
3-24
G2 PowerPC Core Reference Manual
For More Information On This Product,
Go to: www.freescale.com
MOTOROLA
Instruction Set Summary
When a string operation crosses a 4-Kbyte boundary, the instruction may be interrupted by
a DSI exception associated with the address translation of the second page. In this case, the
core performs some or all memory references from the first page and none from the second
before taking the exception. On return from the DSI exception, the load or store string
instruction will re-execute from the beginning. For more information, refer to “DSI
Exception (0x00300)” in Chapter 6, “Exceptions,” in the
Programming Environments
Manual
.
Implementation Note
—If
r
A is in the range of registers to be loaded for a Load String
Word Immediate (
lswi
) instruction or if either
r
A or
r
B is in the range of registers to be
loaded for a Load String Word Indexed (
lswx
) instruction, the PowerPC architecture
defines the instruction to be of an invalid form. In addition, the
lswx
and
stswx
instructions
that specify a string length of zero are defined to be invalid by the PowerPC architecture.
However, none of these cases hold true for the G2 core—the core treats these cases as valid
forms.
3.2.4.3.8
Floating-Point Load and Store Address Generation
Floating-point load and store operations generate effective addresses using the register
indirect with immediate index addressing mode and register indirect with index addressing
mode (details are described below). Floating-point loads and stores are not supported for
direct-store accesses. The use of the floating-point load and store operations for direct-store
accesses results in a DSI exception.
3.2.4.3.9
Floating-Point Load Instructions
Separate floating-point load instructions are used for single-precision and double-precision
operands. Because FPRs support only double-precision format, the FPU converts
single-precision data to double-precision format before loading the operands into the target
FPR. This conversion is described fully in “Floating-Point Load Instructions” in
Appendix D, “Floating-Point Models,” in the
Programming Environments Manual
.
Implementation Note
—The PowerPC architecture defines load with update instructions
with
r
A = 0 as an invalid form; however, the core treats this case as a valid form.
Table 3-19 provides a list of the floating-point load instructions.
Table 3-19. Floating-Point Load Instructions
Name
Mnemonic
Operand Syntax
Load Floating-Point Double
lfd
fr
D
,
d(
r
A)
Load Floating-Point Double Indexed
lfdx
fr
D
,r
A
,r
B
Load Floating-Point Double with Update
lfdu
fr
D
,
d(
r
A)
Load Floating-Point Double with Update
Indexed
lfdux
fr
D
,r
A
,r
B
F
Freescale Semiconductor, Inc.
n
.