Function stbi__idct_block

lite/example/cpp_example/mge/cv/stb_image.h:2616–2675

    t0 += p1 + p3;

static void stbi__idct_block(stbi_uc* out, int out_stride, short data[64]) {
    int i, val[64], *v = val;
    stbi_uc* o;
    short* d = data;

    // columns
    for (i = 0; i < 8; ++i, ++d, ++v) {
        // if all zeroes, shortcut -- this avoids dequantizing 0s and IDCTing
        if (d[8] == 0 && d[16] == 0 && d[24] == 0 && d[32] == 0 && d[40] == 0 &&
            d[48] == 0 && d[56] == 0) {
            //    no shortcut                 0     seconds
            //    (1|2|3|4|5|6|7)==0          0     seconds
            //    all separate               -0.047 seconds
            //    1 && 2|3 && 4|5 && 6|7:    -0.047 seconds
            int dcterm = d[0] * 4;
            v[0] = v[8] = v[16] = v[24] = v[32] = v[40] = v[48] = v[56] = dcterm;
        } else {
            STBI__IDCT_1D(d[0], d[8], d[16], d[24], d[32], d[40], d[48], d[56])
            // constants scaled things up by 1<<12; let's bring them back
            // down, but keep 2 extra bits of precision
            x0 += 512;
            x1 += 512;
            x2 += 512;
            x3 += 512;
            v[0] = (x0 + t3) >> 10;
            v[56] = (x0 - t3) >> 10;
            v[8] = (x1 + t2) >> 10;
            v[48] = (x1 - t2) >> 10;
            v[16] = (x2 + t1) >> 10;
            v[40] = (x2 - t1) >> 10;
            v[24] = (x3 + t0) >> 10;
            v[32] = (x3 - t0) >> 10;
        }
    }

    for (i = 0, v = val, o = out; i < 8; ++i, v += 8, o += out_stride) {
        // no fast case since the first 1D IDCT spread components out
        STBI__IDCT_1D(v[0], v[1], v[2], v[3], v[4], v[5], v[6], v[7])
        // constants scaled things up by 1<<12, plus we had 1<<2 from first
        // loop, plus horizontal and vertical each scale by sqrt(8) so together
        // we've got an extra 1<<3, so 1<<17 total we need to remove.
        // so we want to round that, which means adding 0.5 * 1<<17,
        // aka 65536. Also, we'll end up with -128 to 127 that we want
        // to encode as 0..255 by adding 128, so we'll add that before the shift
        x0 += 65536 + (128 << 17);
        x1 += 65536 + (128 << 17);
        x2 += 65536 + (128 << 17);
        x3 += 65536 + (128 << 17);
        // tried computing the shifts into temps, or'ing the temps to see
        // if any were out of range, but that was slower
        o[0] = stbi__clamp((x0 + t3) >> 17);
        o[7] = stbi__clamp((x0 - t3) >> 17);
        o[1] = stbi__clamp((x1 + t2) >> 17);
        o[6] = stbi__clamp((x1 - t2) >> 17);
        o[2] = stbi__clamp((x2 + t1) >> 17);
        o[5] = stbi__clamp((x2 - t1) >> 17);
        o[3] = stbi__clamp((x3 + t0) >> 17);
        o[4] = stbi__clamp((x3 - t0) >> 17);