e776ee8f29
* qatar/master: lavr: fix handling of custom mix matrices fate: force pix_fmt in lagarith-rgb32 test fate: add tests for lagarith lossless video codec. ARMv6: vp8: fix stack allocation with Apple's assembler ARM: vp56: allow inline asm to build with clang fft: 3dnow: fix register name typo in DECL_IMDCT macro x86: dct32: port to cpuflags x86: build: replace mmx2 by mmxext Revert "wmapro: prevent division by zero when sample rate is unspecified" wmapro: prevent division by zero when sample rate is unspecified lagarith: fix color plane inversion for YUY2 output. lagarith: pad RGB buffer by 1 byte. dsputil: make add_hfyu_left_prediction_sse4() support unaligned src. Conflicts: doc/APIchanges libavcodec/lagarith.c libavfilter/x86/gradfun.c libavutil/cpu.h libavutil/version.h libswscale/utils.c libswscale/version.h libswscale/x86/yuv2rgb.c Merged-by: Michael Niedermayer <michaelni@gmx.at>
94 lines
4.1 KiB
C
94 lines
4.1 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_mmx2 (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]);
|
|
|
|
extern void ff_ac3_extract_exponents_3dnow(uint8_t *exp, int32_t *coef, int nb_coefs);
|
|
extern void ff_ac3_extract_exponents_sse2 (uint8_t *exp, int32_t *coef, int nb_coefs);
|
|
extern void ff_ac3_extract_exponents_ssse3(uint8_t *exp, int32_t *coef, int nb_coefs);
|
|
|
|
av_cold void ff_ac3dsp_init_x86(AC3DSPContext *c, int bit_exact)
|
|
{
|
|
#if HAVE_YASM
|
|
int mm_flags = av_get_cpu_flags();
|
|
|
|
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) {
|
|
c->extract_exponents = ff_ac3_extract_exponents_3dnow;
|
|
if (!bit_exact) {
|
|
c->float_to_fixed24 = ff_float_to_fixed24_3dnow;
|
|
}
|
|
}
|
|
if (mm_flags & AV_CPU_FLAG_MMXEXT && HAVE_MMXEXT) {
|
|
c->ac3_exponent_min = ff_ac3_exponent_min_mmxext;
|
|
c->ac3_max_msb_abs_int16 = ff_ac3_max_msb_abs_int16_mmx2;
|
|
}
|
|
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;
|
|
c->extract_exponents = ff_ac3_extract_exponents_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;
|
|
if (!(mm_flags & AV_CPU_FLAG_ATOM)) {
|
|
c->extract_exponents = ff_ac3_extract_exponents_ssse3;
|
|
}
|
|
}
|
|
#endif
|
|
}
|