
MPC555
/
MPC556
CENTRAL PROCESSING UNIT
MOTOROLA
USER’S MANUAL
Rev. 15 October 2000
3-38
3.13 PowerPC User Instruction Set Architecture (UISA)
3.13.1 Computation Modes
The core of the MPC555 / MPC556
is a 32-bit implementation of the PowerPC archi-
tecture. Any reference in the PowerPC Architecture Books (UISA, VEA, OEA) regard-
ing 64-bit implementations are not supported by the core. All registers except the
floating-point registers are 32 bits wide.
3.13.2 Reserved Fields
Reserved fields in instructions are described under the specific instruction definition
sections. Unless otherwise stated in the specific instruction description, fields marked
“I
”, “
II”
and “
III”
in the instruction are discarded by the core decoding. Thus, this type
of invalid form instructions yield results of the defined instructions with the appropriate
field zero.
In most cases, the reserved fields in registers are ignored on write and return zeros for
them on read on any control register implemented by the MPC555 / MPC556. Excep-
tion to this rule are bits 16:23 of the fixed-point exception cause register (XER) and the
reserved bits of the machine state register (MSR), which are set by the source value
on write and return the value last set for it on read.
3.13.3 Classes of Instructions
Non-optional instructions are implemented by the hardware. Optional instructions are
executed by implementation-dependent code and any attempt to execute one of these
commands causes the MPC555 / MPC556 to take the implementation-dependent soft-
ware emulation interrupt (offset 0x01000 of the vector table).
Illegal and reserved instruction class instructions are supported by implementation-
dependent code and, thus, the MPC555 / MPC556 hardware generates the implemen-
Table 3-22 Instruction Latency and Blockage
Instruction Type
Precision
Latency
Blockage
Floating-point
multiply-add
Double
Single
7
6
7
6
Floating-point
add or subtract
Double
Single
4
4
4
4
Floating-point multiply
Double
Single
5
4
5
4
Floating-point divide
Double
Single
17
10
17
10
Integer multiply
—
2
1 or 2
1
NOTES:
in the
RCPU Reference
Manual
(RCPURM/AD)
for details.
Integer divide
—
2 to 11
2 to 11
Integer load/store
—
See note
See note
F
re
e
sc
a
le
S
e
m
ic
o
n
d
u
c
to
r,
I
Freescale Semiconductor, Inc.
For More Information On This Product,
Go to: www.freescale.com
n
c
.
..