generic-library/vpx
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Remove usage of predict buffer for decode

Browse Source 
Instead of using the predict buffer, the decoder now writes
the predictor into the recon buffer.  For blocks with eob=0,
unnecessary idcts can be eliminated.  This gave a performance
boost of ~1.8% for the HD clips used.

Tero: Added needed changes to ARM side and scheduled some
      assembly code to prevent interlocks.

Patch Set 6:  Merged (I1bcdca7a95aacc3a181b9faa6b10e3a71ee24df3)
into this commit because of similarities in the idct
functions.
Patch Set 7: EC bug fix.

Change-Id: Ie31d90b5d3522e1108163f2ac491e455e3f955e6
This commit is contained in:
Scott LaVarnway
2011-10-18 12:06:50 -04:00
parent 6505adf271
commit ed9c66f584
56 changed files with 1496 additions and 2455 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
vp8/decoder/threading.c
View File

@@ -138,11 +138,11 @@ static void decode_macroblock(VP8D_COMP *pbi, MACROBLOCKD *xd, int mb_row, int m
/* do prediction */
if (xd->mode_info_context->mbmi.ref_frame == INTRA_FRAME)
{
vp8mt_build_intra_predictors_mbuv(pbi, xd, mb_row, mb_col);
vp8mt_build_intra_predictors_mbuv_s(pbi, xd, mb_row, mb_col);
if (xd->mode_info_context->mbmi.mode != B_PRED)
{
vp8mt_build_intra_predictors_mby(pbi, xd, mb_row, mb_col);
vp8mt_build_intra_predictors_mby_s(pbi, xd, mb_row, mb_col);
} else {
vp8mt_intra_prediction_down_copy(pbi, xd, mb_row, mb_col);
}
@@ -201,7 +201,7 @@ static void decode_macroblock(VP8D_COMP *pbi, MACROBLOCKD *xd, int mb_row, int m
DEQUANT_INVOKE (&pbi->dequant, dc_idct_add_y_block)
(xd->qcoeff, xd->block[0].dequant,
xd->predictor, xd->dst.y_buffer,
xd->dst.y_buffer,
xd->dst.y_stride, xd->eobs, xd->block[24].diff);
}
else if (xd->mode_info_context->mbmi.mode == B_PRED)
@@ -211,19 +211,21 @@ static void decode_macroblock(VP8D_COMP *pbi, MACROBLOCKD *xd, int mb_row, int m
BLOCKD *b = &xd->block[i];
int b_mode = xd->mode_info_context->bmi[i].as_mode;
vp8mt_predict_intra4x4(pbi, xd, b_mode, b->predictor, mb_row, mb_col, i);
vp8mt_predict_intra4x4(pbi, xd, b_mode, *(b->base_dst) + b->dst,
b->dst_stride, mb_row, mb_col, i);
if (xd->eobs[i] > 1)
{
DEQUANT_INVOKE(&pbi->dequant, idct_add)
(b->qcoeff, b->dequant, b->predictor,
*(b->base_dst) + b->dst, 16, b->dst_stride);
(b->qcoeff, b->dequant,
*(b->base_dst) + b->dst, b->dst_stride);
}
else
{
IDCT_INVOKE(RTCD_VTABLE(idct), idct1_scalar_add)
(b->qcoeff[0] * b->dequant[0], b->predictor,
*(b->base_dst) + b->dst, 16, b->dst_stride);
(b->qcoeff[0] * b->dequant[0],
*(b->base_dst) + b->dst, b->dst_stride,
*(b->base_dst) + b->dst, b->dst_stride);
((int *)b->qcoeff)[0] = 0;
}
}
@@ -232,13 +234,13 @@ static void decode_macroblock(VP8D_COMP *pbi, MACROBLOCKD *xd, int mb_row, int m
{
DEQUANT_INVOKE (&pbi->dequant, idct_add_y_block)
(xd->qcoeff, xd->block[0].dequant,
xd->predictor, xd->dst.y_buffer,
xd->dst.y_buffer,
xd->dst.y_stride, xd->eobs);
}
DEQUANT_INVOKE (&pbi->dequant, idct_add_uv_block)
(xd->qcoeff+16*16, xd->block[16].dequant,
xd->predictor+16*16, xd->dst.u_buffer, xd->dst.v_buffer,
xd->dst.u_buffer, xd->dst.v_buffer,
xd->dst.uv_stride, xd->eobs+16);
}