You copied the Doc URL to your clipboard.
VRINT (floating-point)
Rounds a floating-point number to integer and places the result in the destination register. The resulting integer is represented in floating-point format.
Note
This instruction is supported only in ARMv8.Syntax
VRINT
{mode
}.F64.F64 cond
, Dd
Dm
VRINT
{mode
}.F32.F32 cond
, Sd
Sm
where:
mode
must be one of:
Z
meaning round towards zero.
R
- meaning use the rounding mode specified in the FPSCR.
X
- meaning use the rounding mode specified in the FPSCR, generating an Inexact exception if the result is not exact.
A
- meaning round to nearest, ties away from zero.
N
- meaning round to nearest, ties to even.
P
- meaning round towards plus infinity.
M
- meaning round towards minus infinity.
cond
- is an optional condition code. This can only be
used when
mode
is Z, R or X. Sd, Sm
- specifies the destination and operand registers, for a word operation.
Dd, Dm
- specifies the destination and operand registers, for a doubleword operation.
Notes
You cannot use VRINT
with a rounding
mode of A, N, P or M inside
an IT block.
Floating-point exceptions
These instructions cannot produce any exceptions, except VRINTX
which
can generate an Inexact exception.