シングル カーネルを使用したベクター化されたバージョン - 2023.2 日本語

Lane 0: acc[0]=acc[0]+coe[1][0]*buff[8]+coe[1][1]*buff[9]+...+coe[1][7]*buff[15];
Lane 1: acc[1]=acc[1]+coe[1][0]*buff[9]+coe[1][1]*buff[10]+...+coe[1][7]*buff[16];
...
Lane 7: acc[7]=acc[7]+coe[1][0]*buff[15]+coe[1][1]*buff[16]+...+coe[1][7]*buff[22];

//keep margin data between different executions of graph
static aie::vector<cint16,32> delay_line;

alignas(aie::vector_decl_align) static cint16 eq_coef[32]={{1,2},{3,4},...};

__attribute__((noinline)) void fir_32tap_vector(input_stream<cint16> * sig_in, output_stream<cint16> * sig_out){
  const int LSIZE=(SAMPLES/32);
  aie::accum<cacc48,8> acc;
  const aie::vector<cint16,8> coe[4] = {aie::load_v<8>(eq_coef),aie::load_v<8>(eq_coef+8),aie::load_v<8>(eq_coef+16),aie::load_v<8>(eq_coef+24)};
  aie::vector<cint16,32> buff=delay_line;
  for(int i=0;i<LSIZE;i++){
    //1st 8 samples
    acc = aie::sliding_mul<8,8>(coe[0],0,buff,0);
    acc = aie::sliding_mac<8,8>(acc,coe[1],0,buff,8);
    buff.insert(0,readincr_v<4>(sig_in));
    buff.insert(1,readincr_v<4>(sig_in));
    acc = aie::sliding_mac<8,8>(acc,coe[2],0,buff,16);
    acc = aie::sliding_mac<8,8>(acc,coe[3],0,buff,24);
    writeincr(sig_out,acc.to_vector<cint16>(SHIFT));

    //2nd 8 samples
    acc = aie::sliding_mul<8,8>(coe[0],0,buff,8);
    acc = aie::sliding_mac<8,8>(acc,coe[1],0,buff,16);
    buff.insert(2,readincr_v<4>(sig_in));
    buff.insert(3,readincr_v<4>(sig_in));
    acc = aie::sliding_mac<8,8>(acc,coe[2],0,buff,24);
    acc = aie::sliding_mac<8,8>(acc,coe[3],0,buff,0);
    writeincr(sig_out,acc.to_vector<cint16>(SHIFT));

    //3rd 8 samples
    acc = aie::sliding_mul<8,8>(coe[0],0,buff,16);
    acc = aie::sliding_mac<8,8>(acc,coe[1],0,buff,24);
    buff.insert(4,readincr_v<4>(sig_in));
    buff.insert(5,readincr_v<4>(sig_in));
    acc = aie::sliding_mac<8,8>(acc,coe[2],0,buff,0);
    acc = aie::sliding_mac<8,8>(acc,coe[3],0,buff,8);
    writeincr(sig_out,acc.to_vector<cint16>(SHIFT));

    //4th 8 samples
    acc = aie::sliding_mul<8,8>(coe[0],0,buff,24);
    acc = aie::sliding_mac<8,8>(acc,coe[1],0,buff,0);
    buff.insert(6,readincr_v<4>(sig_in));
    buff.insert(7,readincr_v<4>(sig_in));
    acc = aie::sliding_mac<8,8>(acc,coe[2],0,buff,8);
    acc = aie::sliding_mac<8,8>(acc,coe[3],0,buff,16);
    writeincr(sig_out,acc.to_vector<cint16>(SHIFT));
  }
  delay_line=buff;
}
void fir_32tap_vector_init()
{
  //initialize data
  for (int i=0;i<8;i++){
    aie::vector<int16,8> tmp=get_wss(0);
    delay_line.insert(i,tmp.cast_to<cint16>());
  }
};