videolan
/
vlc
mirror of https://gitea.goldendeliverer.com/videolan/vlc.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
Browse Source

* Le bug des pixels invers�s de la dct mmx � �t� corrig� (et non plus sau- 

vagement kludg�).

* La sparse idct fonctionne.

* Plusieurs versions de la dct ont �t� inclues dans vdec_idct pour pou-
  voir choisir la plus performante quand tout marchera.
pull/2/head
Gaël Hendryckx 27 years ago
parent
57509f7586
commit
7e618974c2
3 changed files with 240 additions and 5 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 239
      src/video_decoder/vdec_idct.c
  2. 2
      src/video_parser/vpar_blocks.c
  3. 4
      src/video_parser/vpar_synchro.c

239
src/video_decoder/vdec_idct.c
View File

@ -74,11 +74,13 @@ void vdec_InitIDCT (vdec_thread_t * p_vdec)
p_pre[i*64+i] = 1 << SPARSE_SCALE_FACTOR;
vdec_IDCT( p_vdec, &p_pre[i*64], 0) ;
}
return;
}
void vdec_SparseIDCT (vdec_thread_t * p_vdec, dctelem_t * p_block,
int i_sparse_pos)
{
/*debug*/
short int val;
int * dp;
int v;
@ -90,7 +92,20 @@ void vdec_SparseIDCT (vdec_thread_t * p_vdec, dctelem_t * p_block,
if ( i_sparse_pos == 0 )
{
dp=(int *)p_block;
val= *p_block >> 6;
// v=*p_block;
/* cuisine a verifier */
/* if (v < 0)
{
val=-v;
val+=4;
val/=8;
val=-val;
}
else
{*/
/* val= (v + 4) /8; */
val=RIGHT_SHIFT((*p_block + 4), 3);
// }
/* Compute int to assign. This speeds things up a bit */
v = ((val & 0xffff) | (val << 16));
dp[0] = v; dp[1] = v; dp[2] = v; dp[3] = v;
@ -138,7 +153,227 @@ void vdec_SparseIDCT (vdec_thread_t * p_vdec, dctelem_t * p_block,
void vdec_IDCT( vdec_thread_t * p_vdec, dctelem_t * p_block, int i_idontcare )
{
//IDCT_mmx(p_block);
#if 1
#if 0
/* dct classique: pour tester la meilleure entre la classique et la */
/* no classique */
s32 tmp0, tmp1, tmp2, tmp3;
s32 tmp10, tmp11, tmp12, tmp13;
s32 z1, z2, z3, z4, z5;
dctelem_t * dataptr;
int rowctr;
SHIFT_TEMPS
/* Pass 1: process rows. */
/* Note results are scaled up by sqrt(8) compared to a true IDCT; */
/* furthermore, we scale the results by 2**PASS1_BITS. */
dataptr = p_block;
for (rowctr = DCTSIZE-1; rowctr >= 0; rowctr--)
{
/* Due to quantization, we will usually find that many of the input
* coefficients are zero, especially the AC terms. We can exploit this
* by short-circuiting the IDCT calculation for any row in which all
* the AC terms are zero. In that case each output is equal to the
* DC coefficient (with scale factor as needed).
* With typical images and quantization tables, half or more of the
* row DCT calculations can be simplified this way.
*/
if ((dataptr[1] | dataptr[2] | dataptr[3] | dataptr[4] |
dataptr[5] | dataptr[6] | dataptr[7]) == 0)
{
/* AC terms all zero */
dctelem_t dcval = (dctelem_t) (dataptr[0] << PASS1_BITS);
dataptr[0] = dcval;
dataptr[1] = dcval;
dataptr[2] = dcval;
dataptr[3] = dcval;
dataptr[4] = dcval;
dataptr[5] = dcval;
dataptr[6] = dcval;
dataptr[7] = dcval;
dataptr += DCTSIZE; /* advance pointer to next row */
continue;
}
/* Even part: reverse the even part of the forward DCT. */
/* The rotator is sqrt(2)*c(-6). */
z2 = (s32) dataptr[2];
z3 = (s32) dataptr[6];
z1 = MULTIPLY(z2 + z3, FIX(0.541196100));
tmp2 = z1 + MULTIPLY(z3, - FIX(1.847759065));
tmp3 = z1 + MULTIPLY(z2, FIX(0.765366865));
tmp0 = ((s32) dataptr[0] + (s32) dataptr[4]) << CONST_BITS;
tmp1 = ((s32) dataptr[0] - (s32) dataptr[4]) << CONST_BITS;
tmp10 = tmp0 + tmp3;
tmp13 = tmp0 - tmp3;
tmp11 = tmp1 + tmp2;
tmp12 = tmp1 - tmp2;
/* Odd part per figure 8; the matrix is unitary and hence its
* transpose is its inverse. i0..i3 are y7,y5,y3,y1 respectively.
*/
tmp0 = (s32) dataptr[7];
tmp1 = (s32) dataptr[5];
tmp2 = (s32) dataptr[3];
tmp3 = (s32) dataptr[1];
z1 = tmp0 + tmp3;
z2 = tmp1 + tmp2;
z3 = tmp0 + tmp2;
z4 = tmp1 + tmp3;
z5 = MULTIPLY(z3 + z4, FIX(1.175875602)); /* sqrt(2) * c3 */
tmp0 = MULTIPLY(tmp0, FIX(0.298631336)); /* sqrt(2) * (-c1+c3+c5-c7) */
tmp1 = MULTIPLY(tmp1, FIX(2.053119869)); /* sqrt(2) * ( c1+c3-c5+c7) */
tmp2 = MULTIPLY(tmp2, FIX(3.072711026)); /* sqrt(2) * ( c1+c3+c5-c7) */
tmp3 = MULTIPLY(tmp3, 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;
tmp0 += z1 + z3;
tmp1 += z2 + z4;
tmp2 += z2 + z3;
tmp3 += z1 + z4;
/* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */
dataptr[0] = (dctelem_t) DESCALE(tmp10 + tmp3, CONST_BITS-PASS1_BITS);
dataptr[7] = (dctelem_t) DESCALE(tmp10 - tmp3, CONST_BITS-PASS1_BITS);
dataptr[1] = (dctelem_t) DESCALE(tmp11 + tmp2, CONST_BITS-PASS1_BITS);
dataptr[6] = (dctelem_t) DESCALE(tmp11 - tmp2, CONST_BITS-PASS1_BITS);
dataptr[2] = (dctelem_t) DESCALE(tmp12 + tmp1, CONST_BITS-PASS1_BITS);
dataptr[5] = (dctelem_t) DESCALE(tmp12 - tmp1, CONST_BITS-PASS1_BITS);
dataptr[3] = (dctelem_t) DESCALE(tmp13 + tmp0, CONST_BITS-PASS1_BITS);
dataptr[4] = (dctelem_t) DESCALE(tmp13 - tmp0, CONST_BITS-PASS1_BITS);
dataptr += DCTSIZE; /* advance pointer to next row */
}
/* Pass 2: process columns. */
/* Note that we must descale the results by a factor of 8 == 2**3, */
/* and also undo the PASS1_BITS scaling. */
dataptr = p_block;
for (rowctr = DCTSIZE-1; rowctr >= 0; rowctr--)
{
/* Columns of zeroes can be exploited in the same way as we did with rows.
* However, the row calculation has created many nonzero AC terms, so the
* simplification applies less often (typically 5% to 10% of the time).
* On machines with very fast multiplication, it's possible that the
* test takes more time than it's worth. In that case this section
* may be commented out.
*/
#ifndef NO_ZERO_COLUMN_TEST /*ajoute un test mais evite des calculs */
if ((dataptr[DCTSIZE*1] | dataptr[DCTSIZE*2] | dataptr[DCTSIZE*3] |
dataptr[DCTSIZE*4] | dataptr[DCTSIZE*5] | dataptr[DCTSIZE*6] |
dataptr[DCTSIZE*7]) == 0)
{
/* AC terms all zero */
dctelem_t dcval = (dctelem_t) DESCALE((s32) dataptr[0], PASS1_BITS+3);
dataptr[DCTSIZE*0] = dcval;
dataptr[DCTSIZE*1] = dcval;
dataptr[DCTSIZE*2] = dcval;
dataptr[DCTSIZE*3] = dcval;
dataptr[DCTSIZE*4] = dcval;
dataptr[DCTSIZE*5] = dcval;
dataptr[DCTSIZE*6] = dcval;
dataptr[DCTSIZE*7] = dcval;
dataptr++; /* advance pointer to next column */
continue;
}
#endif
/* Even part: reverse the even part of the forward DCT. */
/* The rotator is sqrt(2)*c(-6). */
z2 = (s32) dataptr[DCTSIZE*2];
z3 = (s32) dataptr[DCTSIZE*6];
z1 = MULTIPLY(z2 + z3, FIX(0.541196100));
tmp2 = z1 + MULTIPLY(z3, - FIX(1.847759065));
tmp3 = z1 + MULTIPLY(z2, FIX(0.765366865));
tmp0 = ((s32) dataptr[DCTSIZE*0] + (s32) dataptr[DCTSIZE*4]) << CONST_BITS;
tmp1 = ((s32) dataptr[DCTSIZE*0] - (s32) dataptr[DCTSIZE*4]) << CONST_BITS;
tmp10 = tmp0 + tmp3;
tmp13 = tmp0 - tmp3;
tmp11 = tmp1 + tmp2;
tmp12 = tmp1 - tmp2;
/* Odd part per figure 8; the matrix is unitary and hence its
* transpose is its inverse. i0..i3 are y7,y5,y3,y1 respectively.
*/
tmp0 = (s32) dataptr[DCTSIZE*7];
tmp1 = (s32) dataptr[DCTSIZE*5];
tmp2 = (s32) dataptr[DCTSIZE*3];
tmp3 = (s32) dataptr[DCTSIZE*1];
z1 = tmp0 + tmp3;
z2 = tmp1 + tmp2;
z3 = tmp0 + tmp2;
z4 = tmp1 + tmp3;
z5 = MULTIPLY(z3 + z4, FIX(1.175875602)); /* sqrt(2) * c3 */
tmp0 = MULTIPLY(tmp0, FIX(0.298631336)); /* sqrt(2) * (-c1+c3+c5-c7) */
tmp1 = MULTIPLY(tmp1, FIX(2.053119869)); /* sqrt(2) * ( c1+c3-c5+c7) */
tmp2 = MULTIPLY(tmp2, FIX(3.072711026)); /* sqrt(2) * ( c1+c3+c5-c7) */
tmp3 = MULTIPLY(tmp3, 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;
tmp0 += z1 + z3;
tmp1 += z2 + z4;
tmp2 += z2 + z3;
tmp3 += z1 + z4;
/* Final output stage: inputs are tmp10..tmp13, tmp0..tmp3 */
dataptr[DCTSIZE*0] = (dctelem_t) DESCALE(tmp10 + tmp3,
CONST_BITS+PASS1_BITS+3);
dataptr[DCTSIZE*7] = (dctelem_t) DESCALE(tmp10 - tmp3,
CONST_BITS+PASS1_BITS+3);
dataptr[DCTSIZE*1] = (dctelem_t) DESCALE(tmp11 + tmp2,
CONST_BITS+PASS1_BITS+3);
dataptr[DCTSIZE*6] = (dctelem_t) DESCALE(tmp11 - tmp2,
CONST_BITS+PASS1_BITS+3);
dataptr[DCTSIZE*2] = (dctelem_t) DESCALE(tmp12 + tmp1,
CONST_BITS+PASS1_BITS+3);
dataptr[DCTSIZE*5] = (dctelem_t) DESCALE(tmp12 - tmp1,
CONST_BITS+PASS1_BITS+3);
dataptr[DCTSIZE*3] = (dctelem_t) DESCALE(tmp13 + tmp0,
CONST_BITS+PASS1_BITS+3);
dataptr[DCTSIZE*4] = (dctelem_t) DESCALE(tmp13 - tmp0,
CONST_BITS+PASS1_BITS+3);
dataptr++; /* advance pointer to next column */
}
#endif
#if 1 /*dct avec no classique*/
s32 tmp0, tmp1, tmp2, tmp3;
s32 tmp10, tmp11, tmp12, tmp13;
s32 z1, z2, z3, z4, z5;

2
src/video_parser/vpar_blocks.c
View File

@ -1460,7 +1460,7 @@ static void vpar_DecodeMPEG2Intra( vpar_thread_t * p_vpar, macroblock_t * p_mb,
: i_level;
break;
case DCT_EOB:
if( i_nc <= 0 )
if( i_nc <= 1 )
{
p_mb->pf_idct[i_b] = vdec_SparseIDCT;
p_mb->pi_sparse_pos[i_b] = i_coef;

4
src/video_parser/vpar_synchro.c
View File

@ -149,8 +149,8 @@ boolean_t vpar_SynchroChoose( vpar_thread_t * p_vpar, int i_coding_type,
int i_structure )
{
// return( 1 );
return( i_coding_type == I_CODING_TYPE || i_coding_type == P_CODING_TYPE );
//return( i_coding_type == I_CODING_TYPE );
// return( i_coding_type == I_CODING_TYPE || i_coding_type == P_CODING_TYPE );
return( i_coding_type == I_CODING_TYPE );
}
/*****************************************************************************

Write Preview
Loading…
Cancel
Save