c17b62e1bd
Change bitreading functions to use a larger window which is refilled less often. This makes it cheap enough to do bounds checking each time the window is refilled, which avoids the need to copy the input into a large circular buffer. This uses less memory and speeds up the total decode time by 1.6% on an ARM11, 2.8% on a Cortex A8, and 2.2% on x86-32, but less than 1% on x86-64. Inlining vp8dx_bool_decoder_fill() has a big penalty on x86-32, as does moving the refill loop to the front of vp8dx_decode_bool(). However, having the refill loop between computation of the split values and the branch in vp8_decode_mb_tokens() is a big win on ARM (presumably due to memory latency and code size: refilling after normalization duplicates the code in the DECODE_AND_BRANCH_IF_ZERO and DECODE_AND_LOOP_IF_ZERO cases. Unfortunately, refilling at the end of vp8dx_bool_decoder_fill() and at the beginning of each decode step in vp8_decode_mb_tokens() means the latter requires an extra refill at the end. Platform-specific versions could avoid the problem, but would require most of detokenize.c to be duplicated. Change-Id: I16c782a63376f2a15b78f8086d899b987204c1c7
38 lines
1.1 KiB
C
38 lines
1.1 KiB
C
/*
|
|
* Copyright (c) 2010 The VP8 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_ports/config.h"
|
|
#include "dequantize.h"
|
|
#include "onyxd_int.h"
|
|
|
|
extern void vp8_arch_x86_decode_init(VP8D_COMP *pbi);
|
|
|
|
void vp8_dmachine_specific_config(VP8D_COMP *pbi)
|
|
{
|
|
// Pure C:
|
|
#if CONFIG_RUNTIME_CPU_DETECT
|
|
pbi->mb.rtcd = &pbi->common.rtcd;
|
|
pbi->dequant.block = vp8_dequantize_b_c;
|
|
pbi->dequant.idct = vp8_dequant_idct_c;
|
|
pbi->dequant.idct_dc = vp8_dequant_dc_idct_c;
|
|
pbi->dboolhuff.start = vp8dx_start_decode_c;
|
|
pbi->dboolhuff.fill = vp8dx_bool_decoder_fill_c;
|
|
#if 0 //For use with RTCD, when implemented
|
|
pbi->dboolhuff.debool = vp8dx_decode_bool_c;
|
|
pbi->dboolhuff.devalue = vp8dx_decode_value_c;
|
|
#endif
|
|
#endif
|
|
|
|
#if ARCH_X86 || ARCH_X86_64
|
|
vp8_arch_x86_decode_init(pbi);
|
|
#endif
|
|
}
|