Commit Graph
100 Commits
Author SHA1 Message Date
James Almer 864f9326fb x86/vf_noise: move asm code to a separate file
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-17 00:44:35 -03:00
James Almer ccd04f4320 fate: add test for vp90-2-trac3849.webm
Regression test for the bug from trac ticket #3849 fixed in commit 14e30255

Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-12 19:45:25 -03:00
James Almer 59d8050df1 avfilter: remove obsolete FF_API_DRAWTEXT_OLD_TIMELINE cruft 2014-10-12 15:54:58 -03:00
James Almer 5402d1bce5 float_dsp-test: allow forcing cpuflags
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-10 13:51:51 -03:00
James AlmerandMartin Storsjö b7c3bfd5eb w32pthreads: use the condition variable API directly when targeting newer versions of Windows
Wrap the function calls in a similar fashion to how it's being done
with the critical section API.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
2014-10-10 11:27:30 +03:00
James AlmerandMartin Storsjö 73ea3ffcd5 w32pthreads: use the CONDITION_VARIABLE typedef if available
This silences warnings about passing arguments from incompatible pointer type
when targeting Windows Vista or newer.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Martin Storsjö <martin@martin.st>
2014-10-10 11:27:26 +03:00
James Almer 8c6992bf0c compat/w32pthreads: use the condition variable API directly when targeting newer versions of Windows
Wrap the function calls in a similar fashion to how it's being done
with the critical section API.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-09 17:51:46 -03:00
James Almer 0c06949314 compat/w32pthreads: use the CONDITION_VARIABLE typedef if available
This silences warnings about passing arguments from incompatible pointer type
when targeting Windows Vista or newer.

Tested-by: Matt Oliver <protogonoi@gmail.com>
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-09 13:26:44 -03:00
James AlmerandAnton Khirnov 82f8eb5f77 jpeg2000: split off inverse MCT as Jpeg2000DSP
This makes the addition of arch optimized functions easier.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Anton Khirnov <anton@khirnov.net>
2014-10-08 08:02:55 +00:00
James Almer fb7d8d50bc swscale: remove obsolete FF_API_SWS_FORMAT_NAME cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-05 17:10:29 -03:00
James Almer ddc3768161 avformat: remove obsolete FF_API_READ_PACKET cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-05 17:10:26 -03:00
James Almer ecf457f3ac avformat: remove obsolete FF_API_CLOSE_INPUT_FILE cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-05 17:10:23 -03:00
James Almer 3bd9f17b8a avformat: remove obsolete FF_API_SET_PTS_INFO cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-05 17:10:20 -03:00
James Almer a578b93c73 avformat: remove obsolete FF_API_NEW_STREAM cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-05 17:10:15 -03:00
James Almer cc787709ee avformat: remove obsolete FF_API_FORMAT_PARAMETERS cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-05 17:10:13 -03:00
James Almer 903a0acba4 avformat: remove obsolete FF_API_ALLOC_OUTPUT_CONTEXT cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-05 17:10:07 -03:00
James Almer e524a9b1ff avutil: remove obsolete FF_API_INTFLOAT cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-05 17:10:03 -03:00
James Almer 3e57520982 avutil: remove obsolete FF_API_SAMPLES_UTILS_RETURN_ZERO cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-05 17:09:56 -03:00
James Almer 71718de814 avutil: remove obsolete FF_API_FIND_OPT cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-05 17:09:53 -03:00
James Almer 1abb77285c avutil: remove obsolete FF_API_GET_BITS_PER_SAMPLE_FMT cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-05 17:09:49 -03:00
James Almer 42111bb960 avcodec: remove obsolete FF_API_FAST_MALLOC cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-05 17:09:44 -03:00
James Almer 0de1d6287e x86/mlpdec: add ff_mlp_rematrix_channel_{sse4,avx2}
2x to 2.5x faster than the C version.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-02 22:11:55 -03:00
James Almer ddb813b0ef mlpdec: move rematrix_channels code to output_data()
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-02 22:11:51 -03:00
James Almer c9f2ec8a34 jpeg2000: split off inverse MCT decoding as Jpeg2000DSP
This makes the addition of arch optimized functions easier.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-02 03:21:45 -03:00
James Almer acebff8e5d x86/mpegvideoencdsp: improve ff_pix_sum16_sse2
~15% faster.

Also add an mmxext version that takes advantage of the new code, and
build it alongside with the mmx version only on x86_32.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-10-01 13:07:22 -03:00
James Almer 26cd7b1e1a x86/fmtconvert: add ff_int32_to_float_fmul_array8_{sse,sse2}
About two times faster than the c wrapper.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-26 20:48:40 -03:00
James Almer a829870b2f avcodec/svq1enc: align buffer used by simd functions
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-25 16:00:20 -03:00
James Almer 4b892e469b x86/cavsdsp: fix buffer alignment in cavs_idct8_add_mmx()
It may be used by ff_add_pixels_clamped_sse2().
Should fix fate-cavs failures on some systems.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-25 16:00:16 -03:00
James Almer 4f4f08e6f0 x86/idctdsp: port {put,add}_pixels_clamped to yasm
Also add sse2 versions for both.
put_pixels_clamped port and sse2 version originally written by Timothy Gu.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-24 21:52:13 -03:00
James Almer c99a882814 avcodec/idctdsp: change {put,add}_pixels_clamped to ptrdiff_t line_size
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-24 21:43:19 -03:00
James Almer ad26e83f9c avcodec/x86: use function pointers for {put,add}_pixels_clamped
Same behavior as in simple_idct.
This way the best optimized versions available will be used instead.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-24 18:52:32 -03:00
James Almer 70277d1d23 x86/videodsp: add ff_emu_edge_{hfix,hvar}_avx2
~15% faster than sse2.

Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-24 16:12:55 -03:00
James Almer 164d6c7f5b x86/videodsp: fix warning about discarded 'const' qualifier
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-23 19:59:20 -03:00
James Almer 789274dca8 avcodec/libvpxdec: don't check for formats other than i420 when vp9 decoding is disabled
Should fix ticket #3958.

Reviewed-by: James Zern <jzern@google.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-23 19:50:28 -03:00
James Almer 6b2caa321f x86/vp9: add AVX and AVX2 MC
Roughly 25% faster MC than ssse3 for blocksizes 32 and 64.

Reviewed-by: Ronald S. Bultje <rsbultje@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-22 22:35:03 -03:00
James Almer 33c752be51 x86/me_cmp: port mmxext vsad functions to yasm
Also add mmxext versions of vsad8 and vsad_intra8, and sse2 versions of
vsad16 and vsad_intra16.
Since vsad8 and vsad16 are not bitexact, they are accordingly marked as
approximate.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-19 20:50:20 -03:00
James Almer 6edd6a4f00 avcodec/dv_profile: deprecate internal function that shouldn't be public
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-19 14:32:38 -03:00
James Almer 77f9a81cca x86/me_cmp: combine sad functions into a single macro
No point in having the sad8 functions separate now that the loop is no
longer unrolled.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-17 23:52:36 -03:00
James Almer fffc9a077d avfilter: remove obsolete FF_API_FILL_FRAME cruft
Reviewed-by: Paul B Mahol <onemda@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-17 15:23:26 -03:00
James AlmerandMichael Niedermayer 0456d169c4 x86/me_cmp: port mmxext and sse2 sad functions to yasm
Also add a missing c->pix_abs[0][0] initialization, and sse2 versions of
sad16_x2, sad16_y2 and sad16_xy2 (%15 to %20 faster than mmxext).
Since the _xy2 versions are not bitexact, they are accordingly marked as
approximate.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-09-17 11:12:50 +02:00
James AlmerandPaul B Mahol d1c49bcae9 avfilter: remove obsolete FF_API_ACONVERT_FILTER cruft
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-17 07:43:03 +00:00
James Almer ad1dadac86 avfilter: remove obsolete FF_API_BUFFERSRC_BUFFER cruft
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-15 15:54:06 -03:00
James Almer 95a064f530 avutil: remove obsolete FF_API_OLD_OPENCL cruft
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-15 15:50:17 -03:00
James Almer af7d260626 avutil: remove obsolete FF_API_LLS1 cruft
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-15 15:50:10 -03:00
James Almer 4ae6bcc025 RELEASE: update to 2.4.git
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-15 13:11:10 -03:00
James Almer 91459bd320 avcodec: remove obsolete FF_API_DSPUTIL cruft
Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-14 22:13:05 -03:00
James Almer 52ec81c67d x86/hevc_res_add: add missing guards to hevc_transform_add32_8_avx2
Should fix compilation with old Yasm/Nasm versions.

Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-04 23:34:01 -03:00
James Almer c3d2426cca x86/hevc_res_add: add ff_hevc_transform_add32_8_avx2
~20% faster than AVX.

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-09-04 20:21:29 -03:00
James Almer 7997d78643 lavc/libwebpenc: use WebPMemoryWriterClear()
WebPMemoryWriterClear() must be used instead of free() when libwebp ABI version is > 0x0203

Reviewed-by: Michael Niedermayer <michaelni@gmx.at>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-08-27 15:42:13 -03:00
James Almer d3e9bee6f7 lavf/mp3enc: don't abort if audio packets can't be buffered
Instead skip the picture streams and flush the queued audio packets.
Should address ticket #3851.

Signed-off-by: James Almer <jamrial@gmail.com>
2014-08-27 13:51:34 -03:00
James Almer c2c56d54ee configure: update libvpx_vp9_encoder check
Required to add support for the aq_mode setting.
Any libvpx snapshot prior to 1.3.0 is not recommended for vp9 encoding for that matter.

Reviewed-by: James Zern <jzern@google.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-08-26 00:53:50 -03:00
James AlmerandMichael Niedermayer b140b51ebb lavc/tiff: add support for LZMA compression
Derived from deflate code.
Requires liblzma.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-24 01:21:39 +02:00
James Almer 54ca4dd43b x86/hevc_res_add: refactor ff_hevc_transform_add{16,32}_8
* Reduced xmm register count to 7 (As such they are now enabled for x86_32).
* Removed four movdqa (affects the sse2 version only).
* pxor is now used to clear m0 only once.

~5% faster.

Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-08-21 15:01:33 -03:00
James Almer 76a99d467f x86/hecv_res_add: add ff_hevc_transform_add{8,16,32}_8_avx
~15% faster than sse2

Reviewed-by: Mickaël Raulet <mraulet@gmail.com>
Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Signed-off-by: James Almer <jamrial@gmail.com>
2014-08-20 16:54:52 -03:00
James Almer 9f498f4e6f x86/hevc_res_add: fix register count in hevc_transform_add{16,32}_10_avx2
Signed-off-by: James Almer <jamrial@gmail.com>
2014-08-19 21:34:52 -03:00
James Almer 201a511bb9 lavc/tiff: add support for YUV deflate
Signed-off-by: James Almer <jamrial@gmail.com>
2014-08-19 18:48:39 -03:00
James Almer b4231b4fed lavc/tiff: move unpack_yuv() above the deflate functions
Signed-off-by: James Almer <jamrial@gmail.com>
2014-08-19 18:48:31 -03:00
James AlmerandMichael Niedermayer 853c1fb668 lavf/wavdec: add sanity check for AVCodecContext.channels
Fixes ticket #3862.
As a side effect, this also fixes aac_latm in wav.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-18 09:29:25 +02:00
James AlmerandMichael Niedermayer dffbac0956 lavf/oggparsevp8: use ff_vorbis_stream_comment()
commit db68ef89 did not update the vp8 parser

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-14 05:47:06 +02:00
James AlmerandMichael Niedermayer 9f61d6d8fb lavc/dnxhd: ff_dnxhd_cid_table is not exported
Signed-off-by: James Almer <jamrial@gmail.com>
Reviewed-by: Hendrik Leppkes <h.leppkes@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-13 13:12:52 +02:00
James AlmerandMichael Niedermayer a8592db9bb avcodec/idctdsp: make add/put_pixels_clamped_c internal functions
This reduces code duplication and differences with the fork.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-13 01:44:41 +02:00
James AlmerandMichael Niedermayer 7cafdfe9c7 lavfi: duplicate ff_log2_tab
Fixes compilation failures on msvc/icl shared builds

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-13 01:00:38 +02:00
James AlmerandMichael Niedermayer 9ffac3d00d lsws: duplicate ff_log2_tab
libswscale uses the table but wasn't duplicating it like the rest of the libs.
This should fix compilation failures on msvc/icl after lavu stopped exporting
internal functions and tables.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-12 20:52:21 +02:00
James AlmerandMichael Niedermayer c97870d1a1 x86/dca: remove unused header
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-12 12:46:53 +02:00
James AlmerandMichael Niedermayer e20ff251a6 x86/ttadsp: remove an unnecessary mova
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-12 12:29:05 +02:00
James AlmerandMichael Niedermayer d6711ee648 lavu: stop exporting internal functions
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-12 04:35:52 +02:00
James AlmerandMichael Niedermayer 744f15b6b3 lavu: rename ff_opencl_set_parameter() to avpriv_opencl_set_parameter()
It was wrongly being exported and used by libavfilter.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-12 03:49:45 +02:00
James AlmerandMichael Niedermayer 7b3de03c8f lavf: stop exporting internal functions
Except for those currently used by ffserver.

Signed-off-by: James Almer <jamrial@gmail.com>

Also left some others that seemed used by applications other than ffserver

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-11 14:29:56 +02:00
James AlmerandMichael Niedermayer 31b7ab9f06 lavf/mpegts: remove obsolete ff_mpegts_parse_* cruft
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-11 13:46:53 +02:00
James AlmerandMichael Niedermayer 59ecd4882d lavc/raw: remove obsolete ff_raw_pix_fmt_tags cruft
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-11 13:46:23 +02:00
James AlmerandMichael Niedermayer 8f2634f970 lavc: stop exporting internal functions and tables
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-11 13:23:48 +02:00
James AlmerandMichael Niedermayer 6985ef7813 lavfi: stop exporting internal functions
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-10 04:51:19 +02:00
James AlmerandMichael Niedermayer ddce2b2654 tools/fourcc2pixfmt: use avpriv_get_raw_pix_fmt_tags()
lavc doesn't export ff_raw_pix_fmt_tags[] anymore.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-10 04:50:31 +02:00
James AlmerandMichael Niedermayer d34ec64a22 replace calls to url_feof() with avio_feof()
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-08 00:48:38 +02:00
James AlmerandMichael Niedermayer 5c3c67126f lavf/avio: rename url_feof() to avio_feof()
It's a public function and should use the avio_ namespace

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-08 00:48:22 +02:00
James AlmerandMichael Niedermayer 350f4be12d lavf: remove nonexistent functions from the version file
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-07 13:35:35 +02:00
James AlmerandMichael Niedermayer dd2b0c1cde lavc: remove nonexistent functions from the version file
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-07 13:20:59 +02:00
James AlmerandMichael Niedermayer 1fd880cef3 lavd/dshow: use av_codec_get_id()
ff_codec_get_id() is a lavf internal function

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-07 13:03:17 +02:00
James AlmerandMichael Niedermayer 0ab00a75e4 avcodec/raw: add avpriv_get_raw_pix_fmt_tags()
Used to expose ff_raw_pix_fmt_tags[] to other libav* libraries

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-07 12:52:38 +02:00
James AlmerandMichael Niedermayer 5b12b4fc4b lavf/mpegts: rename ff_mpegts_parse_*() to avpriv_mpegts_parse_*()
The were wrongly being exported and used by libavdevice

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-07 04:28:11 +02:00
James AlmerandMichael Niedermayer 8dfb8190d7 libavcodec/rawdec: remove old ff_find_pix_fmt() function
It's been dead code for more than a year

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-07 00:44:07 +02:00
James AlmerandMichael Niedermayer de417982e8 x86/vp9lpf: use fewer instructions in SPLATB_MIX
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-05 02:47:54 +02:00
James AlmerandMichael Niedermayer b7863c972c x86/hevc_mc: use fewer instructions in hevc_put_hevc_{uni, bi}_w[24]_{8, 10, 12}
Signed-off-by: James Almer <jamrial@gmail.com>
Reviewed-by: Christophe Gisquet <christophe.gisquet@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-04 14:47:15 +02:00
James AlmerandMichael Niedermayer b1a44e6bf5 x86/hevc_mc: remove an unnecessary pxor
Signed-off-by: James Almer <jamrial@gmail.com>
Reviewed-by: Mickaël Raulet <mraulet@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-04 14:35:08 +02:00
James AlmerandMichael Niedermayer d0f56ca071 x86/hevc_deblock: improve 8bit transpose store macros
Up to four instructions less depending on function and instruction set.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-08-03 04:24:15 +02:00
James AlmerandMichael Niedermayer 62baf5b853 x86/hevc_deblock: use existing x86util transpose macro in chroma_{10, 12}
Cosmetic change. No measurable difference in speed.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-31 22:56:21 +02:00
James AlmerandMichael Niedermayer 73c4f63ba5 x86/hevc_deblock: add add ff_hevc_[hv]_loop_filter_luma_{8, 10, 12}_avx
~5% faster than SSSE3

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-29 14:04:59 +02:00
James AlmerandMichael Niedermayer 88ba821f23 x86/hevc_deblock: improve luma functions register allocation
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-29 13:38:05 +02:00
James AlmerandMichael Niedermayer c74b08c5c6 x86/hevc_deblock: remove some unnecessary instructions
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-29 13:27:44 +02:00
James AlmerandMichael Niedermayer 4f91bb0ff0 x86/hevc_deblock: use psignw instead of pmullw where possible
It's slightly faster

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-29 03:42:29 +02:00
James AlmerandMichael Niedermayer 664e9e4331 x86/hevc_deblock: load less data in hevc_h_loop_filter_luma_8
Reading 8 bytes is enough.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-28 21:55:22 +02:00
James AlmerandMichael Niedermayer f137876182 x86/hevc_idct: add a colon to labels
This fixes a warning spam when using NASM

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-28 21:43:32 +02:00
James AlmerandMichael Niedermayer bfb3b2b7a6 x86/hevc_idct: add 12bit idct_dc
Signed-off-by: James Almer <jamrial@gmail.com>
Reviewed-by: Mickaël Raulet <mraulet@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-27 00:30:56 +02:00
James AlmerandMichael Niedermayer 1ace9573dc x86/hevc_idct: replace old and unused idct functions
Only 8-bit and 10-bit idct_dc() functions are included (adding others should be trivial).

Benchmarks on an Intel Core i5-4200U:

idct8x8_dc
       SSE2   MMXEXT  C
cycles 22     26      57

idct16x16_dc
       AVX2   SSE2    C
cycles 27     32      249

idct32x32_dc
       AVX2   SSE2    C
cycles 62     126     1375

Signed-off-by: James Almer <jamrial@gmail.com>
Reviewed-by: Mickaël Raulet <mraulet@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-26 18:00:11 +02:00
James AlmerandMichael Niedermayer 277e5ca617 alpha/me_cmp: move code out of dsputil
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-18 05:15:17 +02:00
James AlmerandMichael Niedermayer 95a2d705cd alpha/idctdsp: move disabled cruft out of dsputil
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-18 05:15:05 +02:00
James AlmerandMichael Niedermayer b67a0e99ee diracdec: don't call ff_emulated_edge_mc_8 directly
Use the videodsp function pointer instead.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-16 03:53:49 +02:00
James AlmerandMichael Niedermayer ad24256e7e diracdec: remove unused dsputil context
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-16 00:11:18 +02:00
James AlmerandMichael Niedermayer 276bef5340 x86/hevc_deblock: add ff_hevc_[hv]_loop_filter_luma_{8, 10}_sse2
Signed-off-by: James Almer <jamrial@gmail.com>
Reviewed-by: Kieran Kunhya <kierank@obe.tv>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-13 13:48:31 +02:00
James AlmerandMichael Niedermayer 123649dd19 x86/dsputilenc: remove some empty if statements
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-12 15:04:58 +02:00