Integer or Fractional Data Formats
Signed Integer
Bit
Weight
- (2
Sign Bit
Unsigned Integer
Bit
Weight
Sign Bit
Figure D-1. Integer Format
In a fractional format, the assumed radix point lies within the number, so
that some or all of the magnitude bits have a weight of less than 1. In the
format shown in
three LSBs, and the bits have the weights indicated.
The native formats for the Blackfin processor family are a signed fractional
1.M format and an unsigned fractional 0.N format, where N is the num-
ber of bits in the data word and M = N – 1.
The notation used to describe a format consists of two numbers separated
by a period (.); the first number is the number of bits to the left of the
radix point, the second is the number of bits to the right of the radix
point. For example, 16.0 format is an integer format; all bits lie to the left
of the radix point. The format in
D-2
ADSP-BF53x/BF56x Blackfin Processor Programming Reference
15
13
14
15
14
13
)
2
2
15
13
14
15
14
13
2
2
2
Figure
D-2, the assumed radix point lies to the left of the
2
1
2
2
2
. . .
1
2
2
2
2
. . .
Figure D-2
is 13.3.
0
1
0
2
Radix Point
0
1
0
2
Radix Point
Need help?
Do you have a question about the ADSP-BF53x Blackfin and is the answer not in the manual?