Using Multiplier Integer And Fractional Formats - Analog Devices ADSP-BF53x Blackfin Reference

Table 2-5. Multiplier Arithmetic Integer Modes Formats (Cont'd)
Operation
Multiplication/Addition
Multiplication/Subtraction
Table 2-6. Shifter Arithmetic Formats
Operation
Logical Shift
Arithmetic Shift
Exponent Detect

Using Multiplier Integer and Fractional Formats

For multiply-and-accumulate functions, the processor provides two
choices—fractional arithmetic for fractional numbers (1.15) and integer
arithmetic for integers (16.0).
For fractional arithmetic, the 32-bit product output is format adjusted—
sign-extended and shifted one bit to the left—before being added to accu-
mulator or
A0
of (which is bit 0 of
A0
of (which is bit 1 of
A0
filled. The fractional multiplier result format appears in
For integer arithmetic, the 32-bit product register is not shifted before
being added to
placement.
ADSP-BF53x/BF56x Blackfin Processor Programming Reference
Operand Formats
16.0 explicitly signed or
unsigned
16.0 explicitly signed or
unsigned
Operand Formats
Unsigned binary string
Signed
Signed
. For example, bit 31 of the product lines up with bit 32
A1
), and bit 0 of the product lines up with bit 1
A0.X
). The Least Significant Bit (LSB) is zero
A0.W
or . Figure 2-6
A0 A1
Computational Units
Result Formats
32.0 not shifted
32.0 not shifted
Result Formats
Same as operands
Same as operands
Same as operands
shows the integer mode result
Figure 2-5.
2-17