
3-16
G2 PowerPC Core Reference Manual
For More Information On This Product,
Go to: www.freescale.com
MOTOROLA
Instruction Set Summary
The generated zero has the same sign as the denormalized number. The core performs
single- and double-precision floating-point operations compliant with the IEEE 754
floating-point standard.
Implementation Note
—Single-precision denormalized results require two additional
processor clock cycles to round. When loading or storing a single-precision denormalized
number, the load/store unit may take up to 24 processor clock cycles to convert between the
internal double-precision format and the external single-precision format.
3.2.4.2.1
Floating-Point Arithmetic Instructions
The floating-point arithmetic instructions are listed in Table 3-8.
3.2.4.2.2
Floating-Point Multiply-Add Instructions
These instructions combine multiply and add operations without an intermediate rounding
operation. The fractional part of the intermediate product is 106 bits wide, and all 106 bits
take part in the add/subtract portion of the instruction.
The floating-point multiply-add instructions are listed in Table 3-9.
Table 3-8. Floating-Point Arithmetic Instructions
Name
Mnemonic
Operand Syntax
Floating Add (Double-Precision)
fadd
(
fadd.
)
fr
D
,fr
A
,fr
B
Floating Add Single
fadds
(
fadds.
)
fr
D
,fr
A
,fr
B
Floating Divide (Double-Precision)
fdiv
(
fdiv.
)
fr
D
,fr
A
,fr
B
Floating Divide Single
fdivs
(
fdivs.
)
fr
D
,fr
A
,fr
B
Floating Multiply
(Double-Precision)
fmul
(
fmul.
)
fr
D
,fr
A
,fr
C
Floating Multiply
Single
fmuls
(
fmuls.
)
fr
D
,fr
A
,fr
C
Floating Reciprocal Estimate Single
fres
(
fres.
)
fr
D
,fr
B
Floating Reciprocal Square Root Estimate
frsqrte
(
frsqrte.
)
fr
D
,fr
B
Floating Select
fsel
(
fsel.
)
fr
D
,fr
A
,fr
C
,fr
B
Floating Subtract (Double-Precision)
fsub
(
fsub.
)
fr
D
,fr
A
,fr
B
Floating Subtract Single
fsubs
(
fsubs.
)
fr
D
,fr
A
,fr
B
Table 3-9. Floating-Point Multiply-Add Instructions
Name
Mnemonic
Operand Syntax
Floating Multiply-Add (Double-Precision)
fmadd
(
fmadd.
)
fr
D
,fr
A
,fr
C
,fr
B
Floating Multiply-Add Single
fmadds
(
fmadds.
)
fr
D
,fr
A
,fr
C
,fr
B
Floating Multiply-Subtract (Double-Precision)
fmsub
(
fmsub.
)
fr
D
,fr
A
,fr
C
,fr
B
Floating Multiply-Subtract Single
fmsubs
(
fmsubs.
)
fr
D
,fr
A
,fr
C
,fr
B
F
Freescale Semiconductor, Inc.
n
.