Scalar Golden Reference - 2023.2 English

The following provides example code for the scalar version of a 32-tap filter:

static cint16 eq_coef[32]={{1,2},{3,4},...};

//keep margin data between different invocations of the graph 
static cint16 delay_line[32];

__attribute__((noinline)) void fir_32tap_scalar(input_stream<cint16> * sig_in,
      output_stream<cint16> * sig_out){
  //For profiling only 
  unsigned cycle_num[2];
  aie::tile tile=aie::tile::current();
  
  for(int i=0;i<SAMPLES;i++){
    cycle_num[0]=tile.cycles();//cycle counter of the AI Engine tile
    cint64 sum={0,0};//larger data to mimic accumulator
    for(int j=0;j<32;j++){
      //auto integer promotion to prevent overflow
      sum.real+=delay_line[j].real*eq_coef[j].real-delay_line[j].imag*eq_coef[j].imag;
      sum.imag+=delay_line[j].real*eq_coef[j].imag+delay_line[j].imag*eq_coef[j].real;
    }
    sum=sum>>SHIFT;
    //produce one sample per loop iteration
    writeincr(sig_out,{(int16)sum.real,(int16)sum.imag});

    for(int j=0;j<32;j++){
      if(j==31){
        delay_line[j]=readincr(sig_in);
      }else{
        delay_line[j]=delay_line[j+1];
      }
    }
    //For profiling only 
    cycle_num[1]=tile.cycles();//cycle counter of the AI Engine tile
    printf("start=%d,end=%d,total=%d\n",cycle_num[0],cycle_num[1],cycle_num[1]-cycle_num[0]);
  }
  
}
void fir_32tap_scalar_init()
{
  //initialize data
  for (int i=0;i<32;i++){
    int tmp=get_ss(0);
    delay_line[i]=*(cint16*)&tmp;
  }
};

From the profiling result, you can see that each sample takes 3068 cycles. You can also view similar information under the Profile section in the Vitis IDE if you enable the option --profile during AI Engine simulation.