Motorola DSP96002 - Manual (Page 760)

D-8 DSP96002 USER’S MANUAL MOTOROLA
register file consisting of 10 96-bit registers for storage of floating-point numbers is available for
that purpose. An automatic conversion unit converts the floating point storage format in memory
to the internal DP format when moving operands and/or results from/to memory.
2. Multiply unit: A full IEEE floating-point multiply unit, delivering either a SP or SEP result in one
instruction cycle.
3. Adder/Subtracter unit: A full IEEE floating-point adder/subtracter unit, which can deliver the
sum as well as the difference of two operands in the same instruction cycle, to either SP or SEP.
4. Special function unit: A special function unit provides various logic functions, as well as support
for divide and square root in terms of an initial seed for a fast convergent divide and square root
algorithm.
5. Controller and arbitrator: A controller/arbitrator supplies all of the control signals necessary for
the operation of the data ALU.
The data ALU uses the SEP format for all of its operations: the results are automatically rounded to either
SP or SEP. All of the rounding modes specified by the IEEE standard are supported. These rounding modes
are:
Figure D-5. DP Format in the Data ALU
95 94 93 92 75 74 64 63 62 32 31 11 10 0
S U V O E 0 Fraction (MSBs) Fraction (LSBs) i
Dn.h Dn.m Dn.l
S : sign
U : single precision unnormalized tag
V : double precision unnormalized
i : explicit integer
Tiny SP Numbers between
±
2
Emin
-1.0
Ч
2
-126
0 +1.0
Ч
2
-126
Figure D-6. Tiny Numbers
Figure D-7. SEP Format in the Data ALU
95 94 93 92 75 74 64 63 62 32 31 11 10 0
S U V O E 0 Fraction 0 i
Dn.h Dn.m Dn.l