Intel i86W Manual page 205

INSTRUCTION SET SUMMARY
pfiadd.w
fsrcl, fsrc2, fdes! ...........................................................
Pipelined Long-Integer Add
fdes!
~
last stage graphics result
last stage graphics result
~
fsrcl
+
fsrc2
pfisub.w
fsrcl, fsrc2, fdes! ...................................................
Pipelined Long-Integer Subtract
fdes!
~
last stage graphics result
last stage graphics result
~
fsrcl - fsrc2
pfix.p
fsrcl, fdes! .........................................
Pipelined Floating-Point to Integer Conversion
fdes!
~
last stage adder result
Advance A pipeline one stage
A pipeline first stage
~
64-bit value with low-order 32 bits
equal to integer part of
fsrcl
rounded
Pipelined Floating-Point Load
pfld.z
isrcl (isrc2) , fdes! ..............................................................................................
(Normal)
pfld.z
isrcl (isrc2)
+
+,
fdes! ...........................................................................
(Autoincrement)
fdes!
~
mem.z (third previous pfld's
(isrcl
+
isrc2))
(where .z is precision of third previous pfld.z)
IF autoincrement
THEN isrc2 ~
isrcl
+
isrc2
FI
pfle.p
fsrcl, fsrc2, fdes! ...................................
Pipelined F-P Less-Than or Equal Compare
(Identical to pfgt.p except that
assembler sets R-bit of instruction.)
fdes!
~
last stage adder result
Co. clear if
fsrcl
:5
fsrc2,
else set
Advance A pipeline one stage
A pipeline first stage is undefined, but no result exception occurs
pfmam.p
fsrcl, fsrc2, fdes! ................................. Pipelined
Floating-Point Add and Multiply
fdes!
~
last stage multiplier result
Advance A and M pipeline one stage
(operands accessed before advancing pipeline)
A pipeline first stage
~
A-opl
+
A-op2
M pipeline first stage
~
M-opl x M-op2
pfmov.r
fsrcl, fdes! ..................................................
Pipelined Floating-Point Reg-Reg Move
Assembler pseudo-operation
pfmov.ss
fsrcl, fdes!
=
pfiadd.ss
fsrcl,
fO,
fdes!
pfmov.dd
fsrcl, fdes!
=
pfiadd.dd
fsrcl,
fO,
fdes!
pfmov.sd
fsrcl, fdes!
=
pfamov.sd
fsrcl, fdes!
pfmov.ds
fsrcl, fdes!
=
pfamov.ds
fsrcl, fdes!
pfmsm.p
fsrcl, fsrc2, fdes! .........................
Pipelined Floating-Point Subtract and Multiply
fdes!
~ last stage multiplier result
Advance A and M pipeline one stage
(operands accessed before advancing pipeline)
A pipeline first stage
~
A-opl - A-op2
M pipeline first stage ~ M-opl x M-op2
A-9