Intel ITANIUM ARCHITECTURE - SOFTWARE DEVELOPERS MANUAL VOLUME 1 REV 2.3 Manual page 1141

setf
setf — Set Floating-point Value, Exponent, or Significand
( ) setf.s
Format: qp
( ) setf.d
qp
( ) setf.exp
qp
( ) setf.sig
qp
In the single and double forms, GR r
Description:
single_form) or double precision (in the double_form) memory representation,
converted into floating-point register format, and placed in FR
and Figure 5-5 on page
In the exponent_form, bits 16:0 of GR
17 of GR r
(0x800...000).
Figure 2-41.
In the significand_form, the value in GR
The exponent field of FR
sign field of FR
Figure 2-42.
For all forms, if the NaT bit corresponding to
instead of the computed result.
3:242
=
f r
1 2
=
f r
1 2
=
f r
1 2
=
f r
1 2
1:93, respectively.
is copied to the sign bit of FR f
2
Function of setf.exp
63
GR r
1
FR f s exponent
1
is set to the biased exponent for 2.0
f
1
is set to positive (0).
f
1
Function of setf.sig
63
GR r
1
FR f 0 0x1003E
1
is treated as a single precision (in the
2
are copied to the exponent field of FR
r
2
. The significand field of FR f
1
18 17
. . .
1000
is copied to the significand field of FR
r
2
significand
is equal to 1, FR
r
2
single_form M18
double_form M18
exponent_form M18
significand_form M18
, as shown in Figure 5-4
f
1
and bit
f
1
is set to one
1
0
000
.
f
1
63
(0x1003E) and the
0
is set to NaTVal
f
1
Volume 3: Instruction Reference