Commit bec180e1 authored by Michael Niedermayer's avatar Michael Niedermayer

Merge commit 'a1bcc76e'

* commit 'a1bcc76e': (21 commits)
  cmdutils: fix a memleak when specifying an option twice.
  x86: mpegvideo: more sensible names for optimization file and init function
  x86: mpegvideoenc: Split optimizations off into a separate file
  dnxhdenc: x86: more sensible names for optimization file and init function
  svq1/svq3: Move common code out of SVQ1 decoder-specific file
  dirac: add Comments and references to the standard
  lavr: x86: optimized 6-channel flt to fltp conversion
  lavr: x86: optimized 2-channel flt to fltp conversion
  lavr: x86: optimized 6-channel flt to s16p conversion
  lavr: x86: optimized 2-channel flt to s16p conversion
  lavr: x86: optimized 6-channel s16 to fltp conversion
  lavr: x86: optimized 2-channel s16 to fltp conversion
  lavr: x86: optimized 6-channel s16 to s16p conversion
  lavr: x86: optimized 2-channel s16 to s16p conversion
  lavr: x86: optimized 2-channel fltp to flt conversion
  lavr: x86: optimized 6-channel fltp to s16 conversion
  lavr: x86: optimized 2-channel fltp to s16 conversion
  lavr: x86: optimized 6-channel s16p to flt conversion
  lavr: x86: optimized 2-channel s16p to flt conversion
  lavr: x86: optimized 6-channel s16p to s16 conversion
  ...

Conflicts:
	libavcodec/dirac.c
	libavcodec/mpegvideo.h
	libavcodec/x86/Makefile
Merged-by: 's avatarMichael Niedermayer <michaelni@gmx.at>
parents 6b72615c a1bcc76e
......@@ -301,6 +301,7 @@ int parse_option(void *optctx, const char *opt, const char *arg,
if (po->flags & OPT_STRING) {
char *str;
str = av_strdup(arg);
// av_freep(dst);
*(char **)dst = str;
} else if (po->flags & OPT_BOOL) {
*(int *)dst = bool_val;
......
......@@ -405,14 +405,13 @@ OBJS-$(CONFIG_SUBRIP_ENCODER) += srtenc.o ass_split.o
OBJS-$(CONFIG_SUBVIEWER_DECODER) += subviewerdec.o ass.o
OBJS-$(CONFIG_SUNRAST_DECODER) += sunrast.o
OBJS-$(CONFIG_SUNRAST_ENCODER) += sunrastenc.o
OBJS-$(CONFIG_SVQ1_DECODER) += svq1dec.o svq1.o h263.o
OBJS-$(CONFIG_SVQ1_DECODER) += svq1dec.o svq1.o svq13.o h263.o
OBJS-$(CONFIG_SVQ1_ENCODER) += svq1enc.o svq1.o \
h263.o ituh263enc.o
OBJS-$(CONFIG_SVQ3_DECODER) += h264.o svq3.o \
OBJS-$(CONFIG_SVQ3_DECODER) += svq3.o svq13.o h263.o h264.o \
h264_loopfilter.o h264_direct.o \
h264_sei.o h264_ps.o h264_refs.o \
h264_cavlc.o h264_cabac.o cabac.o \
svq1dec.o svq1.o h263.o
h264_cavlc.o h264_cabac.o cabac.o
OBJS-$(CONFIG_TARGA_DECODER) += targa.o
OBJS-$(CONFIG_TARGA_ENCODER) += targaenc.o rle.o
OBJS-$(CONFIG_THEORA_DECODER) += xiph.o
......
This diff is collapsed.
......@@ -294,9 +294,8 @@ static int dnxhd_encode_init(AVCodecContext *avctx)
ctx->block_width_l2 = 3;
}
#if HAVE_MMX
ff_dnxhd_init_mmx(ctx);
#endif
if (ARCH_X86)
ff_dnxhdenc_init_x86(ctx);
ctx->m.mb_height = (avctx->height + 15) / 16;
ctx->m.mb_width = (avctx->width + 15) / 16;
......
......@@ -93,6 +93,6 @@ typedef struct DNXHDEncContext {
void (*get_pixels_8x4_sym)(DCTELEM * /*align 16*/, const uint8_t *, int);
} DNXHDEncContext;
void ff_dnxhd_init_mmx(DNXHDEncContext *ctx);
void ff_dnxhdenc_init_x86(DNXHDEncContext *ctx);
#endif /* AVCODEC_DNXHDENC_H */
......@@ -185,8 +185,8 @@ av_cold int ff_dct_common_init(MpegEncContext *s)
s->dct_unquantize_mpeg2_intra = dct_unquantize_mpeg2_intra_bitexact;
s->dct_unquantize_mpeg2_inter = dct_unquantize_mpeg2_inter_c;
#if HAVE_MMX
ff_MPV_common_init_mmx(s);
#if ARCH_X86
ff_MPV_common_init_x86(s);
#elif ARCH_ALPHA
ff_MPV_common_init_axp(s);
#elif HAVE_MMI
......
......@@ -765,7 +765,8 @@ int ff_MPV_encode_init(AVCodecContext *avctx);
int ff_MPV_encode_end(AVCodecContext *avctx);
int ff_MPV_encode_picture(AVCodecContext *avctx, AVPacket *pkt,
AVFrame *frame, int *got_packet);
void ff_MPV_common_init_mmx(MpegEncContext *s);
void ff_MPV_encode_init_x86(MpegEncContext *s);
void ff_MPV_common_init_x86(MpegEncContext *s);
void ff_MPV_common_init_axp(MpegEncContext *s);
void ff_MPV_common_init_mmi(MpegEncContext *s);
void ff_MPV_common_init_arm(MpegEncContext *s);
......
......@@ -832,6 +832,9 @@ av_cold int ff_MPV_encode_init(AVCodecContext *avctx)
if (ff_MPV_common_init(s) < 0)
return -1;
if (ARCH_X86)
ff_MPV_encode_init_x86(s);
if (!s->dct_quantize)
s->dct_quantize = ff_dct_quantize_c;
if (!s->denoise_dct)
......
/*
* SVQ1/SVQ3 decoder common code
*
* 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 <stdint.h>
#include "svq1.h"
static const uint16_t checksum_table[256] = {
0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50A5, 0x60C6, 0x70E7,
0x8108, 0x9129, 0xA14A, 0xB16B, 0xC18C, 0xD1AD, 0xE1CE, 0xF1EF,
0x1231, 0x0210, 0x3273, 0x2252, 0x52B5, 0x4294, 0x72F7, 0x62D6,
0x9339, 0x8318, 0xB37B, 0xA35A, 0xD3BD, 0xC39C, 0xF3FF, 0xE3DE,
0x2462, 0x3443, 0x0420, 0x1401, 0x64E6, 0x74C7, 0x44A4, 0x5485,
0xA56A, 0xB54B, 0x8528, 0x9509, 0xE5EE, 0xF5CF, 0xC5AC, 0xD58D,
0x3653, 0x2672, 0x1611, 0x0630, 0x76D7, 0x66F6, 0x5695, 0x46B4,
0xB75B, 0xA77A, 0x9719, 0x8738, 0xF7DF, 0xE7FE, 0xD79D, 0xC7BC,
0x48C4, 0x58E5, 0x6886, 0x78A7, 0x0840, 0x1861, 0x2802, 0x3823,
0xC9CC, 0xD9ED, 0xE98E, 0xF9AF, 0x8948, 0x9969, 0xA90A, 0xB92B,
0x5AF5, 0x4AD4, 0x7AB7, 0x6A96, 0x1A71, 0x0A50, 0x3A33, 0x2A12,
0xDBFD, 0xCBDC, 0xFBBF, 0xEB9E, 0x9B79, 0x8B58, 0xBB3B, 0xAB1A,
0x6CA6, 0x7C87, 0x4CE4, 0x5CC5, 0x2C22, 0x3C03, 0x0C60, 0x1C41,
0xEDAE, 0xFD8F, 0xCDEC, 0xDDCD, 0xAD2A, 0xBD0B, 0x8D68, 0x9D49,
0x7E97, 0x6EB6, 0x5ED5, 0x4EF4, 0x3E13, 0x2E32, 0x1E51, 0x0E70,
0xFF9F, 0xEFBE, 0xDFDD, 0xCFFC, 0xBF1B, 0xAF3A, 0x9F59, 0x8F78,
0x9188, 0x81A9, 0xB1CA, 0xA1EB, 0xD10C, 0xC12D, 0xF14E, 0xE16F,
0x1080, 0x00A1, 0x30C2, 0x20E3, 0x5004, 0x4025, 0x7046, 0x6067,
0x83B9, 0x9398, 0xA3FB, 0xB3DA, 0xC33D, 0xD31C, 0xE37F, 0xF35E,
0x02B1, 0x1290, 0x22F3, 0x32D2, 0x4235, 0x5214, 0x6277, 0x7256,
0xB5EA, 0xA5CB, 0x95A8, 0x8589, 0xF56E, 0xE54F, 0xD52C, 0xC50D,
0x34E2, 0x24C3, 0x14A0, 0x0481, 0x7466, 0x6447, 0x5424, 0x4405,
0xA7DB, 0xB7FA, 0x8799, 0x97B8, 0xE75F, 0xF77E, 0xC71D, 0xD73C,
0x26D3, 0x36F2, 0x0691, 0x16B0, 0x6657, 0x7676, 0x4615, 0x5634,
0xD94C, 0xC96D, 0xF90E, 0xE92F, 0x99C8, 0x89E9, 0xB98A, 0xA9AB,
0x5844, 0x4865, 0x7806, 0x6827, 0x18C0, 0x08E1, 0x3882, 0x28A3,
0xCB7D, 0xDB5C, 0xEB3F, 0xFB1E, 0x8BF9, 0x9BD8, 0xABBB, 0xBB9A,
0x4A75, 0x5A54, 0x6A37, 0x7A16, 0x0AF1, 0x1AD0, 0x2AB3, 0x3A92,
0xFD2E, 0xED0F, 0xDD6C, 0xCD4D, 0xBDAA, 0xAD8B, 0x9DE8, 0x8DC9,
0x7C26, 0x6C07, 0x5C64, 0x4C45, 0x3CA2, 0x2C83, 0x1CE0, 0x0CC1,
0xEF1F, 0xFF3E, 0xCF5D, 0xDF7C, 0xAF9B, 0xBFBA, 0x8FD9, 0x9FF8,
0x6E17, 0x7E36, 0x4E55, 0x5E74, 0x2E93, 0x3EB2, 0x0ED1, 0x1EF0
};
uint16_t ff_svq1_packet_checksum (const uint8_t *data, const int length, int value) {
int i;
for (i=0; i < length; i++) {
value = checksum_table[data[i] ^ (value >> 8)] ^ ((value & 0xFF) << 8);
}
return value;
}
......@@ -58,41 +58,6 @@ typedef struct svq1_pmv_s {
int y;
} svq1_pmv;
static const uint16_t checksum_table[256] = {
0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50A5, 0x60C6, 0x70E7,
0x8108, 0x9129, 0xA14A, 0xB16B, 0xC18C, 0xD1AD, 0xE1CE, 0xF1EF,
0x1231, 0x0210, 0x3273, 0x2252, 0x52B5, 0x4294, 0x72F7, 0x62D6,
0x9339, 0x8318, 0xB37B, 0xA35A, 0xD3BD, 0xC39C, 0xF3FF, 0xE3DE,
0x2462, 0x3443, 0x0420, 0x1401, 0x64E6, 0x74C7, 0x44A4, 0x5485,
0xA56A, 0xB54B, 0x8528, 0x9509, 0xE5EE, 0xF5CF, 0xC5AC, 0xD58D,
0x3653, 0x2672, 0x1611, 0x0630, 0x76D7, 0x66F6, 0x5695, 0x46B4,
0xB75B, 0xA77A, 0x9719, 0x8738, 0xF7DF, 0xE7FE, 0xD79D, 0xC7BC,
0x48C4, 0x58E5, 0x6886, 0x78A7, 0x0840, 0x1861, 0x2802, 0x3823,
0xC9CC, 0xD9ED, 0xE98E, 0xF9AF, 0x8948, 0x9969, 0xA90A, 0xB92B,
0x5AF5, 0x4AD4, 0x7AB7, 0x6A96, 0x1A71, 0x0A50, 0x3A33, 0x2A12,
0xDBFD, 0xCBDC, 0xFBBF, 0xEB9E, 0x9B79, 0x8B58, 0xBB3B, 0xAB1A,
0x6CA6, 0x7C87, 0x4CE4, 0x5CC5, 0x2C22, 0x3C03, 0x0C60, 0x1C41,
0xEDAE, 0xFD8F, 0xCDEC, 0xDDCD, 0xAD2A, 0xBD0B, 0x8D68, 0x9D49,
0x7E97, 0x6EB6, 0x5ED5, 0x4EF4, 0x3E13, 0x2E32, 0x1E51, 0x0E70,
0xFF9F, 0xEFBE, 0xDFDD, 0xCFFC, 0xBF1B, 0xAF3A, 0x9F59, 0x8F78,
0x9188, 0x81A9, 0xB1CA, 0xA1EB, 0xD10C, 0xC12D, 0xF14E, 0xE16F,
0x1080, 0x00A1, 0x30C2, 0x20E3, 0x5004, 0x4025, 0x7046, 0x6067,
0x83B9, 0x9398, 0xA3FB, 0xB3DA, 0xC33D, 0xD31C, 0xE37F, 0xF35E,
0x02B1, 0x1290, 0x22F3, 0x32D2, 0x4235, 0x5214, 0x6277, 0x7256,
0xB5EA, 0xA5CB, 0x95A8, 0x8589, 0xF56E, 0xE54F, 0xD52C, 0xC50D,
0x34E2, 0x24C3, 0x14A0, 0x0481, 0x7466, 0x6447, 0x5424, 0x4405,
0xA7DB, 0xB7FA, 0x8799, 0x97B8, 0xE75F, 0xF77E, 0xC71D, 0xD73C,
0x26D3, 0x36F2, 0x0691, 0x16B0, 0x6657, 0x7676, 0x4615, 0x5634,
0xD94C, 0xC96D, 0xF90E, 0xE92F, 0x99C8, 0x89E9, 0xB98A, 0xA9AB,
0x5844, 0x4865, 0x7806, 0x6827, 0x18C0, 0x08E1, 0x3882, 0x28A3,
0xCB7D, 0xDB5C, 0xEB3F, 0xFB1E, 0x8BF9, 0x9BD8, 0xABBB, 0xBB9A,
0x4A75, 0x5A54, 0x6A37, 0x7A16, 0x0AF1, 0x1AD0, 0x2AB3, 0x3A92,
0xFD2E, 0xED0F, 0xDD6C, 0xCD4D, 0xBDAA, 0xAD8B, 0x9DE8, 0x8DC9,
0x7C26, 0x6C07, 0x5C64, 0x4C45, 0x3CA2, 0x2C83, 0x1CE0, 0x0CC1,
0xEF1F, 0xFF3E, 0xCF5D, 0xDF7C, 0xAF9B, 0xBFBA, 0x8FD9, 0x9FF8,
0x6E17, 0x7E36, 0x4E55, 0x5E74, 0x2E93, 0x3EB2, 0x0ED1, 0x1EF0
};
static const uint8_t string_table[256] = {
0x00, 0xD5, 0x7F, 0xAA, 0xFE, 0x2B, 0x81, 0x54,
0x29, 0xFC, 0x56, 0x83, 0xD7, 0x02, 0xA8, 0x7D,
......@@ -524,16 +489,6 @@ static int svq1_decode_delta_block (MpegEncContext *s, GetBitContext *bitbuf,
return result;
}
uint16_t ff_svq1_packet_checksum (const uint8_t *data, const int length, int value) {
int i;
for (i=0; i < length; i++) {
value = checksum_table[data[i] ^ (value >> 8)] ^ ((value & 0xFF) << 8);
}
return value;
}
static void svq1_parse_string (GetBitContext *bitbuf, uint8_t *out) {
uint8_t seed;
int i;
......
......@@ -14,7 +14,7 @@ MMX-OBJS += x86/dsputil_mmx.o \
MMX-OBJS-$(CONFIG_AAC_DECODER) += x86/sbrdsp_init.o
MMX-OBJS-$(CONFIG_AC3DSP) += x86/ac3dsp_init.o
MMX-OBJS-$(CONFIG_CAVS_DECODER) += x86/cavsdsp_mmx.o
MMX-OBJS-$(CONFIG_DNXHD_ENCODER) += x86/dnxhd_mmx.o
MMX-OBJS-$(CONFIG_DNXHD_ENCODER) += x86/dnxhdenc.o
MMX-OBJS-$(CONFIG_DWT) += x86/snowdsp_mmx.o \
x86/dwt.o
MMX-OBJS-$(CONFIG_ENCODERS) += x86/dsputilenc_mmx.o
......@@ -24,7 +24,8 @@ MMX-OBJS-$(CONFIG_H264DSP) += x86/h264dsp_init.o
MMX-OBJS-$(CONFIG_H264PRED) += x86/h264_intrapred_init.o
MMX-OBJS-$(CONFIG_LPC) += x86/lpc_mmx.o
MMX-OBJS-$(CONFIG_MPEGAUDIODSP) += x86/mpegaudiodec_mmx.o
MMX-OBJS-$(CONFIG_MPEGVIDEO) += x86/mpegvideo_mmx.o
MMX-OBJS-$(CONFIG_MPEGVIDEO) += x86/mpegvideo.o
MMX-OBJS-$(CONFIG_MPEGVIDEOENC) += x86/mpegvideoenc.o
MMX-OBJS-$(CONFIG_PNG_DECODER) += x86/pngdsp_init.o
MMX-OBJS-$(CONFIG_PRORES_DECODER) += x86/proresdsp_init.o
MMX-OBJS-$(CONFIG_PRORES_LGPL_DECODER) += x86/proresdsp_init.o
......
......@@ -54,7 +54,7 @@ static void get_pixels_8x4_sym_sse2(DCTELEM *block, const uint8_t *pixels, int l
#endif /* HAVE_INLINE_ASM */
void ff_dnxhd_init_mmx(DNXHDEncContext *ctx)
void ff_dnxhdenc_init_x86(DNXHDEncContext *ctx)
{
#if HAVE_INLINE_ASM
if (av_get_cpu_flags() & AV_CPU_FLAG_SSE2) {
......
/*
* The simplest mpeg encoder (well, it was the simplest!)
* Copyright (c) 2000,2001 Fabrice Bellard
*
* Optimized for ia32 CPUs by Nick Kurshev <nickols_k@mail.ru>
* h263, mpeg1, mpeg2 dequantizer & draw_edges by Michael Niedermayer <michaelni@gmx.at>
*
......@@ -31,9 +28,6 @@
#if HAVE_INLINE_ASM
extern uint16_t ff_inv_zigzag_direct16[64];
static void dct_unquantize_h263_intra_mmx(MpegEncContext *s,
DCTELEM *block, int n, int qscale)
{
......@@ -588,56 +582,14 @@ static void denoise_dct_sse2(MpegEncContext *s, DCTELEM *block){
);
}
#if HAVE_SSSE3
#define HAVE_SSSE3_BAK
#endif
#undef HAVE_SSSE3
#define HAVE_SSSE3 0
#undef HAVE_SSE2
#undef HAVE_MMXEXT
#define HAVE_SSE2 0
#define HAVE_MMXEXT 0
#define RENAME(a) a ## _MMX
#define RENAMEl(a) a ## _mmx
#include "mpegvideo_mmx_template.c"
#undef HAVE_MMXEXT
#define HAVE_MMXEXT 1
#undef RENAME
#undef RENAMEl
#define RENAME(a) a ## _MMX2
#define RENAMEl(a) a ## _mmx2
#include "mpegvideo_mmx_template.c"
#undef HAVE_SSE2
#define HAVE_SSE2 1
#undef RENAME
#undef RENAMEl
#define RENAME(a) a ## _SSE2
#define RENAMEl(a) a ## _sse2
#include "mpegvideo_mmx_template.c"
#ifdef HAVE_SSSE3_BAK
#undef HAVE_SSSE3
#define HAVE_SSSE3 1
#undef RENAME
#undef RENAMEl
#define RENAME(a) a ## _SSSE3
#define RENAMEl(a) a ## _sse2
#include "mpegvideo_mmx_template.c"
#endif
#endif /* HAVE_INLINE_ASM */
void ff_MPV_common_init_mmx(MpegEncContext *s)
void ff_MPV_common_init_x86(MpegEncContext *s)
{
#if HAVE_INLINE_ASM
int mm_flags = av_get_cpu_flags();
if (mm_flags & AV_CPU_FLAG_MMX) {
const int dct_algo = s->avctx->dct_algo;
s->dct_unquantize_h263_intra = dct_unquantize_h263_intra_mmx;
s->dct_unquantize_h263_inter = dct_unquantize_h263_inter_mmx;
s->dct_unquantize_mpeg1_intra = dct_unquantize_mpeg1_intra_mmx;
......@@ -651,21 +603,6 @@ void ff_MPV_common_init_mmx(MpegEncContext *s)
} else {
s->denoise_dct= denoise_dct_mmx;
}
if(dct_algo==FF_DCT_AUTO || dct_algo==FF_DCT_MMX){
#if HAVE_SSSE3
if(mm_flags & AV_CPU_FLAG_SSSE3){
s->dct_quantize= dct_quantize_SSSE3;
} else
#endif
if(mm_flags & AV_CPU_FLAG_SSE2){
s->dct_quantize= dct_quantize_SSE2;
} else if (mm_flags & AV_CPU_FLAG_MMXEXT) {
s->dct_quantize= dct_quantize_MMX2;
} else {
s->dct_quantize= dct_quantize_MMX;
}
}
}
#endif /* HAVE_INLINE_ASM */
}
/*
* The simplest mpeg encoder (well, it was the simplest!)
* Copyright (c) 2000,2001 Fabrice Bellard
*
* 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/cpu.h"
#include "libavutil/x86/asm.h"
#include "libavcodec/avcodec.h"
#include "libavcodec/dsputil.h"
#include "libavcodec/mpegvideo.h"
#include "dsputil_mmx.h"
#if HAVE_INLINE_ASM
extern uint16_t ff_inv_zigzag_direct16[64];
#if HAVE_SSSE3
#define HAVE_SSSE3_BAK
#endif
#undef HAVE_SSSE3
#define HAVE_SSSE3 0
#undef HAVE_SSE2
#undef HAVE_MMXEXT
#define HAVE_SSE2 0
#define HAVE_MMXEXT 0
#define RENAME(a) a ## _MMX
#define RENAMEl(a) a ## _mmx
#include "mpegvideoenc_template.c"
#undef HAVE_MMXEXT
#define HAVE_MMXEXT 1
#undef RENAME
#undef RENAMEl
#define RENAME(a) a ## _MMX2
#define RENAMEl(a) a ## _mmx2
#include "mpegvideoenc_template.c"
#undef HAVE_SSE2
#define HAVE_SSE2 1
#undef RENAME
#undef RENAMEl
#define RENAME(a) a ## _SSE2
#define RENAMEl(a) a ## _sse2
#include "mpegvideoenc_template.c"
#ifdef HAVE_SSSE3_BAK
#undef HAVE_SSSE3
#define HAVE_SSSE3 1
#undef RENAME
#undef RENAMEl
#define RENAME(a) a ## _SSSE3
#define RENAMEl(a) a ## _sse2
#include "mpegvideoenc_template.c"
#endif
#endif /* HAVE_INLINE_ASM */
void ff_MPV_encode_init_x86(MpegEncContext *s)
{
#if HAVE_INLINE_ASM
int mm_flags = av_get_cpu_flags();
const int dct_algo = s->avctx->dct_algo;
if (dct_algo == FF_DCT_AUTO || dct_algo == FF_DCT_MMX) {
#if HAVE_SSSE3
if (mm_flags & AV_CPU_FLAG_SSSE3) {
s->dct_quantize = dct_quantize_SSSE3;
} else
#endif
if (mm_flags & AV_CPU_FLAG_SSE2) {
s->dct_quantize = dct_quantize_SSE2;
} else if (mm_flags & AV_CPU_FLAG_MMXEXT) {
s->dct_quantize = dct_quantize_MMX2;
} else {
s->dct_quantize = dct_quantize_MMX;
}
}
#endif /* HAVE_INLINE_ASM */
}
This diff is collapsed.
This diff is collapsed.
......@@ -33,3 +33,9 @@
psrad m%1, 16
%endif
%endmacro
%macro DEINT2_PS 3 ; src0/even dst, src1/odd dst, temp
shufps m%3, m%1, m%2, q3131
shufps m%1, m%2, q2020
SWAP %2,%3
%endmacro
......@@ -637,3 +637,15 @@
%rotate 1
%endrep
%endmacro
%macro PMOVSXWD 2; dst, src
%if cpuflag(sse4)
pmovsxwd %1, %2
%else
%ifnidn %1, %2
mova %1, %2
%endif
punpcklwd %1, %1
psrad %1, 16
%endif
%endmacro
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment