Motorola DSP Developer's Kit

mean-r.asm

y = mot###_mean(X)

Description

This function returns the mean value of the elements in real vector X

Input/Output

Input: Real vector X

Output: Y (the mean value of the elements in real vector X)

Algorithm

y = 0;
for(i=0; i<size; i++)
{
    y += X[i];
}
y = div (y, size);
* The algorithm of div is :
fractional div ( fractional y, int size)
{
    Bit1 = count leading bits of variable size;
    Bit1 += fractionlenght ;
Normalize (size);
Bit2 = count leading bits of variable y;
Normalize (y);
y = y>>1;
Bit2 ++;
Bit1 -= Bit2;
fractional-div(y, size);//this is a standard algorithm 
y >>= Bit1;
return y;  }

Memory & Register

Input / Output:

X memory IN start address of location of input real vector X.

Register X0 store number of items in the array

Register R7 store bits/word, used by division (24 for 56300,16 for 56600)

Register A1 store Result

Status Register

The assembly function mean-r.asm does not explicitly set any status registers/bits during the function execution.

Data Size Limit

The length of vector X can't be larger than the continuous available data memory size.

Data Range Limit

Input data vector X range [-1.0, +1.0]

Precision

In the case of DSP563, precision is 23 bits.

In the case of DSP566, precision is 15 bits.

Performance Limit

DSP563:

DSP566:

max-2c.asm

mean-c.asm