diff options
author | Michael Niedermayer <michaelni@gmx.at> | 2011-07-10 04:28:50 +0200 |
---|---|---|
committer | Michael Niedermayer <michaelni@gmx.at> | 2011-07-10 04:28:50 +0200 |
commit | 2f56a97f2488146f209de415e3338f7e597c5719 (patch) | |
tree | dc5738f578f616d5af685391e82220452b3fbb3e /libavcodec/x86/h264_intrapred_init.c | |
parent | a7d3a51dd1efa3073cc9d419a73f709f784ce267 (diff) | |
parent | 7f7dc4fb55904e7b51b78ebca746c6755fc9770c (diff) | |
download | ffmpeg-2f56a97f2488146f209de415e3338f7e597c5719.tar.gz |
Merge remote-tracking branch 'qatar/master'
* qatar/master: (22 commits)
H.264: fix filter_mb_fast with 4:4:4 + 8x8dct
alsa: limit buffer_size to 32768 frames.
alsa: fallback to buffer_size/4 for period_size.
doc: replace @pxref by @ref where appropriate
mpeg1video: don't abort if thread_count is too high.
segafilm: add support for videos with cri adx adpcm
gxf: Fix 25 fps DV material in GXF being misdetected as 50 fps
libxvid: Add const qualifier to silence compiler warning.
H.264: improve qp_thresh check
H.264: use fill_rectangle in CABAC decoding
H.264: Remove redundant hl_motion_16/8 code
H.264: merge fill_rectangle into P-SKIP MV prediction, to match B-SKIP
H.264: faster P-SKIP decoding
H.264: av_always_inline some more functions
H.264: Add x86 assembly for 10-bit H.264 predict functions
swscale: rename uv_off/uv_off2 to uv_off_px/byte.
swscale: implement error dithering in planarCopyWrapper.
swscale: error dithering for 16/9/10-bit to 8-bit.
swscale: fix overflow in 16-bit vertical scaling.
swscale: fix crash in 8-bpc bilinear output without alpha.
...
Conflicts:
doc/developer.texi
libavdevice/alsa-audio.h
libavformat/gxf.c
libswscale/swscale.c
libswscale/swscale_internal.h
libswscale/swscale_unscaled.c
libswscale/x86/swscale_template.c
tests/ref/lavfi/pixdesc
tests/ref/lavfi/pixfmts_copy
tests/ref/lavfi/pixfmts_crop
tests/ref/lavfi/pixfmts_hflip
tests/ref/lavfi/pixfmts_null
tests/ref/lavfi/pixfmts_scale
tests/ref/lavfi/pixfmts_vflip
Merged-by: Michael Niedermayer <michaelni@gmx.at>
Diffstat (limited to 'libavcodec/x86/h264_intrapred_init.c')
-rw-r--r-- | libavcodec/x86/h264_intrapred_init.c | 58 |
1 files changed, 58 insertions, 0 deletions
diff --git a/libavcodec/x86/h264_intrapred_init.c b/libavcodec/x86/h264_intrapred_init.c index d71f71e861..2ccc584e91 100644 --- a/libavcodec/x86/h264_intrapred_init.c +++ b/libavcodec/x86/h264_intrapred_init.c @@ -43,9 +43,41 @@ PRED4x4(horizontal_down, 10, avx) #define PRED8x8(TYPE, DEPTH, OPT) \ void ff_pred8x8_ ## TYPE ## _ ## DEPTH ## _ ## OPT (uint8_t *src, int stride); +PRED8x8(dc, 10, mmxext) +PRED8x8(dc, 10, sse2) +PRED8x8(top_dc, 10, mmxext) +PRED8x8(top_dc, 10, sse2) PRED8x8(vertical, 10, sse2) PRED8x8(horizontal, 10, sse2) +#define PRED8x8L(TYPE, DEPTH, OPT)\ +void ff_pred8x8l_ ## TYPE ## _ ## DEPTH ## _ ## OPT (uint8_t *src, int has_topleft, int has_topright, int stride); + +PRED8x8L(dc, 10, sse2) +PRED8x8L(dc, 10, ssse3) +PRED8x8L(top_dc, 10, sse2) +PRED8x8L(top_dc, 10, ssse3) +PRED8x8L(vertical, 10, sse2) +PRED8x8L(vertical, 10, ssse3) +PRED8x8L(horizontal, 10, sse2) +PRED8x8L(horizontal, 10, ssse3) +PRED8x8L(down_left, 10, sse2) +PRED8x8L(down_left, 10, ssse3) +PRED8x8L(down_right, 10, sse2) +PRED8x8L(down_right, 10, ssse3) +PRED8x8L(vertical_right, 10, sse2) +PRED8x8L(vertical_right, 10, ssse3) +PRED8x8L(horizontal_up, 10, sse2) +PRED8x8L(horizontal_up, 10, ssse3) + +#define PRED16x16(TYPE, DEPTH, OPT)\ +void ff_pred16x16_ ## TYPE ## _ ## DEPTH ## _ ## OPT (uint8_t *src, int stride); + +PRED16x16(vertical, 10, mmxext) +PRED16x16(vertical, 10, sse2) +PRED16x16(horizontal, 10, mmxext) +PRED16x16(horizontal, 10, sse2) + void ff_pred16x16_vertical_mmx (uint8_t *src, int stride); void ff_pred16x16_vertical_sse (uint8_t *src, int stride); void ff_pred16x16_horizontal_mmx (uint8_t *src, int stride); @@ -253,6 +285,12 @@ void ff_h264_pred_init_x86(H264PredContext *h, int codec_id, const int bit_depth if (mm_flags & AV_CPU_FLAG_MMX2) { h->pred4x4[DC_PRED ] = ff_pred4x4_dc_10_mmxext; h->pred4x4[HOR_UP_PRED ] = ff_pred4x4_horizontal_up_10_mmxext; + + h->pred8x8[DC_PRED8x8 ] = ff_pred8x8_dc_10_mmxext; + h->pred8x8[TOP_DC_PRED8x8 ] = ff_pred8x8_top_dc_10_mmxext; + + h->pred16x16[VERT_PRED8x8 ] = ff_pred16x16_vertical_10_mmxext; + h->pred16x16[HOR_PRED8x8 ] = ff_pred16x16_horizontal_10_mmxext; } if (mm_flags & AV_CPU_FLAG_SSE2) { h->pred4x4[DIAG_DOWN_LEFT_PRED ] = ff_pred4x4_down_left_10_sse2; @@ -261,13 +299,33 @@ void ff_h264_pred_init_x86(H264PredContext *h, int codec_id, const int bit_depth h->pred4x4[VERT_RIGHT_PRED ] = ff_pred4x4_vertical_right_10_sse2; h->pred4x4[HOR_DOWN_PRED ] = ff_pred4x4_horizontal_down_10_sse2; + h->pred8x8[DC_PRED8x8 ] = ff_pred8x8_dc_10_sse2; + h->pred8x8[TOP_DC_PRED8x8 ] = ff_pred8x8_top_dc_10_sse2; h->pred8x8[VERT_PRED8x8 ] = ff_pred8x8_vertical_10_sse2; h->pred8x8[HOR_PRED8x8 ] = ff_pred8x8_horizontal_10_sse2; + + h->pred8x8l[VERT_PRED ] = ff_pred8x8l_vertical_10_sse2; + h->pred8x8l[HOR_PRED ] = ff_pred8x8l_horizontal_10_sse2; + h->pred8x8l[DC_PRED ] = ff_pred8x8l_dc_10_sse2; + h->pred8x8l[TOP_DC_PRED ] = ff_pred8x8l_top_dc_10_sse2; + h->pred8x8l[DIAG_DOWN_LEFT_PRED ] = ff_pred8x8l_down_left_10_sse2; + h->pred8x8l[DIAG_DOWN_RIGHT_PRED] = ff_pred8x8l_down_right_10_sse2; + h->pred8x8l[VERT_RIGHT_PRED ] = ff_pred8x8l_vertical_right_10_sse2; + h->pred8x8l[HOR_UP_PRED ] = ff_pred8x8l_horizontal_up_10_sse2; + + h->pred16x16[VERT_PRED8x8 ] = ff_pred16x16_vertical_10_sse2; + h->pred16x16[HOR_PRED8x8 ] = ff_pred16x16_horizontal_10_sse2; } if (mm_flags & AV_CPU_FLAG_SSSE3) { h->pred4x4[DIAG_DOWN_RIGHT_PRED] = ff_pred4x4_down_right_10_ssse3; h->pred4x4[VERT_RIGHT_PRED ] = ff_pred4x4_vertical_right_10_ssse3; h->pred4x4[HOR_DOWN_PRED ] = ff_pred4x4_horizontal_down_10_ssse3; + + h->pred8x8l[VERT_PRED ] = ff_pred8x8l_vertical_10_ssse3; + h->pred8x8l[HOR_PRED ] = ff_pred8x8l_horizontal_10_ssse3; + h->pred8x8l[DC_PRED ] = ff_pred8x8l_dc_10_ssse3; + h->pred8x8l[TOP_DC_PRED ] = ff_pred8x8l_top_dc_10_ssse3; + h->pred8x8l[DIAG_DOWN_LEFT_PRED ] = ff_pred8x8l_down_left_10_ssse3; } #if HAVE_AVX if (mm_flags & AV_CPU_FLAG_AVX) { |