Stereo System User Manual
6 - 2 DSP96002 USER’S MANUAL MOTOROLA
tion cycle in the IEEE mode if denormalized numbers are not detected, otherwise additional instruction cy-
cles will be required. See Figure 6-1 for a list of the thirty eight floating point arithmetic instructions.
Figure 6-1. Floating-Point Arithmetic Instructions
FABS.S Absolute Value (Single Precision)
FABS.X Absolute Value (Single Extended Precision)
FADD.S Add (Single Precision)
FADD.X Add (Single Extended Precision)
FADDSUB.S Add and Subtract (Single Precision)
FADDSUB.X Add and Subtract (Single Extended Precision)
FCLR Clear a Floating-Point Operand
FCMP Compare
FCMPG Graphics Compare with Trivial Accept/Reject Flags
FCMPM Compare Magnitude
FCOPYS.S Copy Sign (Single Precision)
FCOPYS.X Copy Sign (Single Extended Precision)
FGETMAN Get Mantissa
FINT Convert to Floating-Point Integer
FLOAT.S Integer to SP Floating-Point Conversion
FLOAT.X Integer to SEP Floating-Point Conversion
FLOATU.S Unsigned Integer to SP Floating-Point Conversion
FLOATU.X Unsigned Integer to SEPFloating-Point Conversion
FLOOR Convert to Floating-Point Integer Round to -Infinity
FMPY FADD.S Multiply and Add (Single Precision)
FMPY FADD.X Multiply and Add (Single Extended Precision)
FMPY FADDSUB.S Multiply, Add and Subtract (Single Precision)
FMPY FADDSUB.X Multiply, Add and Subtract (Single Extended Precision)
FMPY FSUB.S Multiply and Subtract (Single Precision)
FMPY FSUB.X Multiply and Subtract (Single Extended Precision)
FMPY.S Multiply (Single Precision)
FMPY.X Multiply (Single Extended Precision)
FNEG.S Change Sign (Single Precision)
FNEG.X Change Sign (Single Extended Precision)
FSCALE.S Scale a Floating-Point Operand (Single Precision)
FSCALE.X Scale a Floating-Point Operand (Single Extended Precision)
FSEEDD Reciprocal Approximation
FSEEDR Square Root Reciprocal Approximation
FSUB.S Subtract (Single Precision)
FSUB.X Subtract (Single Extended Precision)
FTFR.S Transfer Floating-Point Register (Single Precision)
FTFR.X Transfer Floating-Point Register (Single Extended Precision)
FTST Test a Floating-Point Operand