idct.c

void VP62_IDCT8x8(PVP62 pVP62, int b){   
   
    /************************************************************/   
    /*                                                          */   
    /* Inverse DCT defined as:                                  */   
    /*                                                          */   
    /*            sqrt(2)      7              PI                */   
    /*  Qj = X0 * ------- + Sum     Xn * Cos( -- * n*(2*j+1) )  */   
    /*               2         n=1            16                */   
    /*                                                          */   
    /************************************************************/   
   
    short *output = pVP62->block8x8[b];   
    int c, row, col, src = 0, dst = 0, scoeff[64] /* Scaled coeffs */;   
    int x0, x1, x2, x3, x4, x5, x6, x7, t0, t1, t2, t3, t4, t5, t6, t7, u0, u1, u2, u3, u4, u5, v0, v1, v2, v3;   
   
    static unsigned char zigzag[64] = {  0,  1,  8, 16,  9,  2,  3, 10,   
                                        17, 24, 32, 25, 18, 11,  4,  5,   
                                        12, 19, 26, 33, 40, 48, 41, 34,   
                                        27, 20, 13,  6,  7, 14, 21, 28,   
                                        35, 42, 49, 56, 57, 50, 43, 36,   
                                        29, 22, 15, 23, 30, 37, 44, 51,   
                                        58, 59, 52, 45, 38, 31, 39, 46,   
                                        53, 60, 61, 54, 47, 55, 62, 63 };   
   
    for(c = 0; c < 64; c++){   
   
        scoeff[zigzag[c]] = pVP62->coeff420[b][c] * pVP62->coeffScale[c];   
    }   
   
    for(row = 0; row < 8; row++){   
       
        x0 = scoeff[src];   
        x1 = scoeff[src + 1];   
        x2 = scoeff[src + 2];   
        x3 = scoeff[src + 3];   
        x4 = scoeff[src + 4];   
        x5 = scoeff[src + 5];   
        x6 = scoeff[src + 6];   
        x7 = scoeff[src + 7];   
       
        if (x0 | x1 | x2 | x3 | x4 | x5 | x6 | x7){   
   
            t0 = ((COS_1_16 * x1) >> 16) + ((COS_7_16 * x7) >> 16);   
            t1 = ((COS_7_16 * x1) >> 16) - ((COS_1_16 * x7) >> 16);   
            t2 = ((COS_3_16 * x3) >> 16) + ((COS_5_16 * x5) >> 16);   
            t3 = ((COS_3_16 * x5) >> 16) - ((COS_5_16 * x3) >> 16);   
            u0 = (COS_4_16 * (t0 - t2)) >> 16;   
            u1 = (COS_4_16 * (t1 - t3)) >> 16;   
            u2 = t0 + t2;   
            u3 = t1 + t3;   
            t4 = (COS_4_16 * (x0 + x4)) >> 16;   
            t5 = (COS_4_16 * (x0 - x4)) >> 16;   
            t6 = ((COS_2_16 * x2) >> 16) + ((COS_6_16 * x6) >> 16);   
            t7 = ((COS_6_16 * x2) >> 16) - ((COS_2_16 * x6) >> 16);   
            u4 = t4 - t6;   
            u5 = t4 + t6;   
            v0 = t5 + u0;   
            v1 = u1 - t7;   
            v2 = t5 - u0;   
            v3 = u1 + t7;   
           
            scoeff[src] = u5 + u2;   
            scoeff[src + 7] = u5 - u2;   
            scoeff[src + 1] = v0 + v3;   
            scoeff[src + 2] = v0 - v3;   
            scoeff[src + 3] = u4 + u3;   
            scoeff[src + 4] = u4 - u3;   
            scoeff[src + 5] = v2 + v1;   
            scoeff[src + 6] = v2 - v1;   
        }   
       
        src += 8;   
    }   
   
    src = 0;   
    for(col = 0; col < 8; col++){   
   
        x0 = scoeff[src];   
        x1 = scoeff[src + 8];   
        x2 = scoeff[src + 16];   
        x3 = scoeff[src + 24];   
        x4 = scoeff[src + 32];   
        x5 = scoeff[src + 40];   
        x6 = scoeff[src + 48];   
        x7 = scoeff[src + 56];   
       
        if(x0 | x1 | x2 | x3 | x4 | x5 | x6 | x7){   
           
            t0 = ((COS_1_16 * x1) >> 16) + ((COS_7_16 * x7) >> 16);   
            t1 = ((COS_7_16 * x1) >> 16) - ((COS_1_16 * x7) >> 16);   
            t2 = ((COS_3_16 * x3) >> 16) + ((COS_5_16 * x5) >> 16);   
            t3 = ((COS_3_16 * x5) >> 16) - ((COS_5_16 * x3) >> 16);   
            u0 = (COS_4_16 * (t0 - t2)) >> 16;   
            u1 = (COS_4_16 * (t1 - t3)) >> 16;   
            u2 = t0 + t2;   
            u3 = t1 + t3;   
            t4 = (COS_4_16 * (x0 + x4)) >> 16;   
            t5 = (COS_4_16 * (x0 - x4)) >> 16;   
            t6 = ((COS_2_16 * x2) >> 16) + ((COS_6_16 * x6) >> 16);   
            t7 = ((COS_6_16 * x2) >> 16) - ((COS_2_16 * x6) >> 16);   
            u4 = t4 - t6;   
            u5 = t4 + t6;   
            v0 = t5 + u0;   
            v1 = u1 - t7;   
            v2 = t5 - u0;   
            v3 = u1 + t7;   
           
            output[dst] = (short)((u5 + u2 + 8) >> 4);   
            output[dst + 56] = (short)((u5 - u2 + 8) >> 4);   
            output[dst +  8] = (short)((v0 + v3 + 8) >> 4);   
            output[dst + 16] = (short)((v0 - v3 + 8) >> 4);   
            output[dst + 24] = (short)((u4 + u3 + 8) >> 4);   
            output[dst + 32] = (short)((u4 - u3 + 8) >> 4);   
            output[dst + 40] = (short)((v2 + v1 + 8) >> 4);   
            output[dst + 48] = (short)((v2 - v1 + 8) >> 4);   
        }   
        else{   
           
            output[dst] = 0;   
            output[dst +  8] = 0;   
            output[dst + 16] = 0;   
            output[dst + 24] = 0;   
            output[dst + 32] = 0;   
            output[dst + 40] = 0;   
            output[dst + 48] = 0;   
            output[dst + 56] = 0;   
        }   
       
        src++;   
        dst++;   
    }   
}