1-12
ColdFire CF4e Core User’s Manual
For More Information On This Product,
Go to: www.freescale.com
Addressing Modes
1.7.2.1.1 Signed-Integer Data Formats
The FPU supports 8-bit byte (B), 16-bit word (W), and 32-bit longword (L) integer data
formats.
1.7.2.1.2 Floating-Point Data Formats
Figure 1-8 shows the two binary floating-point data formats.
Figure 1-8. 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 1-9. 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 yields a signed, two’s complement power
of two. This represents the magnitude of a normalized floating-point number when
multiplied by the mantissa.
By definition, a normalized mantissa always takes values starting from 1.0 and going up to,
but not including, 2.0; that is, [1.0...2.0).
1.8 Addressing Modes
Addressing modes are categorized by how they are used. Data addressing modes refer to
data operands. Memory addressing modes refer to memory operands. Alterable addressing
modes refer to alterable (writable) data operands. Control addressing modes refer to
memory operands without an associated size.
These categories sometimes combine to form more restrictive categories. Two combined
classifications are alterable memory (both alterable and memory) and data alterable (both
11-Bit Exponent
S
52-Bit Fraction
62
51
0
Sign of Mantissa
0
23-Bit Fraction
8-Bit Exponent
S
Sign of Mantissa
22
30
Single
Double
31
63
(integer bit).(fraction)
Mantissa
F
Freescale Semiconductor, Inc.
n
.