fdct_ifast (DCTELEM * data)
{
int_fast16_t tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
int_fast16_t tmp10, tmp11, tmp12, tmp13;
int_fast16_t z1, z2, z3, z4, z5, z11, z13;
DCTELEM *dataptr;
int ctr;
row_fdct(data);
/* Pass 2: process columns. */
dataptr = data;
for (ctr = DCTSIZE-1; ctr >= 0; ctr--) {
tmp0 = dataptr[DCTSIZE*0] + dataptr[DCTSIZE*7];
tmp7 = dataptr[DCTSIZE*0] - dataptr[DCTSIZE*7];
tmp1 = dataptr[DCTSIZE*1] + dataptr[DCTSIZE*6];
tmp6 = dataptr[DCTSIZE*1] - dataptr[DCTSIZE*6];
tmp2 = dataptr[DCTSIZE*2] + dataptr[DCTSIZE*5];
tmp5 = dataptr[DCTSIZE*2] - dataptr[DCTSIZE*5];
tmp3 = dataptr[DCTSIZE*3] + dataptr[DCTSIZE*4];
tmp4 = dataptr[DCTSIZE*3] - dataptr[DCTSIZE*4];
/* Even part */
tmp10 = tmp0 + tmp3; /* phase 2 */
tmp13 = tmp0 - tmp3;
tmp11 = tmp1 + tmp2;
tmp12 = tmp1 - tmp2;
dataptr[DCTSIZE*0] = tmp10 + tmp11; /* phase 3 */
dataptr[DCTSIZE*4] = tmp10 - tmp11;
z1 = MULTIPLY(tmp12 + tmp13, FIX_0_707106781); /* c4 */
dataptr[DCTSIZE*2] = tmp13 + z1; /* phase 5 */
dataptr[DCTSIZE*6] = tmp13 - z1;
/* Odd part */
tmp10 = tmp4 + tmp5; /* phase 2 */
tmp11 = tmp5 + tmp6;
tmp12 = tmp6 + tmp7;
/* The rotator is modified from fig 4-8 to avoid extra negations. */
z5 = MULTIPLY(tmp10 - tmp12, FIX_0_382683433); /* c6 */
z2 = MULTIPLY(tmp10, FIX_0_541196100) + z5; /* c2-c6 */
z4 = MULTIPLY(tmp12, FIX_1_306562965) + z5; /* c2+c6 */
z3 = MULTIPLY(tmp11, FIX_0_707106781); /* c4 */
z11 = tmp7 + z3; /* phase 5 */
z13 = tmp7 - z3;
dataptr[DCTSIZE*5] = z13 + z2; /* phase 6 */
dataptr[DCTSIZE*3] = z13 - z2;
dataptr[DCTSIZE*1] = z11 + z4;
dataptr[DCTSIZE*7] = z11 - z4;
dataptr++; /* advance pointer to next column */
}
}
void ff_faandct(DCTELEM *data)
{
FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
FLOAT tmp10, tmp11, tmp12, tmp13;
FLOAT z2, z4, z11, z13;
FLOAT av_unused z5;
FLOAT temp[64];
int i;
emms_c();
row_fdct(temp, data);
for (i = 0; i < 8; i++)
{
tmp0 = temp[8*0 + i] + temp[8*7 + i];
tmp7 = temp[8*0 + i] - temp[8*7 + i];
tmp1 = temp[8*1 + i] + temp[8*6 + i];
tmp6 = temp[8*1 + i] - temp[8*6 + i];
tmp2 = temp[8*2 + i] + temp[8*5 + i];
tmp5 = temp[8*2 + i] - temp[8*5 + i];
tmp3 = temp[8*3 + i] + temp[8*4 + i];
tmp4 = temp[8*3 + i] - temp[8*4 + i];
tmp10 = tmp0 + tmp3;
tmp13 = tmp0 - tmp3;
tmp11 = tmp1 + tmp2;
tmp12 = tmp1 - tmp2;
data[8*0 + i] = lrintf(SCALE(8 * 0 + i) * (tmp10 + tmp11));
data[8*4 + i] = lrintf(SCALE(8 * 4 + i) * (tmp10 - tmp11));
tmp12 += tmp13;
tmp12 *= A1;
data[8*2 + i] = lrintf(SCALE(8 * 2 + i) * (tmp13 + tmp12));
data[8*6 + i] = lrintf(SCALE(8 * 6 + i) * (tmp13 - tmp12));
tmp4 += tmp5;
tmp5 += tmp6;
tmp6 += tmp7;
#if 0
z5 = (tmp4 - tmp6) * A5;
z2 = tmp4 * A2 + z5;
z4 = tmp6 * A4 + z5;
#else
z2 = tmp4 * (A2 + A5) - tmp6 * A5;
z4 = tmp6 * (A4 - A5) + tmp4 * A5;
#endif
tmp5 *= A1;
z11 = tmp7 + tmp5;
z13 = tmp7 - tmp5;
data[8*5 + i] = lrintf(SCALE(8 * 5 + i) * (z13 + z2));
data[8*3 + i] = lrintf(SCALE(8 * 3 + i) * (z13 - z2));
data[8*1 + i] = lrintf(SCALE(8 * 1 + i) * (z11 + z4));
data[8*7 + i] = lrintf(SCALE(8 * 7 + i) * (z11 - z4));
}
}
ff_fdct248_islow (DCTELEM * data)
{
int_fast32_t tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
int_fast32_t tmp10, tmp11, tmp12, tmp13;
int_fast32_t z1;
DCTELEM *dataptr;
int ctr;
row_fdct(data);
/* Pass 2: process columns.
* We remove the PASS1_BITS scaling, but leave the results scaled up
* by an overall factor of 8.
*/
dataptr = data;
for (ctr = DCTSIZE-1; ctr >= 0; ctr--)
{
tmp0 = dataptr[DCTSIZE*0] + dataptr[DCTSIZE*1];
tmp1 = dataptr[DCTSIZE*2] + dataptr[DCTSIZE*3];
tmp2 = dataptr[DCTSIZE*4] + dataptr[DCTSIZE*5];
tmp3 = dataptr[DCTSIZE*6] + dataptr[DCTSIZE*7];
tmp4 = dataptr[DCTSIZE*0] - dataptr[DCTSIZE*1];
tmp5 = dataptr[DCTSIZE*2] - dataptr[DCTSIZE*3];
tmp6 = dataptr[DCTSIZE*4] - dataptr[DCTSIZE*5];
tmp7 = dataptr[DCTSIZE*6] - dataptr[DCTSIZE*7];
tmp10 = tmp0 + tmp3;
tmp11 = tmp1 + tmp2;
tmp12 = tmp1 - tmp2;
tmp13 = tmp0 - tmp3;
dataptr[DCTSIZE*0] = (DCTELEM) DESCALE(tmp10 + tmp11, PASS1_BITS);
dataptr[DCTSIZE*4] = (DCTELEM) DESCALE(tmp10 - tmp11, PASS1_BITS);
z1 = MULTIPLY(tmp12 + tmp13, FIX_0_541196100);
dataptr[DCTSIZE*2] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp13, FIX_0_765366865),
CONST_BITS+PASS1_BITS);
dataptr[DCTSIZE*6] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp12, - FIX_1_847759065),
CONST_BITS+PASS1_BITS);
tmp10 = tmp4 + tmp7;
tmp11 = tmp5 + tmp6;
tmp12 = tmp5 - tmp6;
tmp13 = tmp4 - tmp7;
dataptr[DCTSIZE*1] = (DCTELEM) DESCALE(tmp10 + tmp11, PASS1_BITS);
dataptr[DCTSIZE*5] = (DCTELEM) DESCALE(tmp10 - tmp11, PASS1_BITS);
z1 = MULTIPLY(tmp12 + tmp13, FIX_0_541196100);
dataptr[DCTSIZE*3] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp13, FIX_0_765366865),
CONST_BITS+PASS1_BITS);
dataptr[DCTSIZE*7] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp12, - FIX_1_847759065),
CONST_BITS+PASS1_BITS);
dataptr++; /* advance pointer to next column */
}
}
fdct_ifast248 (DCTELEM * data)
{
int_fast16_t tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
int_fast16_t tmp10, tmp11, tmp12, tmp13;
int_fast16_t z1;
DCTELEM *dataptr;
int ctr;
SHIFT_TEMPS
row_fdct(data);
/* Pass 2: process columns. */
dataptr = data;
for (ctr = DCTSIZE-1; ctr >= 0; ctr--) {
tmp0 = dataptr[DCTSIZE*0] + dataptr[DCTSIZE*1];
tmp1 = dataptr[DCTSIZE*2] + dataptr[DCTSIZE*3];
tmp2 = dataptr[DCTSIZE*4] + dataptr[DCTSIZE*5];
tmp3 = dataptr[DCTSIZE*6] + dataptr[DCTSIZE*7];
tmp4 = dataptr[DCTSIZE*0] - dataptr[DCTSIZE*1];
tmp5 = dataptr[DCTSIZE*2] - dataptr[DCTSIZE*3];
tmp6 = dataptr[DCTSIZE*4] - dataptr[DCTSIZE*5];
tmp7 = dataptr[DCTSIZE*6] - dataptr[DCTSIZE*7];
/* Even part */
tmp10 = tmp0 + tmp3;
tmp11 = tmp1 + tmp2;
tmp12 = tmp1 - tmp2;
tmp13 = tmp0 - tmp3;
dataptr[DCTSIZE*0] = tmp10 + tmp11;
dataptr[DCTSIZE*4] = tmp10 - tmp11;
z1 = MULTIPLY(tmp12 + tmp13, FIX_0_707106781);
dataptr[DCTSIZE*2] = tmp13 + z1;
dataptr[DCTSIZE*6] = tmp13 - z1;
tmp10 = tmp4 + tmp7;
tmp11 = tmp5 + tmp6;
tmp12 = tmp5 - tmp6;
tmp13 = tmp4 - tmp7;
dataptr[DCTSIZE*1] = tmp10 + tmp11;
dataptr[DCTSIZE*5] = tmp10 - tmp11;
z1 = MULTIPLY(tmp12 + tmp13, FIX_0_707106781);
dataptr[DCTSIZE*3] = tmp13 + z1;
dataptr[DCTSIZE*7] = tmp13 - z1;
dataptr++; /* advance pointer to next column */
}
}
void ff_faandct(int16_t *data)
{
FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
FLOAT tmp10, tmp11, tmp12, tmp13;
FLOAT z2, z4, z11, z13;
FLOAT temp[64];
int i;
emms_c();
row_fdct(temp, data);
for (i=0; i<8; i++) {
tmp0= temp[8*0 + i] + temp[8*7 + i];
tmp7= temp[8*0 + i] - temp[8*7 + i];
tmp1= temp[8*1 + i] + temp[8*6 + i];
tmp6= temp[8*1 + i] - temp[8*6 + i];
tmp2= temp[8*2 + i] + temp[8*5 + i];
tmp5= temp[8*2 + i] - temp[8*5 + i];
tmp3= temp[8*3 + i] + temp[8*4 + i];
tmp4= temp[8*3 + i] - temp[8*4 + i];
tmp10= tmp0 + tmp3;
tmp13= tmp0 - tmp3;
tmp11= tmp1 + tmp2;
tmp12= tmp1 - tmp2;
data[8*0 + i]= lrintf(postscale[8*0 + i] * (tmp10 + tmp11));
data[8*4 + i]= lrintf(postscale[8*4 + i] * (tmp10 - tmp11));
tmp12 += tmp13;
tmp12 *= A1;
data[8*2 + i]= lrintf(postscale[8*2 + i] * (tmp13 + tmp12));
data[8*6 + i]= lrintf(postscale[8*6 + i] * (tmp13 - tmp12));
tmp4 += tmp5;
tmp5 += tmp6;
tmp6 += tmp7;
z2= tmp4*(A2+A5) - tmp6*A5;
z4= tmp6*(A4-A5) + tmp4*A5;
tmp5*=A1;
z11= tmp7 + tmp5;
z13= tmp7 - tmp5;
data[8*5 + i]= lrintf(postscale[8*5 + i] * (z13 + z2));
data[8*3 + i]= lrintf(postscale[8*3 + i] * (z13 - z2));
data[8*1 + i]= lrintf(postscale[8*1 + i] * (z11 + z4));
data[8*7 + i]= lrintf(postscale[8*7 + i] * (z11 - z4));
}
}
void ff_faandct(DCTELEM * data)
{
FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
FLOAT tmp10, tmp11, tmp12, tmp13;
FLOAT z1, z2, z3, z4, z5, z11, z13;
FLOAT temp[64];
int i;
emms_c();
row_fdct(temp, data);
for (i=0; i<8; i++) {
tmp0= temp[8*0 + i] + temp[8*7 + i];
tmp7= temp[8*0 + i] - temp[8*7 + i];
tmp1= temp[8*1 + i] + temp[8*6 + i];
tmp6= temp[8*1 + i] - temp[8*6 + i];
tmp2= temp[8*2 + i] + temp[8*5 + i];
tmp5= temp[8*2 + i] - temp[8*5 + i];
tmp3= temp[8*3 + i] + temp[8*4 + i];
tmp4= temp[8*3 + i] - temp[8*4 + i];
tmp10= tmp0 + tmp3;
tmp13= tmp0 - tmp3;
tmp11= tmp1 + tmp2;
tmp12= tmp1 - tmp2;
data[8*0 + i]= lrintf(SCALE(8*0 + i) * (tmp10 + tmp11));
data[8*4 + i]= lrintf(SCALE(8*4 + i) * (tmp10 - tmp11));
z1= (tmp12 + tmp13)* A1;
data[8*2 + i]= lrintf(SCALE(8*2 + i) * (tmp13 + z1));
data[8*6 + i]= lrintf(SCALE(8*6 + i) * (tmp13 - z1));
tmp10= tmp4 + tmp5;
tmp11= tmp5 + tmp6;
tmp12= tmp6 + tmp7;
z5= (tmp10 - tmp12) * A5;
z2= tmp10*A2 + z5;
z4= tmp12*A4 + z5;
z3= tmp11*A1;
z11= tmp7 + z3;
z13= tmp7 - z3;
data[8*5 + i]= lrintf(SCALE(8*5 + i) * (z13 + z2));
data[8*3 + i]= lrintf(SCALE(8*3 + i) * (z13 - z2));
data[8*1 + i]= lrintf(SCALE(8*1 + i) * (z11 + z4));
data[8*7 + i]= lrintf(SCALE(8*7 + i) * (z11 - z4));
}
}
void ff_faandct248(DCTELEM *data)
{
FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
FLOAT tmp10, tmp11, tmp12, tmp13;
FLOAT temp[64];
int i;
emms_c();
row_fdct(temp, data);
for (i = 0; i < 8; i++)
{
tmp0 = temp[8*0 + i] + temp[8*1 + i];
tmp1 = temp[8*2 + i] + temp[8*3 + i];
tmp2 = temp[8*4 + i] + temp[8*5 + i];
tmp3 = temp[8*6 + i] + temp[8*7 + i];
tmp4 = temp[8*0 + i] - temp[8*1 + i];
tmp5 = temp[8*2 + i] - temp[8*3 + i];
tmp6 = temp[8*4 + i] - temp[8*5 + i];
tmp7 = temp[8*6 + i] - temp[8*7 + i];
tmp10 = tmp0 + tmp3;
tmp11 = tmp1 + tmp2;
tmp12 = tmp1 - tmp2;
tmp13 = tmp0 - tmp3;
data[8*0 + i] = lrintf(SCALE(8 * 0 + i) * (tmp10 + tmp11));
data[8*4 + i] = lrintf(SCALE(8 * 4 + i) * (tmp10 - tmp11));
tmp12 += tmp13;
tmp12 *= A1;
data[8*2 + i] = lrintf(SCALE(8 * 2 + i) * (tmp13 + tmp12));
data[8*6 + i] = lrintf(SCALE(8 * 6 + i) * (tmp13 - tmp12));
tmp10 = tmp4 + tmp7;
tmp11 = tmp5 + tmp6;
tmp12 = tmp5 - tmp6;
tmp13 = tmp4 - tmp7;
data[8*1 + i] = lrintf(SCALE(8 * 0 + i) * (tmp10 + tmp11));
data[8*5 + i] = lrintf(SCALE(8 * 4 + i) * (tmp10 - tmp11));
tmp12 += tmp13;
tmp12 *= A1;
data[8*3 + i] = lrintf(SCALE(8 * 2 + i) * (tmp13 + tmp12));
data[8*7 + i] = lrintf(SCALE(8 * 6 + i) * (tmp13 - tmp12));
}
}
ff_jpeg_fdct_islow (DCTELEM * data)
{
int_fast32_t tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
int_fast32_t tmp10, tmp11, tmp12, tmp13;
int_fast32_t z1, z2, z3, z4, z5;
DCTELEM *dataptr;
int ctr;
row_fdct(data);
/* Pass 2: process columns.
* We remove the PASS1_BITS scaling, but leave the results scaled up
* by an overall factor of 8.
*/
dataptr = data;
for (ctr = DCTSIZE-1; ctr >= 0; ctr--)
{
tmp0 = dataptr[DCTSIZE*0] + dataptr[DCTSIZE*7];
tmp7 = dataptr[DCTSIZE*0] - dataptr[DCTSIZE*7];
tmp1 = dataptr[DCTSIZE*1] + dataptr[DCTSIZE*6];
tmp6 = dataptr[DCTSIZE*1] - dataptr[DCTSIZE*6];
tmp2 = dataptr[DCTSIZE*2] + dataptr[DCTSIZE*5];
tmp5 = dataptr[DCTSIZE*2] - dataptr[DCTSIZE*5];
tmp3 = dataptr[DCTSIZE*3] + dataptr[DCTSIZE*4];
tmp4 = dataptr[DCTSIZE*3] - dataptr[DCTSIZE*4];
/* Even part per LL&M figure 1 --- note that published figure is faulty;
* rotator "sqrt(2)*c1" should be "sqrt(2)*c6".
*/
tmp10 = tmp0 + tmp3;
tmp13 = tmp0 - tmp3;
tmp11 = tmp1 + tmp2;
tmp12 = tmp1 - tmp2;
dataptr[DCTSIZE*0] = (DCTELEM) DESCALE(tmp10 + tmp11, PASS1_BITS);
dataptr[DCTSIZE*4] = (DCTELEM) DESCALE(tmp10 - tmp11, PASS1_BITS);
z1 = MULTIPLY(tmp12 + tmp13, FIX_0_541196100);
dataptr[DCTSIZE*2] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp13, FIX_0_765366865),
CONST_BITS+PASS1_BITS);
dataptr[DCTSIZE*6] = (DCTELEM) DESCALE(z1 + MULTIPLY(tmp12, - FIX_1_847759065),
CONST_BITS+PASS1_BITS);
/* Odd part per figure 8 --- note paper omits factor of sqrt(2).
* cK represents cos(K*pi/16).
* i0..i3 in the paper are tmp4..tmp7 here.
*/
z1 = tmp4 + tmp7;
z2 = tmp5 + tmp6;
z3 = tmp4 + tmp6;
z4 = tmp5 + tmp7;
z5 = MULTIPLY(z3 + z4, FIX_1_175875602); /* sqrt(2) * c3 */
tmp4 = MULTIPLY(tmp4, FIX_0_298631336); /* sqrt(2) * (-c1+c3+c5-c7) */
tmp5 = MULTIPLY(tmp5, FIX_2_053119869); /* sqrt(2) * ( c1+c3-c5+c7) */
tmp6 = MULTIPLY(tmp6, FIX_3_072711026); /* sqrt(2) * ( c1+c3+c5-c7) */
tmp7 = MULTIPLY(tmp7, FIX_1_501321110); /* sqrt(2) * ( c1+c3-c5-c7) */
z1 = MULTIPLY(z1, - FIX_0_899976223); /* sqrt(2) * (c7-c3) */
z2 = MULTIPLY(z2, - FIX_2_562915447); /* sqrt(2) * (-c1-c3) */
z3 = MULTIPLY(z3, - FIX_1_961570560); /* sqrt(2) * (-c3-c5) */
z4 = MULTIPLY(z4, - FIX_0_390180644); /* sqrt(2) * (c5-c3) */
z3 += z5;
z4 += z5;
dataptr[DCTSIZE*7] = (DCTELEM) DESCALE(tmp4 + z1 + z3,
CONST_BITS+PASS1_BITS);
dataptr[DCTSIZE*5] = (DCTELEM) DESCALE(tmp5 + z2 + z4,
CONST_BITS+PASS1_BITS);
dataptr[DCTSIZE*3] = (DCTELEM) DESCALE(tmp6 + z2 + z3,
CONST_BITS+PASS1_BITS);
dataptr[DCTSIZE*1] = (DCTELEM) DESCALE(tmp7 + z1 + z4,
CONST_BITS+PASS1_BITS);
dataptr++; /* advance pointer to next column */
}
}
