Motorola DSP96002 User Manual page 767

32-bit digital signal processor
Table of Contents

Advertisement

lowing the above operation, the Data ALU register will be read first by a single precision and then by a dou-
ble precision floating-point move.
- 32-bit data from source is $00200000 (= +2**(-128))
- exp
- mantissa = $200000 (the hidden bit is zero)
- data stored in the register
- e
- I
- U-TAG = 1
- fraction = 40000000
- mantissa = 0.010...00
In this last case, the U-TAG tells us that an operation using this operand will first add extra cycles to nor-
malize it. However, an SP move will render the correct result since the "formatting" scheme presented in
Section 5.5 chooses the right bits. One should notice that a double precision floating-point move that reads
MOTOROLA
= $00
(8 bit bias)
= 380
(incorrect representation with 11-bit bias; the
correct representation would be 37F)
= 0
(the number is unnormalized)
(set; the number cannot be used in computations
without adding extra cycles for normalization,
since it is unnormalized)
DSP96002 USER'S MANUAL
D-15

Advertisement

Table of Contents
loading

Table of Contents