frinta
Floating-Point Round to Integral (Nearest)
FRINTA <Hd|Sd|Dd>, <Hn|Sn|Dn>
Rounds float to nearest integral value (ties away from zero).
Details
Rounds a floating-point scalar value to the nearest integral value, with ties rounded away from zero. The rounding mode is always "round to nearest, ties away from zero" regardless of the FPCR rounding mode setting. This is an AArch64-only instruction that does not modify condition flags.
Pseudocode Operation
rounded_val ← RoundToIntegral_TiesAwayFromZero(Vn)
Vd ← rounded_val
Example
FRINTA Dd, Dn
Encoding
Binary Layout
0
0
0
11110
00
1001
100
10000
Rn
Rd
Operands
-
Vd
Destination SIMD/FP vector register -
Vn
First source SIMD/FP vector register
Reference (Arm A64 ISA)
Instruction Forms
| Encoding | Instruction | ISA | Bit pattern | ||
|---|---|---|---|---|---|
| 0x2E798800 | FRINTA <Vd>.<T>, <Vn>.<T> | A64 | 0 | Q | 1 | 01110 | 0 | 1111001100 | 0 | 10 | Rn | Rd | ||
| 0x2E218800 | FRINTA <Vd>.<T>, <Vn>.<T> | A64 | 0 | Q | 1 | 01110 | 0 | sz | 100001100 | 0 | 10 | Rn | Rd | ||
| 0x1EE64000 | FRINTA <Hd>, <Hn> | A64 | 0 | 0 | 0 | 11110 | 11 | 1001 | 100 | 10000 | Rn | Rd | ||
| 0x1E264000 | FRINTA <Sd>, <Sn> | A64 | 0 | 0 | 0 | 11110 | 00 | 1001 | 100 | 10000 | Rn | Rd | ||
| 0x1E664000 | FRINTA <Dd>, <Dn> | A64 | 0 | 0 | 0 | 11110 | 01 | 1001 | 100 | 10000 | Rn | Rd | ||
| 0xC1ACE000 | FRINTA { <Zd1>.S-<Zd2>.S }, { <Zn1>.S-<Zn2>.S } | A64 | 11000001 | 1 | 0 | 101 | 10 | 0 | 111000 | Zn | 0 | Zd | 0 | ||
| 0xC1BCE000 | FRINTA { <Zd1>.S-<Zd4>.S }, { <Zn1>.S-<Zn4>.S } | A64 | 11000001 | 1 | 0 | 111 | 10 | 0 | 111000 | Zn | 00 | Zd | 00 | ||
| 0x6504A000 | FRINTA <Zd>.<T>, <Pg>/M, <Zn>.<T> | A64 | 01100101 | size | 000 | 10 | 0 | 101 | Pg | Zn | Zd |
Description
Floating-point Round to Integral, to nearest with ties to Away (scalar). This instruction rounds a floating-point value in the SIMD&FP source register to an integral floating-point value of the same size using the Round to Nearest with Ties to Away rounding mode, and writes the result to the SIMD&FP destination register.
A zero input gives a zero result with the same sign, an infinite input gives an infinite result with the same sign, and a NaN is propagated as for normal arithmetic.
A floating-point exception can be generated by this instruction. 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(); boolean merge = IsMerging(FPCR); bits(128) result = if merge then V[d, 128] else Zeros(128); bits(esize) operand = V[n, esize]; Elem[result, 0, esize] = FPRoundInt(operand, FPCR, FPRounding_TIEAWAY, FALSE); V[d, 128] = result;