fcvtps
Floating-Point Convert to Signed Integer (Plus Infinity)
FCVTPS <Wd|Xd>, <Hn|Sn|Dn>
Converts float to signed integer, rounding towards plus infinity (Ceil).
Details
Converts a floating-point value to a signed integer, rounding towards plus infinity (ceiling). The source is read from a half-precision (H), single-precision (S), or double-precision (D) FP register, and the result is written to a 32-bit (W) or 64-bit (X) general-purpose register. NZCV flags are not affected by this instruction. This is an AArch64-only instruction that executes at any privilege level.
Pseudocode Operation
if source_is_nan then
result ← 0
else
result ← round_to_plus_infinity(FP_to_signed_integer(Vn))
Rd ← result
Example
FCVTPS Wd, Dn
Encoding
Binary Layout
0
0
0
11110
00
1
01
000
000000
Rn
Rd
Operands
-
Rd
Int Dest -
Vn
Float Src
Reference (Arm A64 ISA)
Instruction Forms
| Encoding | Instruction | ISA | Bit pattern | ||
|---|---|---|---|---|---|
| 0x5EF9A800 | FCVTPS <Hd>, <Hn> | A64 | 01 | 0 | 11110 | 1 | 1111001101 | 0 | 10 | Rn | Rd | ||
| 0x5EA1A800 | FCVTPS <V><d>, <V><n> | A64 | 01 | 0 | 11110 | 1 | sz | 100001101 | 0 | 10 | Rn | Rd | ||
| 0x0EF9A800 | FCVTPS <Vd>.<T>, <Vn>.<T> | A64 | 0 | Q | 0 | 01110 | 1 | 1111001101 | 0 | 10 | Rn | Rd | ||
| 0x0EA1A800 | FCVTPS <Vd>.<T>, <Vn>.<T> | A64 | 0 | Q | 0 | 01110 | 1 | sz | 100001101 | 0 | 10 | Rn | Rd | ||
| 0x1EE80000 | FCVTPS <Wd>, <Hn> | A64 | 0 | 0 | 0 | 11110 | 11 | 1 | 01 | 000 | 000000 | Rn | Rd | ||
| 0x9EE80000 | FCVTPS <Xd>, <Hn> | A64 | 1 | 0 | 0 | 11110 | 11 | 1 | 01 | 000 | 000000 | Rn | Rd | ||
| 0x1E280000 | FCVTPS <Wd>, <Sn> | A64 | 0 | 0 | 0 | 11110 | 00 | 1 | 01 | 000 | 000000 | Rn | Rd | ||
| 0x9E280000 | FCVTPS <Xd>, <Sn> | A64 | 1 | 0 | 0 | 11110 | 00 | 1 | 01 | 000 | 000000 | Rn | Rd | ||
| 0x1E680000 | FCVTPS <Wd>, <Dn> | A64 | 0 | 0 | 0 | 11110 | 01 | 1 | 01 | 000 | 000000 | Rn | Rd | ||
| 0x9E680000 | FCVTPS <Xd>, <Dn> | A64 | 1 | 0 | 0 | 11110 | 01 | 1 | 01 | 000 | 000000 | Rn | Rd |
Description
Floating-point Convert to Signed integer, rounding toward Plus infinity (scalar). This instruction converts the floating-point value in the SIMD&FP source register to a 32-bit or 64-bit signed integer using the Round towards Plus Infinity rounding mode, and writes the result to the general-purpose destination register.
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(); bits(decode_fltsize) fltval; bits(intsize) intval; fltval = V[n, decode_fltsize]; intval = FPToFixed(fltval, 0, FALSE, FPCR, rounding, intsize); X[d, intsize] = intval;