b8a43bc1b5
* qatar/master: (27 commits) ac3enc: fix LOCAL_ALIGNED usage in count_mantissa_bits() ac3dsp: do not use the ff_* prefix when referencing ff_ac3_bap_bits. ac3dsp: fix loop condition in ac3_update_bap_counts_c() ARM: unbreak build ac3enc: modify mantissa bit counting to keep bap counts for all values of bap instead of just 0 to 4. ac3enc: split mantissa bit counting into a separate function. ac3enc: store per-block/channel bap pointers by reference block in a 2D array rather than in the AC3Block struct. get_bits: add av_unused tag to cache variable sws: replace all long with int. ARM: aacdec: fix constraints on inline asm ARM: remove unnecessary volatile from inline asm ARM: add "cc" clobbers to inline asm where needed ARM: improve FASTDIV asm ac3enc: use LOCAL_ALIGNED macro APIchanges: fill in git hash for av_get_pix_fmt_name (0420bd7). lavu: add av_get_pix_fmt_name() convenience function cmdutils: remove OPT_FUNC2 swscale: fix crash in bilinear scaling. vpxenc: add VP8E_SET_STATIC_THRESHOLD mapping webm: support stereo videos in matroska/webm muxer ... Conflicts: Changelog cmdutils.c cmdutils.h doc/APIchanges doc/muxers.texi ffmpeg.c ffplay.c libavcodec/ac3enc.c libavcodec/ac3enc_float.c libavcodec/avcodec.h libavcodec/get_bits.h libavcodec/libvpxenc.c libavcodec/version.h libavdevice/libdc1394.c libavformat/matroskaenc.c libavutil/avutil.h libswscale/rgb2rgb.c libswscale/swscale.c libswscale/swscale_template.c libswscale/x86/swscale_template.c Merged-by: Michael Niedermayer <michaelni@gmx.at>
85 lines
3.6 KiB
C
85 lines
3.6 KiB
C
/*
|
|
* x86-optimized AC-3 DSP utils
|
|
* Copyright (c) 2011 Justin Ruggles
|
|
*
|
|
* This file is part of FFmpeg.
|
|
*
|
|
* FFmpeg is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU Lesser General Public
|
|
* License as published by the Free Software Foundation; either
|
|
* version 2.1 of the License, or (at your option) any later version.
|
|
*
|
|
* FFmpeg is distributed in the hope that it will be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
* Lesser General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU Lesser General Public
|
|
* License along with FFmpeg; if not, write to the Free Software
|
|
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
|
|
*/
|
|
|
|
#include "libavutil/x86_cpu.h"
|
|
#include "dsputil_mmx.h"
|
|
#include "libavcodec/ac3dsp.h"
|
|
|
|
extern void ff_ac3_exponent_min_mmx (uint8_t *exp, int num_reuse_blocks, int nb_coefs);
|
|
extern void ff_ac3_exponent_min_mmxext(uint8_t *exp, int num_reuse_blocks, int nb_coefs);
|
|
extern void ff_ac3_exponent_min_sse2 (uint8_t *exp, int num_reuse_blocks, int nb_coefs);
|
|
|
|
extern int ff_ac3_max_msb_abs_int16_mmx (const int16_t *src, int len);
|
|
extern int ff_ac3_max_msb_abs_int16_mmxext(const int16_t *src, int len);
|
|
extern int ff_ac3_max_msb_abs_int16_sse2 (const int16_t *src, int len);
|
|
extern int ff_ac3_max_msb_abs_int16_ssse3 (const int16_t *src, int len);
|
|
|
|
extern void ff_ac3_lshift_int16_mmx (int16_t *src, unsigned int len, unsigned int shift);
|
|
extern void ff_ac3_lshift_int16_sse2(int16_t *src, unsigned int len, unsigned int shift);
|
|
|
|
extern void ff_ac3_rshift_int32_mmx (int32_t *src, unsigned int len, unsigned int shift);
|
|
extern void ff_ac3_rshift_int32_sse2(int32_t *src, unsigned int len, unsigned int shift);
|
|
|
|
extern void ff_float_to_fixed24_3dnow(int32_t *dst, const float *src, unsigned int len);
|
|
extern void ff_float_to_fixed24_sse (int32_t *dst, const float *src, unsigned int len);
|
|
extern void ff_float_to_fixed24_sse2 (int32_t *dst, const float *src, unsigned int len);
|
|
|
|
extern int ff_ac3_compute_mantissa_size_sse2(uint16_t mant_cnt[6][16]);
|
|
|
|
av_cold void ff_ac3dsp_init_x86(AC3DSPContext *c, int bit_exact)
|
|
{
|
|
int mm_flags = av_get_cpu_flags();
|
|
|
|
#if HAVE_YASM
|
|
if (mm_flags & AV_CPU_FLAG_MMX) {
|
|
c->ac3_exponent_min = ff_ac3_exponent_min_mmx;
|
|
c->ac3_max_msb_abs_int16 = ff_ac3_max_msb_abs_int16_mmx;
|
|
c->ac3_lshift_int16 = ff_ac3_lshift_int16_mmx;
|
|
c->ac3_rshift_int32 = ff_ac3_rshift_int32_mmx;
|
|
}
|
|
if (mm_flags & AV_CPU_FLAG_3DNOW && HAVE_AMD3DNOW) {
|
|
if (!bit_exact) {
|
|
c->float_to_fixed24 = ff_float_to_fixed24_3dnow;
|
|
}
|
|
}
|
|
if (mm_flags & AV_CPU_FLAG_MMX2 && HAVE_MMX2) {
|
|
c->ac3_exponent_min = ff_ac3_exponent_min_mmxext;
|
|
c->ac3_max_msb_abs_int16 = ff_ac3_max_msb_abs_int16_mmxext;
|
|
}
|
|
if (mm_flags & AV_CPU_FLAG_SSE && HAVE_SSE) {
|
|
c->float_to_fixed24 = ff_float_to_fixed24_sse;
|
|
}
|
|
if (mm_flags & AV_CPU_FLAG_SSE2 && HAVE_SSE) {
|
|
c->ac3_exponent_min = ff_ac3_exponent_min_sse2;
|
|
c->ac3_max_msb_abs_int16 = ff_ac3_max_msb_abs_int16_sse2;
|
|
c->float_to_fixed24 = ff_float_to_fixed24_sse2;
|
|
c->compute_mantissa_size = ff_ac3_compute_mantissa_size_sse2;
|
|
if (!(mm_flags & AV_CPU_FLAG_SSE2SLOW)) {
|
|
c->ac3_lshift_int16 = ff_ac3_lshift_int16_sse2;
|
|
c->ac3_rshift_int32 = ff_ac3_rshift_int32_sse2;
|
|
}
|
|
}
|
|
if (mm_flags & AV_CPU_FLAG_SSSE3 && HAVE_SSSE3) {
|
|
c->ac3_max_msb_abs_int16 = ff_ac3_max_msb_abs_int16_ssse3;
|
|
}
|
|
#endif
|
|
}
|