Motorola DSP96002 - Manual (Page 284)

A - 96 DSP96002 USER’S MANUAL MOTOROLA
FADDSUB.X Add and Subtract FADDSUB.X
Description:
Add and subtract the two specified operands and round to single extended precision. Store the result of
the addition in D2 and of the subtraction in D1.
Input Operand(s) Precision: SEP Floating-Point.
Output Operand(s) Precision: SEP Floating-Point.
CCR Condition Codes:
C - Not affected.
V - Not affected.
Z - Set if result of the addition is zero. Cleared otherwise.
N - Set if result of the addition is negative. Cleared otherwise.
I - Set if result of the addition is infinity. Cleared otherwise.
LR - Not affected.
–
R - Not affected.
A - Not affected.
ER Status Bits:
INX -Set if the addition or subtraction result is inexact. Cleared otherwise.
DZ -Always cleared.
UNF -Set if the addition or subtraction result underflows. Cleared otherwise.
OVF -Set if the addition or subtraction result overflows. Cleared otherwise.
OPERR -Set if operands of the addition are opposite-signed infinities or if the operands of
the subtraction are like-signed infinities. Cleared otherwise.
SNAN -Set if any operand is a signaling NaN. Cleared otherwise.
NAN -Set if result of the addition is a NaN. Cleared otherwise.
UNCC -Always cleared.
IER Flags: Flags changed according to standard definition.
Assembler Syntax:
FADDSUB.X D1,D2 (move syntax - see the MOVE
instruction description.)
Operation:
D1 + D2
→
ROUND(SEP)
→
D2
(parallel data bus move)
D1 - D2
→
ROUND(SEP)
→
D1