Chapter 4. Floating-Point Unit (FPU)
For More Information On This Product,
Go to: www.freescale.com
4-19
FPU Programmer’s Model
4.3.6 Floating-Point Exceptions
This section describes floating-point exceptions and how they are handled. Table 4-10 lists
the vector numbers related to floating-point exceptions. If the exception is taken
pre-instruction, the PC contains the address of the next floating-point instruction (nextFP).
If the exception is taken post-instruction, the PC contains the address of the faulting
instruction (fault).
In addition to these vectors, attempting to execute a FRESTORE instruction with a
unsupported frame value generates a format error exception (vector 14). See the
FRESTORE instruction in the
PRM
.
UGT
Unordered or greater than
NAN | (N | Z)
001010
No
OGL
Ordered greater or less than
NAN | Z
000110
No
UEQ
Unordered or equal
NAN | Z
001001
No
OR
Ordered
NAN
000111
No
UN
Unordered
NAN
001000
No
Miscellaneous Tests
F
False
False
000000
No
T
True
True
001111
No
SF
Signaling false
False
010000
Yes
ST
Signaling true
True
011111
Yes
SEQ
Signaling equal
Z
010001
Yes
SNE
Signaling not equal
Z
011110
Yes
1
This column refers to the value in the instruction’s conditional predicate field that specifies this test.
Table 4-10. Floating-Point Exception Vectors
Vector Number
Vector Offset Program Counter
Assignment
48
0x0C0
Fault
Floating-point branch/set on unordered condition
49
0x0C4
NextFP or Fault
Floating-point inexact result
50
0x0C8
NextFP
Floating-point divide-by-zero
51
0x0CC
NextFP or Fault
Floating-point underflow
52
0x0D0
NextFP or Fault
Floating-point operand error
53
0x0D4
NextFP or Fault
Floating-point overflow
54
0x0D8
NextFP or Fault
Floating-point input NAN
55
0x0DC
NextFP or Fault
Floating-point input denormalized number
Table 4-9. Floating-Point Conditional Tests (Continued)
Mnemonic
Definition
Equation
Predicate
1
EXC[BSUN] Set
F
Freescale Semiconductor, Inc.
n
.