the result to the destination register. The operation respects IEEE 754 rounding modes and may generate floating-point exception conditions (invalid, overflow, underflow, inexact, divide-by-zero). The instruction operates on Half-precision (16-bit), Single-precision (32-bit), or Double-precision (64-bit) formats, determined by the type field. This is an AArch64-only instruction.
Pseudocode Operation
Example
FDIV Dd, Dn, Dm
Encoding
Binary Layout
0
0
0
11110
00
1
Rm
0001
10
Rn
Rd
Operands
-
Vd
Destination SIMD/FP vector register -
Vn
Dividend -
Vm
Divisor
Reference (Arm A64 ISA)
Instruction Forms
| Encoding | Instruction | ISA | Bit pattern | ||
|---|---|---|---|---|---|
| 0x2E403C00 | FDIV <Vd>.<T>, <Vn>.<T>, <Vm>.<T> | A64 | 0 | Q | 1 | 01110 | 0 | 10 | Rm | 00 | 111 | 1 | Rn | Rd | ||
| 0x2E20FC00 | FDIV <Vd>.<T>, <Vn>.<T>, <Vm>.<T> | A64 | 0 | Q | 1 | 011100 | sz | 1 | Rm | 11111 | 1 | Rn | Rd | ||
| 0x1EE01800 | FDIV <Hd>, <Hn>, <Hm> | A64 | 0 | 0 | 0 | 11110 | 11 | 1 | Rm | 0001 | 10 | Rn | Rd | ||
| 0x1E201800 | FDIV <Sd>, <Sn>, <Sm> | A64 | 0 | 0 | 0 | 11110 | 00 | 1 | Rm | 0001 | 10 | Rn | Rd | ||
| 0x1E601800 | FDIV <Dd>, <Dn>, <Dm> | A64 | 0 | 0 | 0 | 11110 | 01 | 1 | Rm | 0001 | 10 | Rn | Rd | ||
| 0x650D8000 | FDIV <Zdn>.<T>, <Pg>/M, <Zdn>.<T>, <Zm>.<T> | A64 | 01100101 | size | 00 | 110 | 1 | 100 | Pg | Zm | Zdn |
Description
Floating-point Divide (scalar). This instruction divides the floating-point value of the first source SIMD&FP register by the floating-point value of the second source SIMD&FP register, and writes 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); Elem[result, 0, esize] = FPDiv(operand1, operand2, FPCR); V[d, 128] = result;