Summary - Analog Devices adsp-2100 Manual

2 Computational Units
2.1.8
Table 2.1 summarizes some of the arithmetic characteristics of ADSP-2100
family operations. In addition to the numeric types described in this
section, the ADSP-2100 Family C Compiler supports a form of 32-bit
floating-point in which one 16-bit word is the exponent and the other
word is the mantissa. See the ADSP-2100 Family C Tools Manual.
O
PERATION
ALU
Addition
Subtraction
Logical Operations
Division
ALU Overflow
ALU Carry Bit
ALU Saturation
MAC, Fractional
Multiplication (P)
Multiplication (MR)
Mult / Add
Mult / Subtract
MAC Saturation
MAC, Integer Mode
Multiplication (P)
Multiplication (MR)
Mult / Add
Mult / Subtract
MAC Saturation
Shifter
Logical Shift
Arithmetic Shift
Exponent Detection
Table 2.1 Arithmetic Formats
2 – 4

Summary

Operands
Signed or unsigned
Signed or unsigned
Binary string
Explicitly signed/unsigned
Signed
16-bit unsigned
Signed
1.15 Explicitly signed/unsigned
1.15 Explicitly signed/unsigned
1.15 Explicitly signed/unsigned
1.15 Explicitly signed/unsigned
Signed
1.15 Explicitly signed/unsigned
16.0 Explicitly signed/unsigned
16.0 Explicitly signed/unsigned
16.0 Explicitly signed/unsigned
Signed
Unsigned / binary string
Signed
Signed
A F
RITHMETIC ORMATS
Result
Interpret flags
Interpret flags
same as operands
same as operands
same as operands
same as operands
same as operands
32 bits (2.30)
2.30 shifted to 1.31
2.30 shifted to 1.31
2.30 shifted to 1.31
same as operands
32 bits (2.30)
32.0 no shift
32.0 no shift
32.0 no shift
same as operands
same as operands
same as operands
same as operands