
MOTOROLA
6-44
EXCEPTIONS
For More Information On This Product,
Go to: www.freescale.com
RCPU
REFERENCE MANUAL
6.11.10.8 Overflow Exception Condition
Overflow occurs when the magnitude of what would have been the rounded result
if the exponent range were unbounded exceeds that of the largest finite number of
the specified result precision.
The action to be taken depends on the setting of the overflow exception condition
enable bit of the FPSCR. When the overflow exception condition is enabled (FP-
SCR[OE] = 1) and an exponent overflow condition occurs, the following actions are
taken:
Overflow exception condition bit is set: FPSCR[OX] = 1.
For double-precision arithmetic instructions, the exponent of the normalized
intermediate result is adjusted by subtracting 1536.
For single-precision arithmetic instructions and the floating round to single-
precision instruction, the exponent of the normalized intermediate result is ad-
justed by subtracting 192.
The adjusted rounded result is placed into the target FPR.
FPSCR[FPRF] is set to indicate the class and sign of the result (±normal num-
ber).
When the overflow exception condition is disabled (FPSCR[OE] = 0) and an over-
flow condition occurs, the following actions are taken:
Overflow exception condition bit is set: FPSCR[OX] = 1
Inexact exception condition bit is set: FPSCR[XX] = 1
The result is determined by the rounding mode (FPSCR[RN]) and the sign of
the intermediate result as follows:
— Round to nearest
Store ± infinity, where the sign is the sign of the intermediate result
— Round toward zero
Store the format's largest finite number with the sign of the intermediate
result
— Round toward +infinity
For negative overflows, store the format's most negative finite number; for
positive overflows, store +infinity
— Round toward –infinity
For negative overflows, store –infinity; for positive overflows, store the for-
mat's largest finite number
The result is placed into the target FPR
FPSCR[FR FI] are cleared
FPSCR[FPRF] is set to indicate the class and sign of the result (±infinity or
±normal number)
6.11.10.9 Underflow Exception Condition
The underflow exception condition is defined separately for the enabled and dis-
abled states:
Enabled — Underflow occurs when the intermediate result is tiny.
Disabled — Underflow occurs when the intermediate result is tiny and there is
loss of accuracy.
F
Freescale Semiconductor, Inc.
n
.