mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-12-12 19:18:44 +02:00
59eb12faff
* qatar/master: (30 commits) AVOptions: make default_val a union, as proposed in AVOption2. arm/h264pred: add missing argument type. h264dsp_mmx: place bracket outside #if/#endif block. lavf/utils: fix ff_interleave_compare_dts corner case. fate: add 10-bit H264 tests. h264: do not print "too many references" warning for intra-only. Enable decoding of high bit depth h264. Adds 8-, 9- and 10-bit versions of some of the functions used by the h264 decoder. Add support for higher QP values in h264. Add the notion of pixel size in h264 related functions. Make the h264 loop filter bit depth aware. Template dsputil_template.c with respect to pixel size, etc. Template h264idct_template.c with respect to pixel size, etc. Preparatory patch for high bit depth h264 decoding support. Move some functions in dsputil.c into a new file dsputil_template.c. Move the functions in h264idct into a new file h264idct_template.c. Move the functions in h264pred.c into a new file h264pred_template.c. Preparatory patch for high bit depth h264 decoding support. Add pixel formats for 9- and 10-bit yuv420p. Choose h264 chroma dc dequant function dynamically. ... Conflicts: doc/APIchanges ffmpeg.c ffplay.c libavcodec/alpha/dsputil_alpha.c libavcodec/arm/dsputil_init_arm.c libavcodec/arm/dsputil_init_armv6.c libavcodec/arm/dsputil_init_neon.c libavcodec/arm/dsputil_iwmmxt.c libavcodec/arm/h264pred_init_arm.c libavcodec/bfin/dsputil_bfin.c libavcodec/dsputil.c libavcodec/h264.c libavcodec/h264.h libavcodec/h264_cabac.c libavcodec/h264_cavlc.c libavcodec/h264_loopfilter.c libavcodec/h264_ps.c libavcodec/h264_refs.c libavcodec/h264dsp.c libavcodec/h264idct.c libavcodec/h264pred.c libavcodec/mlib/dsputil_mlib.c libavcodec/options.c libavcodec/ppc/dsputil_altivec.c libavcodec/ppc/dsputil_ppc.c libavcodec/ppc/h264_altivec.c libavcodec/ps2/dsputil_mmi.c libavcodec/sh4/dsputil_align.c libavcodec/sh4/dsputil_sh4.c libavcodec/sparc/dsputil_vis.c libavcodec/utils.c libavcodec/version.h libavcodec/x86/dsputil_mmx.c libavformat/options.c libavformat/utils.c libavutil/pixfmt.h libswscale/swscale.c libswscale/swscale_internal.h libswscale/swscale_template.c tests/ref/seek/lavf_avi Merged-by: Michael Niedermayer <michaelni@gmx.at>
211 lines
8.9 KiB
C
211 lines
8.9 KiB
C
/*
|
|
* iWMMXt optimized DSP utils
|
|
* Copyright (c) 2004 AGAWA Koji
|
|
*
|
|
* 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 "libavcodec/dsputil.h"
|
|
|
|
#define DEF(x, y) x ## _no_rnd_ ## y ##_iwmmxt
|
|
#define SET_RND(regd) __asm__ volatile ("mov r12, #1 \n\t tbcsth " #regd ", r12":::"r12");
|
|
#define WAVG2B "wavg2b"
|
|
#include "dsputil_iwmmxt_rnd_template.c"
|
|
#undef DEF
|
|
#undef SET_RND
|
|
#undef WAVG2B
|
|
|
|
#define DEF(x, y) x ## _ ## y ##_iwmmxt
|
|
#define SET_RND(regd) __asm__ volatile ("mov r12, #2 \n\t tbcsth " #regd ", r12":::"r12");
|
|
#define WAVG2B "wavg2br"
|
|
#include "dsputil_iwmmxt_rnd_template.c"
|
|
#undef DEF
|
|
#undef SET_RND
|
|
#undef WAVG2BR
|
|
|
|
// need scheduling
|
|
#define OP(AVG) \
|
|
__asm__ volatile ( \
|
|
/* alignment */ \
|
|
"and r12, %[pixels], #7 \n\t" \
|
|
"bic %[pixels], %[pixels], #7 \n\t" \
|
|
"tmcr wcgr1, r12 \n\t" \
|
|
\
|
|
"wldrd wr0, [%[pixels]] \n\t" \
|
|
"wldrd wr1, [%[pixels], #8] \n\t" \
|
|
"add %[pixels], %[pixels], %[line_size] \n\t" \
|
|
"walignr1 wr4, wr0, wr1 \n\t" \
|
|
\
|
|
"1: \n\t" \
|
|
\
|
|
"wldrd wr2, [%[pixels]] \n\t" \
|
|
"wldrd wr3, [%[pixels], #8] \n\t" \
|
|
"add %[pixels], %[pixels], %[line_size] \n\t" \
|
|
"pld [%[pixels]] \n\t" \
|
|
"walignr1 wr5, wr2, wr3 \n\t" \
|
|
AVG " wr6, wr4, wr5 \n\t" \
|
|
"wstrd wr6, [%[block]] \n\t" \
|
|
"add %[block], %[block], %[line_size] \n\t" \
|
|
\
|
|
"wldrd wr0, [%[pixels]] \n\t" \
|
|
"wldrd wr1, [%[pixels], #8] \n\t" \
|
|
"add %[pixels], %[pixels], %[line_size] \n\t" \
|
|
"walignr1 wr4, wr0, wr1 \n\t" \
|
|
"pld [%[pixels]] \n\t" \
|
|
AVG " wr6, wr4, wr5 \n\t" \
|
|
"wstrd wr6, [%[block]] \n\t" \
|
|
"add %[block], %[block], %[line_size] \n\t" \
|
|
\
|
|
"subs %[h], %[h], #2 \n\t" \
|
|
"bne 1b \n\t" \
|
|
: [block]"+r"(block), [pixels]"+r"(pixels), [h]"+r"(h) \
|
|
: [line_size]"r"(line_size) \
|
|
: "memory", "r12");
|
|
void put_pixels8_y2_iwmmxt(uint8_t *block, const uint8_t *pixels, const int line_size, int h)
|
|
{
|
|
OP("wavg2br");
|
|
}
|
|
void put_no_rnd_pixels8_y2_iwmmxt(uint8_t *block, const uint8_t *pixels, const int line_size, int h)
|
|
{
|
|
OP("wavg2b");
|
|
}
|
|
#undef OP
|
|
|
|
void add_pixels_clamped_iwmmxt(const DCTELEM *block, uint8_t *pixels, int line_size)
|
|
{
|
|
uint8_t *pixels2 = pixels + line_size;
|
|
|
|
__asm__ volatile (
|
|
"mov r12, #4 \n\t"
|
|
"1: \n\t"
|
|
"pld [%[pixels], %[line_size2]] \n\t"
|
|
"pld [%[pixels2], %[line_size2]] \n\t"
|
|
"wldrd wr4, [%[pixels]] \n\t"
|
|
"wldrd wr5, [%[pixels2]] \n\t"
|
|
"pld [%[block], #32] \n\t"
|
|
"wunpckelub wr6, wr4 \n\t"
|
|
"wldrd wr0, [%[block]] \n\t"
|
|
"wunpckehub wr7, wr4 \n\t"
|
|
"wldrd wr1, [%[block], #8] \n\t"
|
|
"wunpckelub wr8, wr5 \n\t"
|
|
"wldrd wr2, [%[block], #16] \n\t"
|
|
"wunpckehub wr9, wr5 \n\t"
|
|
"wldrd wr3, [%[block], #24] \n\t"
|
|
"add %[block], %[block], #32 \n\t"
|
|
"waddhss wr10, wr0, wr6 \n\t"
|
|
"waddhss wr11, wr1, wr7 \n\t"
|
|
"waddhss wr12, wr2, wr8 \n\t"
|
|
"waddhss wr13, wr3, wr9 \n\t"
|
|
"wpackhus wr14, wr10, wr11 \n\t"
|
|
"wpackhus wr15, wr12, wr13 \n\t"
|
|
"wstrd wr14, [%[pixels]] \n\t"
|
|
"add %[pixels], %[pixels], %[line_size2] \n\t"
|
|
"subs r12, r12, #1 \n\t"
|
|
"wstrd wr15, [%[pixels2]] \n\t"
|
|
"add %[pixels2], %[pixels2], %[line_size2] \n\t"
|
|
"bne 1b \n\t"
|
|
: [block]"+r"(block), [pixels]"+r"(pixels), [pixels2]"+r"(pixels2)
|
|
: [line_size2]"r"(line_size << 1)
|
|
: "cc", "memory", "r12");
|
|
}
|
|
|
|
static void clear_blocks_iwmmxt(DCTELEM *blocks)
|
|
{
|
|
__asm__ volatile(
|
|
"wzero wr0 \n\t"
|
|
"mov r1, #(128 * 6 / 32) \n\t"
|
|
"1: \n\t"
|
|
"wstrd wr0, [%0] \n\t"
|
|
"wstrd wr0, [%0, #8] \n\t"
|
|
"wstrd wr0, [%0, #16] \n\t"
|
|
"wstrd wr0, [%0, #24] \n\t"
|
|
"subs r1, r1, #1 \n\t"
|
|
"add %0, %0, #32 \n\t"
|
|
"bne 1b \n\t"
|
|
: "+r"(blocks)
|
|
:
|
|
: "r1"
|
|
);
|
|
}
|
|
|
|
static void nop(uint8_t *block, const uint8_t *pixels, int line_size, int h)
|
|
{
|
|
return;
|
|
}
|
|
|
|
/* A run time test is not simple. If this file is compiled in
|
|
* then we should install the functions
|
|
*/
|
|
|
|
void ff_dsputil_init_iwmmxt(DSPContext* c, AVCodecContext *avctx)
|
|
{
|
|
int mm_flags = AV_CPU_FLAG_IWMMXT; /* multimedia extension flags */
|
|
const int high_bit_depth = avctx->codec_id == CODEC_ID_H264 && avctx->bits_per_raw_sample > 8;
|
|
|
|
if (avctx->dsp_mask) {
|
|
if (avctx->dsp_mask & AV_CPU_FLAG_FORCE)
|
|
mm_flags |= (avctx->dsp_mask & 0xffff);
|
|
else
|
|
mm_flags &= ~(avctx->dsp_mask & 0xffff);
|
|
}
|
|
|
|
if (!(mm_flags & AV_CPU_FLAG_IWMMXT)) return;
|
|
|
|
c->add_pixels_clamped = add_pixels_clamped_iwmmxt;
|
|
|
|
if (!high_bit_depth) {
|
|
c->clear_blocks = clear_blocks_iwmmxt;
|
|
|
|
c->put_pixels_tab[0][0] = put_pixels16_iwmmxt;
|
|
c->put_pixels_tab[0][1] = put_pixels16_x2_iwmmxt;
|
|
c->put_pixels_tab[0][2] = put_pixels16_y2_iwmmxt;
|
|
c->put_pixels_tab[0][3] = put_pixels16_xy2_iwmmxt;
|
|
c->put_no_rnd_pixels_tab[0][0] = put_pixels16_iwmmxt;
|
|
c->put_no_rnd_pixels_tab[0][1] = put_no_rnd_pixels16_x2_iwmmxt;
|
|
c->put_no_rnd_pixels_tab[0][2] = put_no_rnd_pixels16_y2_iwmmxt;
|
|
c->put_no_rnd_pixels_tab[0][3] = put_no_rnd_pixels16_xy2_iwmmxt;
|
|
|
|
c->put_pixels_tab[1][0] = put_pixels8_iwmmxt;
|
|
c->put_pixels_tab[1][1] = put_pixels8_x2_iwmmxt;
|
|
c->put_pixels_tab[1][2] = put_pixels8_y2_iwmmxt;
|
|
c->put_pixels_tab[1][3] = put_pixels8_xy2_iwmmxt;
|
|
c->put_no_rnd_pixels_tab[1][0] = put_pixels8_iwmmxt;
|
|
c->put_no_rnd_pixels_tab[1][1] = put_no_rnd_pixels8_x2_iwmmxt;
|
|
c->put_no_rnd_pixels_tab[1][2] = put_no_rnd_pixels8_y2_iwmmxt;
|
|
c->put_no_rnd_pixels_tab[1][3] = put_no_rnd_pixels8_xy2_iwmmxt;
|
|
|
|
c->avg_pixels_tab[0][0] = avg_pixels16_iwmmxt;
|
|
c->avg_pixels_tab[0][1] = avg_pixels16_x2_iwmmxt;
|
|
c->avg_pixels_tab[0][2] = avg_pixels16_y2_iwmmxt;
|
|
c->avg_pixels_tab[0][3] = avg_pixels16_xy2_iwmmxt;
|
|
c->avg_no_rnd_pixels_tab[0][0] = avg_pixels16_iwmmxt;
|
|
c->avg_no_rnd_pixels_tab[0][1] = avg_no_rnd_pixels16_x2_iwmmxt;
|
|
c->avg_no_rnd_pixels_tab[0][2] = avg_no_rnd_pixels16_y2_iwmmxt;
|
|
c->avg_no_rnd_pixels_tab[0][3] = avg_no_rnd_pixels16_xy2_iwmmxt;
|
|
|
|
c->avg_pixels_tab[1][0] = avg_pixels8_iwmmxt;
|
|
c->avg_pixels_tab[1][1] = avg_pixels8_x2_iwmmxt;
|
|
c->avg_pixels_tab[1][2] = avg_pixels8_y2_iwmmxt;
|
|
c->avg_pixels_tab[1][3] = avg_pixels8_xy2_iwmmxt;
|
|
c->avg_no_rnd_pixels_tab[1][0] = avg_no_rnd_pixels8_iwmmxt;
|
|
c->avg_no_rnd_pixels_tab[1][1] = avg_no_rnd_pixels8_x2_iwmmxt;
|
|
c->avg_no_rnd_pixels_tab[1][2] = avg_no_rnd_pixels8_y2_iwmmxt;
|
|
c->avg_no_rnd_pixels_tab[1][3] = avg_no_rnd_pixels8_xy2_iwmmxt;
|
|
}
|
|
}
|