mc68ec060 Freescale Semiconductor, Inc, mc68ec060 Datasheet - Page 129

• Manufacturer Part Number: mc68ec060
• Description: Mc68060 Superscalar 68k Microprocessor Including The Lc060 And Ec060
• Manufacturer: Freescale Semiconductor, Inc

6.3 COMPUTATIONAL ACCURACY
Whenever an attempt is made to represent a real number in a binary format of finite preci-
sion, there is a possibility that the number can not be represented exactly. This is commonly
referred to as a round-off error. Furthermore, when two inexact numbers are used in a cal-
culation, the error present in each number is reflected, and possibly aggravated, in the
result. All FPU calculations use an intermediate result. When the MC68060 performs an
operation, the calculation is carried out using extended-precision inputs, and the intermedi-
ate result is calculated as if to produce infinite precision. After the calculation is complete,
the intermediate result is rounded to the selected precision and stored in the destination.
The FPCR RND and PREC encodings (see Table 6-1 and Table 6-2) provide emulation for
devices that only support single and double precision. By setting the rounding precision to
single, the MC68060 will perform all calculations as if only 24 bits of precision were available
for the result. Setting the rounding precision to double does the same to 53 bits of precision.
The execution speed of all instructions is the same whether using single- or double-precision
rounding. When using these two forced rounding precisions, the MC68060 produces the
same results as any other device that conforms to the IEEE 754 standard, but does not sup-
port extended precision. The results are the same when performing the same operation in
extended precision and storing the results in single- or double-precision format.
MOTOROLA
NOTE: EXP3 is generated only during an FMOVE OUT if the source is too large to be represented
Data Type
+ In-Range
–In-Range
Table 6-6. Extended-Precision Real Format Summary (Continued)
+ Zero
–Zero
Infinity
SNAN
NAN
with a three-digit exponent. Otherwise, it is a don’t care.
Maximum Positive Normalized
Minimum Positive Normalized
Minimum Positive Denormalized
SM SE Y Y
95
63
31
Table 6-7. Packed Decimal Real Format Summary
FRAC15
FRAC7
SM
0/1
0/1
0/1
0
1
0
1
0/1
0/1
0/1
0/1
SE
FRAC14
FRAC6
1
1
1
EXP2
Y
X
X
X
X
1
1
1
FRAC13
FRAC5
EXP1
M68060 USER’S MANUAL
Approximate Ranges
Y
X
X
X
X
1
1
1
FRAC12
FRAC4
EXP0
$000–$999
$000–$999
$000–$999
$000–$999
Exponent
3-Digit
$FFF
$FFF
$FFF
FRAC3
FRAC11
(EXP3)
FRAC2
X X X X
FRAC10
$XXX0–$XXX9
$XXX0–$XXX9
Integer
$XXXX
$XXXX
$XXXX
1-Digit
$XXX0
$XXX0
1.7
1.7
1.2
X X X X
FRAC9
FRAC1
10 –4932
10 –4951
10 4932
INTEGER
FRAC8
FRAC0
$00…01–$99…99
$00…01–$99…99
16-Digit Fraction
64
32
0
$00…00
Nonzero
Nonzero
$00…00
$00…00
Floating-Point Unit
6-11