ed9c66f584
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
64 lines
1.4 KiB
C
64 lines
1.4 KiB
C
/*
|
|
* Copyright (c) 2010 The WebM project authors. All Rights Reserved.
|
|
*
|
|
* Use of this source code is governed by a BSD-style license
|
|
* that can be found in the LICENSE file in the root of the source
|
|
* tree. An additional intellectual property rights grant can be found
|
|
* in the file PATENTS. All contributing project authors may
|
|
* be found in the AUTHORS file in the root of the source tree.
|
|
*/
|
|
|
|
|
|
#include "vpx_config.h"
|
|
#include "dequantize.h"
|
|
#include "vp8/common/idct.h"
|
|
#include "vpx_mem/vpx_mem.h"
|
|
|
|
void vp8_dequantize_b_c(BLOCKD *d)
|
|
{
|
|
int i;
|
|
short *DQ = d->dqcoeff;
|
|
short *Q = d->qcoeff;
|
|
short *DQC = d->dequant;
|
|
|
|
for (i = 0; i < 16; i++)
|
|
{
|
|
DQ[i] = Q[i] * DQC[i];
|
|
}
|
|
}
|
|
|
|
void vp8_dequant_idct_add_c(short *input, short *dq,
|
|
unsigned char *dest, int stride)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < 16; i++)
|
|
{
|
|
input[i] = dq[i] * input[i];
|
|
}
|
|
|
|
vp8_short_idct4x4llm_c(input, dest, stride, dest, stride);
|
|
|
|
vpx_memset(input, 0, 32);
|
|
|
|
}
|
|
|
|
void vp8_dequant_dc_idct_add_c(short *input, short *dq,
|
|
unsigned char *dest, int stride,
|
|
int Dc)
|
|
{
|
|
int i;
|
|
|
|
input[0] = (short)Dc;
|
|
|
|
for (i = 1; i < 16; i++)
|
|
{
|
|
input[i] = dq[i] * input[i];
|
|
}
|
|
|
|
vp8_short_idct4x4llm_c(input, dest, stride, dest, stride);
|
|
|
|
vpx_memset(input, 0, 32);
|
|
|
|
}
|