7-34
FLOATING-POINT UNIT
Like the CMOVcc instructions, the FCMOVcc instructions are useful for optimizing small IF
constructions. They also help eliminate branching overhead for IF operations and the possibility
of branch mispredictions by the processor.
NOTE
The FCMOVcc instructions may not be supported on some processors in the
Pentium
®
Pro processor family. Software can check if the FCMOVcc instruc-
tions are supported by checking the processors feature information with the
CPUID instruction (refer to CPUIDCPU Identification in Chapter 3,
Instruction Set Reference, of the Intel Architecture Software Developers
Manual, Volume 2).
7.5.4.Load Constant Instructions
The following instructions push commonly used constants onto the top [ST(0)] of the FPU
register stack:
FLDZ
Load +0.0
FLD1
Load +1.0
FLDPI
Load
?
FLDL2T
Load log
2
10
FLDL2E
Load log
2
e
FLDLG2
Load log
10
2
FLDLN2
Load log
e
2
The constant values have full extended-real precision (64 bits) and are accurate to approximately
19 decimal digits. They are stored internally in a format more precise than extended real. When
loading the constant, the FPU rounds the more precise internal constant according to the RC
(rounding control) field of the FPU control word. Refer to Section 7.5.8., Pi, for information
on the
?
constant.
