Table 2-6. Floating-Point Result Data-Type Behavior - IBM PowerPC 750GX User Manual

Table 2-5. Floating-Point Operand Data-Type Behavior
Operand A
Data Type
Don't care
Don't care
Single normalized
Single infinity
Single zero
Double normalized
Double infinity
Double zero
1. Prioritize according to Chapter 3, "Operand Conventions," in the PowerPC Microprocessor Family: The Programming Environ-
ments Manual.
Table 2-6 summarizes the mode behavior for results.

Table 2-6. Floating-Point Result Data-Type Behavior

Precision Data Type
Single Denormalized
Normalized, infinity,
Single
zero
Single QNaN, SNaN
Single Integer
Double Denormalized
Normalized, infinity,
Double
zero
Double QNaN, SNaN
Double INT
gx_02.fm.(1.2)
March 27, 2006
Operand B
Data Type
Single QNaN
Single SNaN
Double QNaN
Double SNaN
Don't care
Single normalized Single normalized
Single infinity
Single zero
Double normalized Double normalized
Double infinity
Double zero
IEEE Mode (NI = 0)
Return single-precision denormalized number with trail-
ing zeros.
Return the result.
Return QNaN.
Place integer into low word of FPR.
Return double-precision denormalized number.
Return the result.
Return QNaN.
Not supported by the 750GX
IBM PowerPC 750GX and 750GL RISC Microprocessor
(Page 2 of 2)
Operand C IEEE Mode
Data Type
Don't care
Single QNaN
Single SNaN
Double QNaN
Double SNaN
Single infinity
Single zero
Do the operation
Double infinity
Double zero
User's Manual
Non-IEEE Mode
(NI = 0) (NI = 1)
1
QNaN QNaN
1
QNaN QNaN
Do the operation
Non-IEEE Mode (NI = 1)
Return zero.
Return the result.
Return QNaN.
If (Invalid Operation)
then
Place (0x8000) into FPR[32–63]
else
Place integer into FPR[32–63].
Return zero.
Return the result.
Return QNaN.
Not supported by the 750GX
Programming Model
Page 85 of 377
1
1