vpx/vp9/decoder/x86/vp9_idct_blk_sse2.c

118 lines
4.0 KiB
C
Raw Normal View History

/*
* 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.
*/
WebM Experimental Codec Branch Snapshot This is a code snapshot of experimental work currently ongoing for a next-generation codec. The codebase has been cut down considerably from the libvpx baseline. For example, we are currently only supporting VBR 2-pass rate control and have removed most of the code relating to coding speed, threading, error resilience, partitions and various other features. This is in part to make the codebase easier to work on and experiment with, but also because we want to have an open discussion about how the bitstream will be structured and partitioned and not have that conversation constrained by past work. Our basic working pattern has been to initially encapsulate experiments using configure options linked to #IF CONFIG_XXX statements in the code. Once experiments have matured and we are reasonably happy that they give benefit and can be merged without breaking other experiments, we remove the conditional compile statements and merge them in. Current changes include: * Temporal coding experiment for segments (though still only 4 max, it will likely be increased). * Segment feature experiment - to allow various bits of information to be coded at the segment level. Features tested so far include mode and reference frame information, limiting end of block offset and transform size, alongside Q and loop filter parameters, but this set is very fluid. * Support for 8x8 transform - 8x8 dct with 2nd order 2x2 haar is used in MBs using 16x16 prediction modes within inter frames. * Compound prediction (combination of signals from existing predictors to create a new predictor). * 8 tap interpolation filters and 1/8th pel motion vectors. * Loop filter modifications. * Various entropy modifications and changes to how entropy contexts and updates are handled. * Extended quantizer range matched to transform precision improvements. There are also ongoing further experiments that we hope to merge in the near future: For example, coding of motion and other aspects of the prediction signal to better support larger image formats, use of larger block sizes (e.g. 32x32 and up) and lossless non-transform based coding options (especially for key frames). It is our hope that we will be able to make regular updates and we will warmly welcome community contributions. Please be warned that, at this stage, the codebase is currently slower than VP8 stable branch as most new code has not been optimized, and even the 'C' has been deliberately written to be simple and obvious, not fast. The following graphs have the initial test results, numbers in the tables measure the compression improvement in terms of percentage. The build has the following optional experiments configured: --enable-experimental --enable-enhanced_interp --enable-uvintra --enable-high_precision_mv --enable-sixteenth_subpel_uv CIF Size clips: http://getwebm.org/tmp/cif/ HD size clips: http://getwebm.org/tmp/hd/ (stable_20120309 represents encoding results of WebM master branch build as of commit#7a15907) They were encoded using the following encode parameters: --good --cpu-used=0 -t 0 --lag-in-frames=25 --min-q=0 --max-q=63 --end-usage=0 --auto-alt-ref=1 -p 2 --pass=2 --kf-max-dist=9999 --kf-min-dist=0 --drop-frame=0 --static-thresh=0 --bias-pct=50 --minsection-pct=0 --maxsection-pct=800 --sharpness=0 --arnr-maxframes=7 --arnr-strength=3(for HD,6 for CIF) --arnr-type=3 Change-Id: I5c62ed09cfff5815a2bb34e7820d6a810c23183c
2012-03-10 02:32:50 +01:00
#include "vpx_ports/config.h"
#include "vp9/common/vp9_blockd.h"
#include "vp9/decoder/vp9_dequantize.h"
void vp9_idct_dequant_dc_0_2x_sse2(short *q, const short *dq,
unsigned char *pre, unsigned char *dst,
int dst_stride, const short *dc);
void vp9_idct_dequant_dc_full_2x_sse2(short *q, const short *dq,
unsigned char *pre, unsigned char *dst,
int dst_stride, const short *dc);
void vp9_idct_dequant_0_2x_sse2(short *q, const short *dq,
unsigned char *pre, unsigned char *dst,
int dst_stride, int blk_stride);
void vp9_idct_dequant_full_2x_sse2(short *q, const short *dq,
unsigned char *pre, unsigned char *dst,
int dst_stride, int blk_stride);
void vp9_dequant_dc_idct_add_y_block_sse2(short *q, const short *dq,
unsigned char *pre,
unsigned char *dst,
int stride, unsigned short *eobs,
const short *dc) {
int i;
for (i = 0; i < 4; i++) {
if (((short *)(eobs))[0] & 0xfefe)
vp9_idct_dequant_dc_full_2x_sse2(q, dq, pre, dst, stride, dc);
else
vp9_idct_dequant_dc_0_2x_sse2(q, dq, pre, dst, stride, dc);
if (((short *)(eobs))[1] & 0xfefe)
vp9_idct_dequant_dc_full_2x_sse2(q + 32, dq, pre + 8, dst + 8,
stride, dc + 2);
else
vp9_idct_dequant_dc_0_2x_sse2(q + 32, dq, pre + 8, dst + 8,
stride, dc + 2);
q += 64;
dc += 4;
pre += 64;
dst += stride * 4;
eobs += 4;
}
}
void vp9_dequant_idct_add_y_block_sse2(short *q, const short *dq,
unsigned char *pre, unsigned char *dst,
int stride, unsigned short *eobs) {
int i;
for (i = 0; i < 4; i++) {
if (((short *)(eobs))[0] & 0xfefe)
vp9_idct_dequant_full_2x_sse2(q, dq, pre, dst, stride, 16);
else
vp9_idct_dequant_0_2x_sse2(q, dq, pre, dst, stride, 16);
if (((short *)(eobs))[1] & 0xfefe)
vp9_idct_dequant_full_2x_sse2(q + 32, dq, pre + 8, dst + 8, stride, 16);
else
vp9_idct_dequant_0_2x_sse2(q + 32, dq, pre + 8, dst + 8, stride, 16);
q += 64;
pre += 64;
dst += stride * 4;
eobs += 4;
}
}
void vp9_dequant_idct_add_uv_block_sse2(short *q, const short *dq,
unsigned char *pre,
unsigned char *dstu,
unsigned char *dstv,
int stride, unsigned short *eobs) {
if (((short *)(eobs))[0] & 0xfefe)
vp9_idct_dequant_full_2x_sse2(q, dq, pre, dstu, stride, 8);
else
vp9_idct_dequant_0_2x_sse2(q, dq, pre, dstu, stride, 8);
q += 32;
pre += 32;
dstu += stride * 4;
if (((short *)(eobs))[1] & 0xfefe)
vp9_idct_dequant_full_2x_sse2(q, dq, pre, dstu, stride, 8);
else
vp9_idct_dequant_0_2x_sse2(q, dq, pre, dstu, stride, 8);
q += 32;
pre += 32;
if (((short *)(eobs))[2] & 0xfefe)
vp9_idct_dequant_full_2x_sse2(q, dq, pre, dstv, stride, 8);
else
vp9_idct_dequant_0_2x_sse2(q, dq, pre, dstv, stride, 8);
q += 32;
pre += 32;
dstv += stride * 4;
if (((short *)(eobs))[3] & 0xfefe)
vp9_idct_dequant_full_2x_sse2(q, dq, pre, dstv, stride, 8);
else
vp9_idct_dequant_0_2x_sse2(q, dq, pre, dstv, stride, 8);
}