Operand Data Formats and Types
MCF548x Reference Manual, Rev. 3
Freescale Semiconductor 6-3

6.2 Operand Data Formats and Types

The FPU supports signed byte, word, and longword integer formats, which are identical to those supported
by the integer unit. The FPU also supports single- and double-precision binary floating-point formats that
fully comply with the IEEE-754 standard.

6.2.1 Signed-Integer Data Formats

The FPU supports 8-bit byte (B), 16-bit word (W), and 32-bit longword (L) integer data formats.

6.2.2 Floating-Point Data Formats

Figure 6-1 shows the two binary floating-point data formats.
Figure 6-1. Floating-Point Data Formats
Note that, throughout this chapter, a mantissa is defined as the concatenation of an integer bit, the binary
point, and a fraction. A fraction is the term designating the bits to the right of the binary point in the
mantissa.
Figure 6-2. Mantissa
The integer bit is implied to be set for normalized numbers and infinities, clear for zeros and denormalized
numbers. For not-a-numbers (NANs), the integer bit is ignored. The exponent in both floating-point
formats is an unsigned binary integer with an implied bias added to it. Subtracting the bias from exponent
Table 6-2. Floating-Point Addressing Modes
Addressing Modes Syntax
Register direct
Address register direct
Address register direct
Dy
Ay
Register indirect
Address register indirect
Address register indirect with postincrement
Address register indirect with predecrement
Address register indirect with displacement
(Ay)
–(Ay)
(d16,Ay)
Program counter indirect with displacement (d16,PC)
11-Bit Exponent
S52-Bit Fraction
62 51 0
Sign of Mantissa
0
23-Bit Fraction8-Bit Exponent
S
Sign of Mantissa
2230
Single
Double
31
63
(integer bit).(fraction)
Mantissa