Commit Graph
100 Commits
Author SHA1 Message Date
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
James AlmerandMichael Niedermayer ddea3b7106 x86/yadif-10: remove duplicate ABS macro
And use the x86util ones instead, which are optimized for mmxext/sse2.
About ~1% increase in performance on pre SSSE3 processors.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-10 21:06:51 +02:00
James AlmerandMichael Niedermayer 2571e8fe37 alpha/pixblockdsp: move code out of dsputil
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-10 04:01:03 +02:00
James AlmerandMichael Niedermayer 2375b09473 alpha/idctdsp: move idct init code out of dsputil
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-08 22:19:38 +02:00
James AlmerandMichael Niedermayer 195f7bd23d x86/svq1enc: use unaligned mov on SSE2
Might fix fate failures on some systems

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-06 20:27:57 +02:00
James AlmerandMichael Niedermayer dad31083ae x86/svq1enc: port ssd_int8_vs_int16 to yasm
Also add an SSE2 version

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-05 21:43:40 +02:00
James AlmerandMichael Niedermayer 9937362c54 x86/swr: use lavu helper macros to check CPU extensions
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-04 02:12:16 +02:00
James AlmerandMichael Niedermayer 8279a15284 x86/swr: split audioconvert and rematrix DSP into separate files
Also rename resample_x86_dsp.c to resample_init.c

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-04 02:00:11 +02:00
James AlmerandMichael Niedermayer 857cd1f33b swr: initialize only the necessary resample dsp functions
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-04 01:37:41 +02:00
James AlmerandMichael Niedermayer b5f0eac068 swr: rename swresample_dsp init functions to swri_resample_dsp
The swresample_ prefix is not for internal functions

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-02 13:18:30 +02:00
James AlmerandMichael Niedermayer 42a92a240d swr: remove obsolete resample prototypes
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-02 03:14:45 +02:00
James AlmerandMichael Niedermayer 23a9edf531 Partially revert "swr: add prototypes for resample dsp functions"
Prototypes are not needed anymore now that the x86 functions don't
include resample_template.c

The DO_RESAMPLE_ONE macro is removed for that same reason as well.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-02 03:14:36 +02:00
James AlmerandMichael Niedermayer c45b7f0d80 x86/swr: add ff_resample_{common, linear}_int16_xop
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-02 01:11:20 +02:00
James AlmerandMichael Niedermayer 1a69224f44 x86/swr: add ff_resample_{common, linear}_float_fma
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-02 01:09:53 +02:00
James AlmerandMichael Niedermayer a441a2437b x86: rename dsputil.asm to idctdsp.asm
Its only function is no longer part of dsputil.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-02 01:08:04 +02:00
James AlmerandMichael Niedermayer dd2c9034b1 x86/swr: convert resample_{common, linear}_double_sse2 to yasm
Signed-off-by: James Almer <jamrial@gmail.com>

312531 -> 311528 dezicycles

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-07-01 17:57:36 +02:00
James AlmerandMichael Niedermayer 5fef4afb85 configure: add missing audiodsp dependency for ra144
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-27 13:37:10 +02:00
James AlmerandMichael Niedermayer 607c88126c configure: fix g729 decoder dependencies
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-27 13:36:50 +02:00
James AlmerandMichael Niedermayer a6b8aef0dc configure: remove duplicate ape_decoder_select line
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-27 13:36:37 +02:00
James AlmerandMichael Niedermayer 057d2704e7 x86/videodsp: add emulated_edge_mc_mmxext
This also changes hfix8_mmx and above to use mmx regs instead of
gprs, and makes emulated_edge_mc_sse and emulated_edge_mc_sse2 use
mmxext hfix and hvar functions instead of mmx where possible.

This is mostly in preparation for an ssse3 version.

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

code is about 1 cpu cycle faster approximately

Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-26 17:58:57 +02:00
James AlmerandMichael Niedermayer 476bd3c7e4 x86/dsputil: move put_signed_pixels_clamped out of bswapdsp.asm
It's still a dsputil function

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-23 22:11:18 +02:00
James AlmerandMichael Niedermayer c172683bf4 x86/dsputil: remove redundant global motion compensation code
The SSE version has been no different than the mmx one since commit a41bf09d

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-23 02:15:06 +02:00
James AlmerandMichael Niedermayer 6ec3dc97fc x86/audiodsp: move asm code out of dsputil
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-22 19:53:09 +02:00
James AlmerandMichael Niedermayer e930287900 configure: remove superfluous check for AVX/FMA3 support in Yasm
The minimum Yasm/NASM version required to compile ffmpeg supports both
instruction sets

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-20 15:53:58 +02:00
James AlmerandMichael Niedermayer 05d95c53a7 alpha/blockdsp: move clear_blocks out of dsputil
The blockdsp split did not cover Alpha optimizations

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-19 22:39:38 +02:00
James AlmerandMichael Niedermayer a5ce608fc7 x86/blockdsp: restore author attribution
See commits
649c00c96d
5fecfb7d58
73b02e2460

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-19 18:31:44 +02:00
James AlmerandMichael Niedermayer 4c9ee1590f lavf/Makefile: fix standalone compilation of live_flv demuxer
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-19 13:25:28 +02:00
James AlmerandMichael Niedermayer 60a06400a9 configure: fix NASM output format on Win64
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-19 13:18:30 +02:00
James AlmerandMichael Niedermayer 454c019cb5 x86/hevc_idct: fix movd parameter size in DC_ADD_INIT
Fixes compilation with NASM x86_64

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-19 13:18:13 +02:00
James AlmerandMichael Niedermayer fe782233aa x86/blockdsp: move asm code out of dsputil
Also replace INLINE_<opt> with EXTERNAL_<opt> that were wrongly
changed by commit 2b05db4f81

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-19 13:09:03 +02:00
James AlmerandMichael Niedermayer 7f4dfbd080 swr: add prototypes for resample dsp functions
Should fix compilation failures with MSVC and any other compiler
without inline asm support.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-15 01:33:17 +02:00
James AlmerandMichael Niedermayer 345f2234d1 x86/scale: fix xmm register count for hscale*_sse2
xmm6 was being clobbered in ff_hscale8to{15,19}_8_sse2 on Win64

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-09 04:13:23 +02:00
James AlmerandMichael Niedermayer 6d408495b5 x86/dct32: don't build ff_dct32_float_sse on x86_64
There's an SSE2 version already, and technically the SSE version
on x86_64 was wrong (using pshufd and pshuflw, SSE2 instructions).

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-09 00:51:43 +02:00
James AlmerandMichael Niedermayer 85065d2a7c x86/float_dsp: add missing femms
It was lost during the port.
Should fix fate on 3dnowext machines.

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-08 20:06:28 +02:00
James AlmerandMichael Niedermayer dcaf9660b6 x86/float_dsp: port vector_fmul_window to yasm
Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-08 12:41:32 +02:00
James AlmerandMichael Niedermayer fc8db12a73 x86/vp9: inital AVX2 intra_pred
tos3k-vp9-b10000.webm on a Core i5-4200U @1.6GHz

1219 decicycles in ff_vp9_ipred_dc_32x32_ssse3, 131070 runs, 2 skips
439 decicycles in ff_vp9_ipred_dc_32x32_avx2, 131070 runs, 2 skips

3570 decicycles in ff_vp9_ipred_dc_top_32x32_ssse3, 4096 runs, 0 skips
2494 decicycles in ff_vp9_ipred_dc_top_32x32_avx2, 4096 runs, 0 skips

1419 decicycles in ff_vp9_ipred_dc_left_32x32_ssse3, 16384 runs, 0 skips
717 decicycles in ff_vp9_ipred_dc_left_32x32_avx2, 16384 runs, 0 skips

2737 decicycles in ff_vp9_ipred_tm_32x32_avx, 1024 runs, 0 skips
2088 decicycles in ff_vp9_ipred_tm_32x32_avx2, 1024 runs, 0 skips

3090 decicycles in ff_vp9_ipred_v_32x32_avx, 512 runs, 0 skips
2226 decicycles in ff_vp9_ipred_v_32x32_avx2, 512 runs, 0 skips

1565 decicycles in ff_vp9_ipred_h_32x32_avx, 1024 runs, 0 skips
922 decicycles in ff_vp9_ipred_h_32x32_avx2, 1024 runs, 0 skips

Signed-off-by: James Almer <jamrial@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
2014-06-08 02:37:20 +02:00