FFmpeg

Commit Graph

Author	SHA1	Message	Date
Ronald S. Bultje	e3f7bf774c	Fix SPLATB_REG mess. Used to be a if/elseif/elseif/elseif spaghetti, so this splits it into small optimization-specific macros which are selected for each DSP function. The advantage of this approach is that the sse4 functions now use the ssse3 codepath also without needing an explicit sse4 codepath. Originally committed as revision 24487 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Måns Rullgård	e6e3069b54	Simplify lavfi test script a little Originally committed as revision 24486 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Måns Rullgård	8fae6e7c11	Unbreak parallel lavfi testing Originally committed as revision 24485 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Alex Converse	63e1278d88	aacenc: TLS: Save maximum values for each swb in a table. This gives an almost 20% speedup. Originally committed as revision 24484 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Alex Converse	031d5cea04	10l: Remove some commented out code that slipped in. Originally committed as revision 24483 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Alex Converse	fe461767e6	aacenc: TLS: Try to preserve some energy in each non-zero band. Reduce scalefactors in non-zero bands that underflow by twice as much as those in bands that just fail to hit psy targets. Originally committed as revision 24482 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Reimar Döffinger	6cce7cabdb	Fix compilation, forgot to add const also to the definition of ff_yuv2packedX_altivec Originally committed as revision 31782 to svn://svn.mplayerhq.hu/mplayer/trunk/libswscale	15 years ago
Reimar Döffinger	edac49daf5	Use "const" qualifier for pointers that point to input data of audio encoders. This is purely for clarity/documentation purposes. Originally committed as revision 24481 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Reimar Döffinger	6f2c523c85	Fix a "function declaration isn't a prototype" warning. Originally committed as revision 24480 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Reimar Döffinger	a2a17d3f87	Fix use of uninitialized data: A array element can not be used to initialized another array element of the same array. Originally committed as revision 24479 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Reimar Döffinger	5a55d5b592	More const-correctness fixes to avoid warnings. Originally committed as revision 31781 to svn://svn.mplayerhq.hu/mplayer/trunk/libswscale	15 years ago
Reimar Döffinger	a4eef68f53	Add some "const" to avoid incompatible pointer type warnings Originally committed as revision 31780 to svn://svn.mplayerhq.hu/mplayer/trunk/libswscale	15 years ago
Stefano Sabatini	04f6ab1cef	Add missing comma, fix rgb2yuv_table[SWS_CS_SMPTE240M] coefficients. Originally committed as revision 31779 to svn://svn.mplayerhq.hu/mplayer/trunk/libswscale	15 years ago
Stefano Sabatini	24911613a5	Add some comments to the rgb2yuv_table, clarifying the standard where are defined. Originally committed as revision 31778 to svn://svn.mplayerhq.hu/mplayer/trunk/libswscale	15 years ago
Martin Storsjö	496c645d3b	Never shrink the ByteIOContext buffer in ff_rewind_with_probe_data If there is little unread data in the ByteIOContext buffer, this may lead to reducing the size of the ByteIOContext buffer to little more the probe data size. This can lead to suboptimal aviobuf behaviour, e.g. making some demuxers fail to do short seeks backwards (if the input isn't seekable). Originally committed as revision 24478 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Martin Storsjö	8dd25c52cb	mpegts: Warn if unable to seek back Originally committed as revision 24477 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Alex Converse	c226fc5bfb	aacenc: Prevent premature termination of the two loop search. Originally committed as revision 24476 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Alex Converse	81824fe059	aacdec: Only load and write each predictor variable once. This is slightly faster and opens the door for further optimization. Originally committed as revision 24475 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Alex Converse	70c99adb48	aacdec: 4% faster main profile decoding. Originally committed as revision 24474 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Alex Converse	51ffd3a62f	aacenc: Favor log2f() and sqrtf() over log2() and sqrt(). Originally committed as revision 24473 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Alex Converse	04d72abf17	aacenc: Factorize some scalefactor utilities. Originally committed as revision 24472 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Eli Friedman	3611e7a309	Inline asm for VP56 arith coder This is a lot more reliable to get cmov rather than trying to trick gcc into generating it, useful since it's 2% faster overall. Patch by Eli Friedman <eli.friedman at gmail> Originally committed as revision 24471 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
David Conrad	ca18a478e3	VP8: Inline traversing vp8_small_mvtree Much faster read_mv_component, slightly faster overall Originally committed as revision 24470 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
David Conrad	7697cdcf95	VP8: Use vp56_rac_get_prob_branchy when the bit is only used by an if() Originally committed as revision 24469 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
David Conrad	fe1b5d974a	Decode DCT tokens by branching to a different code path for each branch on the huffman tree, instead of traversing the tree in a while loop. Based on the similar optimization in libvpx's detokenize.c 10% faster at normal bitrates, and 30% faster for high-bitrate intra-only Originally committed as revision 24468 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
David Conrad	5474ec2ac8	Move renormalization of the VP56 arith decoder to before decoding a bit No difference at the moment, but allows a future branchy variant of vp56_rac_get_prob to be significantly faster Originally committed as revision 24467 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
David Conrad	b3d755ec8b	Split renorm of vp56 arith decoder to its own function Originally committed as revision 24466 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
David Conrad	24675b8093	vp56's arith decoder's code_word is only 16 bits, no need for unsigned long Originally committed as revision 24465 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	13a1304bb3	Add myself to VP8 copyright and maintainers. Also add Ronald to maintainers. Originally committed as revision 24464 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	414ac27d8f	VP8: always_inline some things to force gcc to do the right thing Mostly seems to help in the MC code, which gets a hundred cycles faster. Originally committed as revision 24463 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	06d50ca804	VP8: use AV_RL24 instead of defining a new RL24. Originally committed as revision 24462 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Ramiro Polla	73016d29c9	swscale-test: scale from reference to source only once for each algorithm Originally committed as revision 31777 to svn://svn.mplayerhq.hu/mplayer/trunk/libswscale	15 years ago
Ramiro Polla	be1c5d35cc	indent Originally committed as revision 31776 to svn://svn.mplayerhq.hu/mplayer/trunk/libswscale	15 years ago
Ramiro Polla	da78053af0	swscale-test: change order tests are run, maintaining the same algorithm for sequential geometries instead of running all algorithms sequentially for each geometry. Originally committed as revision 31775 to svn://svn.mplayerhq.hu/mplayer/trunk/libswscale	15 years ago
Jason Garrett-Glaser	9fddd14a8e	VP8: Slightly faster MV selection Don't clamp best mv unless it's actually used. Originally committed as revision 24461 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	14767f35ed	VP8: use AV_ZERO32 instead of AV_WN32A where relevant Originally committed as revision 24460 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	09959ec46e	VP8: eliminate redundant code in r24458 Originally committed as revision 24459 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	a71abb714e	VP8: shave a few clocks off check_intra_pred_mode Originally committed as revision 24458 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Vitor Sessak	a58ed9a2e7	Add VP8 sign bias code regtest. Not tested by the official conformance suite. Originally committed as revision 24457 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	0087aa47d0	VP8: fix broken sign bias code in MV pred Apparently the official conformance test vectors don't test this feature, even though libvpx uses it. Originally committed as revision 24456 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	3ae079a3c8	VP8: optimize DC-only chroma case in the same way as luma. Add MMX idct_dc_add4uv function for this case. ~40% faster chroma idct. Originally committed as revision 24455 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	3df56f4118	VP8: Clean up some variable shadowing. Originally committed as revision 24454 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	51c9156438	VP8 asm: cosmetics (spacing) Originally committed as revision 24453 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	8a467b2d44	VP8: 30% faster idct_mb Take shortcuts based on statistically common situations. Add 4-at-a-time idct_dc function (mmx and sse2) since rows of 4 DC-only DCT blocks are common. TODO: tie this more directly into the MB mode, since the DC-level transform is only used for non-splitmv blocks? Originally committed as revision 24452 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	ef38842f0b	VP8: smarter prefetching Don't prefetch reference frames that were used less than 1/32th of the time so far in the frame. This helps speed up to ~2% on videos that, in many frames, make near-zero (but not entirely zero) use of golden and/or alt-refs. This is a very common property of videos encoded by libvpx. Originally committed as revision 24451 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Baptiste Coudurier	9479415e4e	In h264 parser, return immediately if buf_size is 0, avoid printing erroneous message for last frame. Originally committed as revision 24450 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Baptiste Coudurier	ef011e6d58	In mpegts muxer, fix rbsp trailing bits in AUD nal, fixes issue #2122 Originally committed as revision 24449 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	c25c776708	VP8: clear DCT blocks in iDCT instead of using clear_blocks. ~0.3% faster overall. Originally committed as revision 24448 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	b74f70d646	VP8: avoid a memset for non-i4x4 blocks with no coefficients Originally committed as revision 24447 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago
Jason Garrett-Glaser	145d31865d	Get rid of more unnecessary dereferences in VP8 deblocking Originally committed as revision 24446 to svn://svn.ffmpeg.org/ffmpeg/trunk	15 years ago

1 2 3 4 5 ...

25313 Commits (e3f7bf774caad334b258f4494e77420a7c161b63) All Branches Search

25313 Commits (e3f7bf774caad334b258f4494e77420a7c161b63)

All Branches