mirror of https://github.com/FFmpeg/FFmpeg.git
* commit '3c650efb81aaa3b395ba4606ee68a47ee4efb57b': dsputil: Move draw_edges() to mpegvideoencdsp Conflicts: libavcodec/mpegvideo_enc.c libavcodec/x86/Makefile libavcodec/x86/dsputil_init.c libavcodec/x86/dsputil_mmx.c libavcodec/x86/dsputil_x86.h Merged-by: Michael Niedermayer <michaelni@gmx.at>pull/76/merge
Michael Niedermayer
11 years ago
commit
3790801f9c
16 changed files with 206 additions and 240 deletions
@ -1,150 +0,0 @@ |
||||
/*
|
||||
* MMX optimized DSP utils |
||||
* Copyright (c) 2000, 2001 Fabrice Bellard |
||||
* Copyright (c) 2002-2004 Michael Niedermayer <michaelni@gmx.at> |
||||
* |
||||
* 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 |
||||
* |
||||
* MMX optimization by Nick Kurshev <nickols_k@mail.ru> |
||||
*/ |
||||
|
||||
#include "config.h" |
||||
#include "libavutil/avassert.h" |
||||
#include "libavutil/cpu.h" |
||||
#include "libavutil/x86/asm.h" |
||||
#include "libavcodec/pixels.h" |
||||
#include "libavcodec/videodsp.h" |
||||
#include "dsputil_x86.h" |
||||
#include "inline_asm.h" |
||||
|
||||
#if HAVE_INLINE_ASM |
||||
|
||||
/* Draw the edges of width 'w' of an image of size width, height
|
||||
* this MMX version can only handle w == 8 || w == 16. */ |
||||
void ff_draw_edges_mmx(uint8_t *buf, int wrap, int width, int height, |
||||
int w, int h, int sides) |
||||
{ |
||||
uint8_t *ptr, *last_line; |
||||
int i; |
||||
|
||||
last_line = buf + (height - 1) * wrap; |
||||
/* left and right */ |
||||
ptr = buf; |
||||
if (w == 8) { |
||||
__asm__ volatile ( |
||||
"1: \n\t" |
||||
"movd (%0), %%mm0 \n\t" |
||||
"punpcklbw %%mm0, %%mm0 \n\t" |
||||
"punpcklwd %%mm0, %%mm0 \n\t" |
||||
"punpckldq %%mm0, %%mm0 \n\t" |
||||
"movq %%mm0, -8(%0) \n\t" |
||||
"movq -8(%0, %2), %%mm1 \n\t" |
||||
"punpckhbw %%mm1, %%mm1 \n\t" |
||||
"punpckhwd %%mm1, %%mm1 \n\t" |
||||
"punpckhdq %%mm1, %%mm1 \n\t" |
||||
"movq %%mm1, (%0, %2) \n\t" |
||||
"add %1, %0 \n\t" |
||||
"cmp %3, %0 \n\t" |
||||
"jb 1b \n\t" |
||||
: "+r" (ptr) |
||||
: "r" ((x86_reg) wrap), "r" ((x86_reg) width), |
||||
"r" (ptr + wrap * height)); |
||||
} else if (w == 16) { |
||||
__asm__ volatile ( |
||||
"1: \n\t" |
||||
"movd (%0), %%mm0 \n\t" |
||||
"punpcklbw %%mm0, %%mm0 \n\t" |
||||
"punpcklwd %%mm0, %%mm0 \n\t" |
||||
"punpckldq %%mm0, %%mm0 \n\t" |
||||
"movq %%mm0, -8(%0) \n\t" |
||||
"movq %%mm0, -16(%0) \n\t" |
||||
"movq -8(%0, %2), %%mm1 \n\t" |
||||
"punpckhbw %%mm1, %%mm1 \n\t" |
||||
"punpckhwd %%mm1, %%mm1 \n\t" |
||||
"punpckhdq %%mm1, %%mm1 \n\t" |
||||
"movq %%mm1, (%0, %2) \n\t" |
||||
"movq %%mm1, 8(%0, %2) \n\t" |
||||
"add %1, %0 \n\t" |
||||
"cmp %3, %0 \n\t" |
||||
"jb 1b \n\t" |
||||
: "+r"(ptr) |
||||
: "r"((x86_reg)wrap), "r"((x86_reg)width), "r"(ptr + wrap * height) |
||||
); |
||||
} else { |
||||
av_assert1(w == 4); |
||||
__asm__ volatile ( |
||||
"1: \n\t" |
||||
"movd (%0), %%mm0 \n\t" |
||||
"punpcklbw %%mm0, %%mm0 \n\t" |
||||
"punpcklwd %%mm0, %%mm0 \n\t" |
||||
"movd %%mm0, -4(%0) \n\t" |
||||
"movd -4(%0, %2), %%mm1 \n\t" |
||||
"punpcklbw %%mm1, %%mm1 \n\t" |
||||
"punpckhwd %%mm1, %%mm1 \n\t" |
||||
"punpckhdq %%mm1, %%mm1 \n\t" |
||||
"movd %%mm1, (%0, %2) \n\t" |
||||
"add %1, %0 \n\t" |
||||
"cmp %3, %0 \n\t" |
||||
"jb 1b \n\t" |
||||
: "+r" (ptr) |
||||
: "r" ((x86_reg) wrap), "r" ((x86_reg) width), |
||||
"r" (ptr + wrap * height)); |
||||
} |
||||
|
||||
/* top and bottom (and hopefully also the corners) */ |
||||
if (sides & EDGE_TOP) { |
||||
for (i = 0; i < h; i += 4) { |
||||
ptr = buf - (i + 1) * wrap - w; |
||||
__asm__ volatile ( |
||||
"1: \n\t" |
||||
"movq (%1, %0), %%mm0 \n\t" |
||||
"movq %%mm0, (%0) \n\t" |
||||
"movq %%mm0, (%0, %2) \n\t" |
||||
"movq %%mm0, (%0, %2, 2) \n\t" |
||||
"movq %%mm0, (%0, %3) \n\t" |
||||
"add $8, %0 \n\t" |
||||
"cmp %4, %0 \n\t" |
||||
"jb 1b \n\t" |
||||
: "+r" (ptr) |
||||
: "r" ((x86_reg) buf - (x86_reg) ptr - w), |
||||
"r" ((x86_reg) - wrap), "r" ((x86_reg) - wrap * 3), |
||||
"r" (ptr + width + 2 * w)); |
||||
} |
||||
} |
||||
|
||||
if (sides & EDGE_BOTTOM) { |
||||
for (i = 0; i < h; i += 4) { |
||||
ptr = last_line + (i + 1) * wrap - w; |
||||
__asm__ volatile ( |
||||
"1: \n\t" |
||||
"movq (%1, %0), %%mm0 \n\t" |
||||
"movq %%mm0, (%0) \n\t" |
||||
"movq %%mm0, (%0, %2) \n\t" |
||||
"movq %%mm0, (%0, %2, 2) \n\t" |
||||
"movq %%mm0, (%0, %3) \n\t" |
||||
"add $8, %0 \n\t" |
||||
"cmp %4, %0 \n\t" |
||||
"jb 1b \n\t" |
||||
: "+r" (ptr) |
||||
: "r" ((x86_reg) last_line - (x86_reg) ptr - w), |
||||
"r" ((x86_reg) wrap), "r" ((x86_reg) wrap * 3), |
||||
"r" (ptr + width + 2 * w)); |
||||
} |
||||
} |
||||
} |
||||
|
||||
#endif /* HAVE_INLINE_ASM */ |
||||
Loading…
Reference in new issue