Memory To Floating-Point Register Data Translation - Double Precision - Intel ITANIUM ARCHITECTURE - SOFTWARE DEVELOPERS MANUAL VOLUME 1 REV 2.3 Manual

Figure 5-5. Memory to Floating-point Register Data Translation – Double Precision
sign exponent
FR:
Memory /GR :
Double-precision Load
sign exponent
FR:
0x1FFFF
1111111 1
/GR
Memory :
Double-precision Load
sign exponent
FR:
0
0000000 0
/GR
Memory :
Double-precision Load
sign exponent
FR: 0x0FC01
0000000 0
Memory /GR :
Double-precision Load
Volume 1, Part 1: Floating-point Programming Model
integer
bit
1
/setf.d
– normal numbers
integer
bit
1
111
/setf.d
– infinities and NaNs
integer
bit
0
000 0 0
/setf.d – zeros
integer
bit
0
000
/setf.d
– denormal numbers
significand
significand
significand
0
0 0 0
significand
0
0
0 0
0
1:93