vec_mpy_08.c

dsp6713开发板的许多例程.对入门特别有用

void vec_mpy(const short *restrict a, const short *restrict b,
             short *restrict c, int len, int shift)
{
    int i;
    unsigned a3_a2, a1_a0;             /* Packed 16-bit values        */
    unsigned b3_b2, b1_b0;             /* Packed 16-bit values        */
    double   c3_c2_dbl, c1_c0_dbl;     /* 32-bit prod in 64-bit pairs */
    int      c3, c2, c1, c0;           /* Separate 32-bit products    */
    unsigned c3_c2, c1_c0;             /* Packed 16-bit values        */

    for (i = 0; i < len; i += 4)
    {
        a3_a2 = _hi(*(const double *) &a[i]);
        a1_a0 = _lo(*(const double *) &a[i]);

        b3_b2 = _hi(*(const double *) &b[i]);
        b1_b0 = _lo(*(const double *) &b[i]);

        /* Multiply elements together, producing four products */
        c3_c2_dbl = _mpy2(a3_a2, b3_b2);
        c1_c0_dbl = _mpy2(a1_a0, b1_b0);

        /* Shift each of the four products right by our shift amount */
        c3 = _hi(c3_c2_dbl) >> shift;
        c2 = _lo(c3_c2_dbl) >> shift;
        c1 = _hi(c1_c0_dbl) >> shift;
        c0 = _lo(c1_c0_dbl) >> shift;

        /* Pack the results back together into packed 16-bit format */
        c3_c2 = _pack2(c3, c2);
        c1_c0 = _pack2(c1, c0);

        /* Store the results. */
        *(double *) &c[i] = _itod(c3_c2, c1_c0);
    }
}