
TM1300 Data Book
Philips Semiconductors
A-178
PRODUCT SPECIFICATION
Convert unsigned integer to oating-point
SYNTAX
[ IF r
guard ] ufloat rsrc1
→ rdest
FUNCTION
if r
guard then {
r
dest
← (oat) ((unsigned long)rsrc1)
}
ATTRIBUTES
Function unit
falu
Operation code
127
Number of operands
1
Modier
No
Modier range
—
Latency
3
Issue slots
1, 4
DESCRIPTION
The ufloat operation converts the unsigned integer value in r
src1 to single-precision IEEE oating-point format
and writes the result into r
dest. Rounding is according to the IEEE rounding mode bits in PCSW. If ufloat causes an
IEEE exception, such as inexact, the corresponding exception ags in the PCSW are set. The PCSW exception ags
are sticky: the ags can be set as a side-effect of any oating-point operation but can only be reset by an explicit
writepcsw
operation. The update of the PCSW exception ags occurs at the same time as r
dest is written. If any
other oating-point compute operations update the PCSW at the same time, the net result in each exception ag is the
logical OR of all simultaneous updates ORed with the existing PCSW value for that exception ag.
The ufloatflags operation computes the exception ags that would result from an individual ufloat.
The ufloat operation optionally takes a guard, specied in r
guard. If a guard is present, its LSB controls the
modication of the destination register. If the LSB of r
guard is 1, rdest and the exception ags in PCSW are written;
otherwise, r
dest is not changed and the operation does not affect the exception ags in PCSW.
EXAMPLES
Initial Values
Operation
Result
r30 = 3
ufloat r30
→ r100
r100
← 0x40400000 (3.0)
r40 = 0xffffffff (4294967295)
ufloat r40
→ r105
r105
← 0x4f800000 (4.294967296e+9), INX ag set
r10 = 0, r50 = 0xfffffffd
IF r10 ufloat r50
→ r110
no change, since guard is false
r20 = 1, r50 = 0xfffffffd
IF r20 ufloat r50
→ r115
r115
← 0x4f800000 (4.294967296e+9), INX ag set
r60 = 0x7fffffff (2147483647)
ufloat r60
→ r117
r117
← 0x4f000000 (2.147483648e+9), INX ag set
r70 = 0x80000000 (2147483648)
ufloat r70
→ r120
r120
← 0x4f000000 (2.147483648e+9)
r80 = 0x7ffffff1 (2147483633)
ufloat r80
→ r122
r122
← 0x4f000000 (2.147483648e+9), INX ag set
SEE ALSO
ifloat ifloatrz ufloatrz
ifixieee ufloatflags
ufloat