Chapter 2. Programming Model
2-55
Instruction Set Summary
Implementation Notes
The MPC7400 treats exceptions as follows:
¥
The FPU can be run in two different modesIgnore exceptions mode (MSR[FE0] =
MSR[FE1] = 0) and precise mode (any other settings for MSR[FE0,FE1]). For the
MPC7400, ignore exceptions mode allows oating-point instructions to complete
earlier and thus can provide better performance than precise mode.
The oating-point load and store indexed instructions (
lfsx
,
lfsux
,
lfdx
,
lfdux
,
stfsx
,
stfsux
,
stfdx
,
stfdux
) are invalid when the Rc bit is one. In the MPC7400, executing
one of these invalid instruction forms causes CR0 to be set to an undeTned value.
¥
The PowerPC architecture deTnes a load with update instruction with
r
A = 0 as an invalid
form. Table 2-35 summarizes the oating-point load instructions.
2.3.4.3.10 Floating-Point Store Instructions
This section describes oating-point store instructions. There are three basic forms of the
store instructionsingle-precision, double-precision, and integer. The integer form is
supported by the optional
stTwx
instruction. Because the FPRs support only oating-point,
double-precision format for oating-point data, single-precision oating-point store
instructions convert double-precision data to single-precision format before storing the
operands. Table 2-36 summarizes the oating-point store instructions.
Table 2-35. Floating-Point Load Instructions
Name
Mnemonic
Syntax
Load Floating-Point Single
lfs
fr
D
,d(r
A
)
Load Floating-Point Single Indexed
lfsx
fr
D
,r
A
,r
B
Load Floating-Point Single with Update
lfsu
fr
D
,d(r
A
)
Load Floating-Point Single with Update Indexed
lfsux
fr
D
,r
A
,r
B
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
Table 2-36. Floating-Point Store Instructions
Name
Mnemonic
Syntax
Store Floating-Point Single
stfs
fr
S
,d(r
A
)
Store Floating-Point Single Indexed
stfsx
fr
S
,r
B
Store Floating-Point Single with Update
stfsu
fr
S
,d(
rA
)
Store Floating-Point Single with Update Indexed
stfsux
fr
S
,r
B
Store Floating-Point Double
stfd
fr
S
,d(r
A
)
Store Floating-Point Double Indexed
stfdx
fr
S
,r
B
Store Floating-Point Double with Update
fr
S
,d(
rA
)