x86 Assembly Language Reference Manual

Floating-Point Instructions

The floating point instructions operate on floating-point, integer, and binary coded decimal (BCD) operands.

Data Transfer Instructions (Floating Point)

The data transfer instructions move floating-point, integer, and BCD values between memory and the floating point registers.

Table 3–13 Data Transfer Instructions (Floating-Point)


Solaris Mnemonic	Intel/AMD Mnemonic	Description
`fbld`	`FBLD`	load BCD
`fbstp`	`FBSTP`	store BCD and pop
`fcmovb`	`FCMOVB`	floating-point conditional move if below
`fcmovbe`	`FCMOVBE`	floating-point conditional move if below or equal
`fcmove`	`FCMOVE`	floating-point conditional move if equal
`fcmovnb`	`FCMOVNB`	floating-point conditional move if not below
`fcmovnbe`	`FCMOVNBE`	floating-point conditional move if not below or equal
`fcmovne`	`FCMOVNE`	floating-point conditional move if not equal
`fcmovnu`	`FCMOVNU`	floating-point conditional move if unordered
`fcmovu`	`FCMOVU`	floating-point conditional move if unordered
`fild`	`FILD`	load integer
`fist`	`FIST`	store integer
`fistp`	`FISTP`	store integer and pop
`fld`	`FLD`	load floating-point value
`fst`	`FST`	store floating-point value
`fstp`	`FSTP`	store floating-point value and pop
`fxch`	`FXCH`	exchange registers

The basic arithmetic instructions perform basic arithmetic operations on floating-point and integer operands.

Table 3–14 Basic Arithmetic Instructions (Floating-Point)


Solaris Mnemonic	Intel/AMD Mnemonic	Description
`fabs`	`FABS`	absolute value
`fadd`	`FADD`	add floating-point
`faddp`	`FADDP`	add floating-point and pop
`fchs`	`FCHS`	change sign
`fdiv`	`FDIV`	divide floating-point
`fdivp`	`FDIVP`	divide floating-point and pop
`fdivr`	`FDIVR`	divide floating-point reverse
`fdivrp`	`FDIVRP`	divide floating-point reverse and pop
`fiadd`	`FIADD`	add integer
`fidiv`	`FIDIV`	divide integer
`fidivr`	`FIDIVR`	divide integer reverse
`fimul`	`FIMUL`	multiply integer
`fisub`	`FISUB`	subtract integer
`fisubr`	`FISUBR`	subtract integer reverse
`fmul`	`FMUL`	multiply floating-point
`fmulp`	`FMULP`	multiply floating-point and pop
`fprem`	`FPREM`	partial remainder
`fprem1`	`FPREM1`	IEEE partial remainder
`frndint`	`FRNDINT`	round to integer
`fscale`	`FSCALE`	scale by power of two
`fsqrt`	`FSQRT`	square root
`fsub`	`FSUB`	subtract floating-point
`fsubp`	`FSUBP`	subtract floating-point and pop
`fsubr`	`FSUBR`	subtract floating-point reverse
`fsubrp`	`FSUBRP`	subtract floating-point reverse and pop
`fxtract`	`FXTRACT`	extract exponent and significand

The floating-point comparison instructions operate on floating-point or integer operands.

Table 3–15 Comparison Instructions (Floating-Point)


Solaris Mnemonic	Intel/AMD Mnemonic	Description
`fcom`	`FCOM`	compare floating-point
`fcomi`	`FCOMI`	compare floating-point and set `%eflags`
`fcomip`	`FCOMIP`	compare floating-point, set `%eflags`, and pop
`fcomp`	`FCOMP`	compare floating-point and pop
`fcompp`	`FCOMPP`	compare floating-point and pop twice
`ficom`	`FICOM`	compare integer
`ficomp`	`FICOMP`	compare integer and pop
`ftst`	`FTST`	test floating-point (compare with 0.0)
`fucom`	`FUCOM`	unordered compare floating-point
`fucomi`	`FUCOMI`	unordered compare floating-point and set `%eflags`
`fucomip`	`FUCOMIP`	unordered compare floating-point, set `%eflags`, and pop
`fucomp`	`FUCOMP`	unordered compare floating-point and pop
`fucompp`	`FUCOMPP`	compare floating-point and pop twice
`fxam`	`FXAM`	examine floating-point

The transcendental instructions perform trigonometric and logarithmic operations on floating-point operands.

Table 3–16 Transcendental Instructions (Floating-Point)


Solaris Mnemonic	Intel/AMD Mnemonic	Description
`f2xm1`	`F2XM1`	computes 2^x-1
`fcos`	`FCOS`	cosine
`fpatan`	`FPATAN`	partial arctangent
`fptan`	`FPTAN`	partial tangent
`fsin`	`FSIN`	sine
`fsincos`	`FSINCOS`	sine and cosine
`fyl2x`	`FYL2X`	computes y * log₂x
`fyl2xp1`	`FYL2XP1`	computes y * log₂(x+1)

The load constants instructions load common constants, such as π, into the floating-point registers.

Table 3–17 Load Constants Instructions (Floating-Point)


Solaris Mnemonic	Intel/AMD Mnemonic	Description
`fld1`	`FLD1`	load +1.0
`fldl2e`	`FLDL2E`	load log₂e
`fldl2t`	`FLDL2T`	load log₂10
`fldlg2`	`FLDLG2`	load log₁₀2
`fldln2`	`FLDLN2`	load log_e2
`fldpi`	`FLDPI`	load π
`fldz`	`FLDZ`	load +0.0

The floating-point control instructions operate on the floating-point register stack and save and restore the floating-point state.

Table 3–18 Control Instructions (Floating-Point)


Solaris Mnemonic	Intel/AMD Mnemonic	Description
`fclex`	`FCLEX`	clear floating-point exception flags after checking for error conditions
`fdecstp`	`FDECSTP`	decrement floating-point register stack pointer
`ffree`	`FFREE`	free floating-point register
`fincstp`	`FINCSTP`	increment floating-point register stack pointer
`finit`	`FINIT`	initialize floating-point unit after checking error conditions
`fldcw`	`FLDCW`	load floating-point unit control word
`fldenv`	`FLDENV`	load floating-point unit environment
`fnclex`	`FNCLEX`	clear floating-point exception flags without checking for error conditions
`fninit`	`FNINIT`	initialize floating-point unit without checking error conditions
`fnop`	`FNOP`	floating-point no operation
`fnsave`	`FNSAVE`	save floating-point unit state without checking error conditions
`fnstcw`	`FNSTCW`	store floating-point unit control word without checking error conditions
`fnstenv`	`FNSTENV`	store floating-point unit environment without checking error conditions
`fnstsw`	`FNSTSW`	store floating-point unit status word without checking error conditions
`frstor`	`FRSTOR`	restore floating-point unit state
`fsave`	`FSAVE`	save floating-point unit state after checking error conditions
`fstcw`	`FSTCW`	store floating-point unit control word after checking error conditions
`fstenv`	`FSTENV`	store floating-point unit environment after checking error conditions
`fstsw`	`FSTSW`	store floating-point unit status word after checking error conditions
`fwait`	`FWAIT`	wait for floating-point unit
`wait`	`WAIT`	wait for floating-point unit