diff options
author | Michael Niedermayer <michaelni@gmx.at> | 2012-08-24 14:22:38 +0200 |
---|---|---|
committer | Michael Niedermayer <michaelni@gmx.at> | 2012-08-24 14:30:40 +0200 |
commit | bec180e1127f6753b5af1e6e5242020e0de12366 (patch) | |
tree | b27493eb57b5a484bde3cbc5740d9e60f06f9776 /libavcodec/x86/dnxhdenc.c | |
parent | 6b72615c32d7f3bc53a6d6075042aee626d07412 (diff) | |
parent | a1bcc76e6036e78f25cbb7323c145056cfca9d93 (diff) | |
download | ffmpeg-bec180e1127f6753b5af1e6e5242020e0de12366.tar.gz |
Merge commit 'a1bcc76e6036e78f25cbb7323c145056cfca9d93'
* commit 'a1bcc76e6036e78f25cbb7323c145056cfca9d93': (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: Michael Niedermayer <michaelni@gmx.at>
Diffstat (limited to 'libavcodec/x86/dnxhdenc.c')
-rw-r--r-- | libavcodec/x86/dnxhdenc.c | 65 |
1 files changed, 65 insertions, 0 deletions
diff --git a/libavcodec/x86/dnxhdenc.c b/libavcodec/x86/dnxhdenc.c new file mode 100644 index 0000000000..8b0c2ad225 --- /dev/null +++ b/libavcodec/x86/dnxhdenc.c @@ -0,0 +1,65 @@ +/* + * VC3/DNxHD SIMD functions + * Copyright (c) 2007 Baptiste Coudurier <baptiste dot coudurier at smartjog dot com> + * + * VC-3 encoder funded by the British Broadcasting Corporation + * + * 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/asm.h" +#include "libavcodec/dnxhdenc.h" + +#if HAVE_INLINE_ASM + +static void get_pixels_8x4_sym_sse2(DCTELEM *block, const uint8_t *pixels, int line_size) +{ + __asm__ volatile( + "pxor %%xmm5, %%xmm5 \n\t" + "movq (%0), %%xmm0 \n\t" + "add %2, %0 \n\t" + "movq (%0), %%xmm1 \n\t" + "movq (%0, %2), %%xmm2 \n\t" + "movq (%0, %2,2), %%xmm3 \n\t" + "punpcklbw %%xmm5, %%xmm0 \n\t" + "punpcklbw %%xmm5, %%xmm1 \n\t" + "punpcklbw %%xmm5, %%xmm2 \n\t" + "punpcklbw %%xmm5, %%xmm3 \n\t" + "movdqa %%xmm0, (%1) \n\t" + "movdqa %%xmm1, 16(%1) \n\t" + "movdqa %%xmm2, 32(%1) \n\t" + "movdqa %%xmm3, 48(%1) \n\t" + "movdqa %%xmm3 , 64(%1) \n\t" + "movdqa %%xmm2 , 80(%1) \n\t" + "movdqa %%xmm1 , 96(%1) \n\t" + "movdqa %%xmm0, 112(%1) \n\t" + : "+r" (pixels) + : "r" (block), "r" ((x86_reg)line_size) + ); +} + +#endif /* HAVE_INLINE_ASM */ + +void ff_dnxhdenc_init_x86(DNXHDEncContext *ctx) +{ +#if HAVE_INLINE_ASM + if (av_get_cpu_flags() & AV_CPU_FLAG_SSE2) { + if (ctx->cid_table->bit_depth == 8) + ctx->get_pixels_8x4_sym = get_pixels_8x4_sym_sse2; + } +#endif /* HAVE_INLINE_ASM */ +} |