6035da5448
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
158 lines
5.6 KiB
C
158 lines
5.6 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.
|
|
*/
|
|
|
|
|
|
/* \file
|
|
* \brief Provides portable memory access primitives for operating on aligned
|
|
* data
|
|
*
|
|
* This file is split from mem_ops.h for easier maintenance. See mem_ops.h
|
|
* for a more detailed description of these primitives.
|
|
*/
|
|
#ifndef INCLUDED_BY_MEM_OPS_H
|
|
#error Include mem_ops.h, not mem_ops_aligned.h directly.
|
|
#endif
|
|
|
|
/* Architectures that provide instructions for doing this byte swapping
|
|
* could redefine these macros.
|
|
*/
|
|
#define swap_endian_16(val,raw) do {\
|
|
val = ((raw>>8) & 0x00ff) \
|
|
| ((raw<<8) & 0xff00);\
|
|
} while(0)
|
|
#define swap_endian_32(val,raw) do {\
|
|
val = ((raw>>24) & 0x000000ff) \
|
|
| ((raw>>8) & 0x0000ff00) \
|
|
| ((raw<<8) & 0x00ff0000) \
|
|
| ((raw<<24) & 0xff000000); \
|
|
} while(0)
|
|
#define swap_endian_16_se(val,raw) do {\
|
|
swap_endian_16(val,raw);\
|
|
val = ((val << 16) >> 16);\
|
|
} while(0)
|
|
#define swap_endian_32_se(val,raw) swap_endian_32(val,raw)
|
|
|
|
#define mem_get_ne_aligned_generic(end,sz) \
|
|
static unsigned MEM_VALUE_T mem_get_##end##sz##_aligned(const void *vmem) {\
|
|
const uint##sz##_t *mem = (const uint##sz##_t *)vmem;\
|
|
return *mem;\
|
|
}
|
|
|
|
#define mem_get_sne_aligned_generic(end,sz) \
|
|
static signed MEM_VALUE_T mem_get_s##end##sz##_aligned(const void *vmem) {\
|
|
const int##sz##_t *mem = (const int##sz##_t *)vmem;\
|
|
return *mem;\
|
|
}
|
|
|
|
#define mem_get_se_aligned_generic(end,sz) \
|
|
static unsigned MEM_VALUE_T mem_get_##end##sz##_aligned(const void *vmem) {\
|
|
const uint##sz##_t *mem = (const uint##sz##_t *)vmem;\
|
|
unsigned MEM_VALUE_T val, raw = *mem;\
|
|
swap_endian_##sz(val,raw);\
|
|
return val;\
|
|
}
|
|
|
|
#define mem_get_sse_aligned_generic(end,sz) \
|
|
static signed MEM_VALUE_T mem_get_s##end##sz##_aligned(const void *vmem) {\
|
|
const int##sz##_t *mem = (const int##sz##_t *)vmem;\
|
|
unsigned MEM_VALUE_T val, raw = *mem;\
|
|
swap_endian_##sz##_se(val,raw);\
|
|
return val;\
|
|
}
|
|
|
|
#define mem_put_ne_aligned_generic(end,sz) \
|
|
static void mem_put_##end##sz##_aligned(void *vmem, MEM_VALUE_T val) {\
|
|
uint##sz##_t *mem = (uint##sz##_t *)vmem;\
|
|
*mem = (uint##sz##_t)val;\
|
|
}
|
|
|
|
#define mem_put_se_aligned_generic(end,sz) \
|
|
static void mem_put_##end##sz##_aligned(void *vmem, MEM_VALUE_T val) {\
|
|
uint##sz##_t *mem = (uint##sz##_t *)vmem, raw;\
|
|
swap_endian_##sz(raw,val);\
|
|
*mem = (uint##sz##_t)raw;\
|
|
}
|
|
|
|
#include "config.h"
|
|
#if CONFIG_BIG_ENDIAN
|
|
#define mem_get_be_aligned_generic(sz) mem_get_ne_aligned_generic(be,sz)
|
|
#define mem_get_sbe_aligned_generic(sz) mem_get_sne_aligned_generic(be,sz)
|
|
#define mem_get_le_aligned_generic(sz) mem_get_se_aligned_generic(le,sz)
|
|
#define mem_get_sle_aligned_generic(sz) mem_get_sse_aligned_generic(le,sz)
|
|
#define mem_put_be_aligned_generic(sz) mem_put_ne_aligned_generic(be,sz)
|
|
#define mem_put_le_aligned_generic(sz) mem_put_se_aligned_generic(le,sz)
|
|
#else
|
|
#define mem_get_be_aligned_generic(sz) mem_get_se_aligned_generic(be,sz)
|
|
#define mem_get_sbe_aligned_generic(sz) mem_get_sse_aligned_generic(be,sz)
|
|
#define mem_get_le_aligned_generic(sz) mem_get_ne_aligned_generic(le,sz)
|
|
#define mem_get_sle_aligned_generic(sz) mem_get_sne_aligned_generic(le,sz)
|
|
#define mem_put_be_aligned_generic(sz) mem_put_se_aligned_generic(be,sz)
|
|
#define mem_put_le_aligned_generic(sz) mem_put_ne_aligned_generic(le,sz)
|
|
#endif
|
|
|
|
#undef mem_get_be16_aligned
|
|
#define mem_get_be16_aligned mem_ops_wrap_symbol(mem_get_be16_aligned)
|
|
mem_get_be_aligned_generic(16);
|
|
|
|
#undef mem_get_be32_aligned
|
|
#define mem_get_be32_aligned mem_ops_wrap_symbol(mem_get_be32_aligned)
|
|
mem_get_be_aligned_generic(32);
|
|
|
|
#undef mem_get_le16_aligned
|
|
#define mem_get_le16_aligned mem_ops_wrap_symbol(mem_get_le16_aligned)
|
|
mem_get_le_aligned_generic(16);
|
|
|
|
#undef mem_get_le32_aligned
|
|
#define mem_get_le32_aligned mem_ops_wrap_symbol(mem_get_le32_aligned)
|
|
mem_get_le_aligned_generic(32);
|
|
|
|
#undef mem_get_sbe16_aligned
|
|
#define mem_get_sbe16_aligned mem_ops_wrap_symbol(mem_get_sbe16_aligned)
|
|
mem_get_sbe_aligned_generic(16);
|
|
|
|
#undef mem_get_sbe32_aligned
|
|
#define mem_get_sbe32_aligned mem_ops_wrap_symbol(mem_get_sbe32_aligned)
|
|
mem_get_sbe_aligned_generic(32);
|
|
|
|
#undef mem_get_sle16_aligned
|
|
#define mem_get_sle16_aligned mem_ops_wrap_symbol(mem_get_sle16_aligned)
|
|
mem_get_sle_aligned_generic(16);
|
|
|
|
#undef mem_get_sle32_aligned
|
|
#define mem_get_sle32_aligned mem_ops_wrap_symbol(mem_get_sle32_aligned)
|
|
mem_get_sle_aligned_generic(32);
|
|
|
|
#undef mem_put_be16_aligned
|
|
#define mem_put_be16_aligned mem_ops_wrap_symbol(mem_put_be16_aligned)
|
|
mem_put_be_aligned_generic(16);
|
|
|
|
#undef mem_put_be32_aligned
|
|
#define mem_put_be32_aligned mem_ops_wrap_symbol(mem_put_be32_aligned)
|
|
mem_put_be_aligned_generic(32);
|
|
|
|
#undef mem_put_le16_aligned
|
|
#define mem_put_le16_aligned mem_ops_wrap_symbol(mem_put_le16_aligned)
|
|
mem_put_le_aligned_generic(16);
|
|
|
|
#undef mem_put_le32_aligned
|
|
#define mem_put_le32_aligned mem_ops_wrap_symbol(mem_put_le32_aligned)
|
|
mem_put_le_aligned_generic(32);
|
|
|
|
#undef mem_get_ne_aligned_generic
|
|
#undef mem_get_se_aligned_generic
|
|
#undef mem_get_sne_aligned_generic
|
|
#undef mem_get_sse_aligned_generic
|
|
#undef mem_put_ne_aligned_generic
|
|
#undef mem_put_se_aligned_generic
|
|
#undef swap_endian_16
|
|
#undef swap_endian_32
|
|
#undef swap_endian_16_se
|
|
#undef swap_endian_32_se
|