Table 22-12 Single-Precision Float-To-Integer Bounce Thresholds And Stored Results - ARM ARM1176JZF-S Technical Reference Manual

Floating-point
value
NaN
0x7F800000
0x7F7FFFFF
to
0x4F800000
0x4F7FFFFF
to
0x4F000000
0x4EFFFFFF
to
0x4E800000
0x4E7FFFFF
to
0x00000000
0x80000000
to
0xCE7FFFFF
0xCE800000
to
0xCEFFFFFF
0xCF000000
0xCF000000
to
0xFF7FFFFF
0xFF800000
a. SP = single-precision.
b. A negative input value that rounds to a zero result returns zero and is not invalid.
ARM DDI 0301H
ID012310
In the Unsigned results and Signed results columns, the rounding mode notations are:
N Round-to-nearest mode.
P Round-towards-plus-infinity mode.
M Round-towards-minus infinity mode.
Z Round-towards-zero mode.
Table 22-12 lists the single-precision float-to-integer bounce range and the results returned for
exceptional conditions. The exponent values that Table 22-12 lists are in biased format.

Table 22-12 Single-precision float-to-integer bounce thresholds and stored results

Integer value Unsigned result
-
0x00000000
+infinity 0xFFFFFFFF
a 0xFFFFFFFF
+maximum SP
to
32
2
32 8 0xFFFFFF00
2 – 2
to
to
0x80000000
31
2
31 7
2 – 2 0x7FFFFF80
to
to
30 0x40000000
2
30 6 0x3FFFFFC0
2 – 2
to
to
0x00000000
+0
–0 0x00000000
to
30 6
–2 + 2
30
–2 0x00000000
to
31 7
–2 + 2 )
31 0x00000000
–2
31 0x00000000
–2
to
–maximum SP
–infinity
0x00000000
Copyright © 2004-2009 ARM Limited. All rights reserved.
Non-Confidential, Unrestricted Access
Status Signed result
Invalid
0x00000000
Invalid 0x7FFFFFFF
Invalid 0x7FFFFFFF
Valid
0x7FFFFFFF
Valid
0x7FFFFF80
to
0x40000000
Valid
0x3FFFFFC0
to
0x00000000
b 0x00000000
Invalid
to
0xC0000040
Invalid
0xC0000000
to
0x80000080
Invalid 0x80000000
Invalid 0x80000000
Invalid
0x80000000
VFP Exception Handling
Status Response
Invalid Bounce all
Invalid Bounce all
Invalid Bounce all
Invalid Bounce S UnZ
Valid Bounce SnZ
Valid No bounce
Valid Bounce U
Valid Bounce U
Valid Bounce U SnZ
Invalid Bounce all
Invalid Bounce all
22-25