FFmpeg

Commit Graph

Author	SHA1	Message	Date
Loren Merritt	d1a5c4216c	20% faster lpc, 6% overall flac decoding Originally committed as revision 10627 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	08965b22e2	replace FIR with finite differences. 3x faster decode_subframe_fixed(). overall flac decoding: 10% faster if file was encoded with fixed predictors. Originally committed as revision 10626 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	bfdd5bc1f1	unroll finite differences to avoid swapping registers. 1.5x faster encode_residual_fixed(). overall flac encoding: 3% faster at compression_levels 0-2. Originally committed as revision 10625 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	a309dce75f	encode_residual_fixed(): replace FIR with finite differences. 4x faster order 2, 3.5x order 3, 3x order 4. overall flac encoding: 35% faster at compression_levels 0-2, no effect at higher levels. Originally committed as revision 10624 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	6810b93a81	sse2 version of compute_autocorr(). 4x faster than c (somehow, even though doubles only allow 2x simd). overal flac encoding: 15-50% faster on core2, 4-11% on k8, 3-13% on p4. Originally committed as revision 10621 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Vladimir Voroshilov	8787d8377f	AMV video decoder. Patch by Vladimir Voroshilov (voroshil - gmail - com) Originally committed as revision 10617 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Ronald S. Bultje	55ffe9df2a	Use emms_c() instead of ifdef patch by: Ronald S. Bultje rsbultje a gmail d com Originally committed as revision 10616 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Vladimir Voroshilov	a449faeacb	Add variables to prepare to the AMV decoder patch. Patch by Vladimir Voroshilov (voroshil - gmail - com) Originally committed as revision 10614 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	19b9c7cc66	was computing one more autocorrelation coefficient that was actually used Originally committed as revision 10613 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	14bd2a9f25	replace brute force find_optimal_param() with a closed-form solution. overall flac encoding: 4-15% faster. output is not identical to the previous algorithm due to occasional rounding errors, but the differece is less than .0005% bitrate. Originally committed as revision 10612 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	f6215b1b06	gcc isn't smart enough to factor out duplicate stores Originally committed as revision 10611 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Ivan Kalvachev	551109d48a	On bitstream error is_intra_more_likely() could use dsp.sad[0]() that will segfault when xvmc is in use. Originally committed as revision 10610 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	28e968c4a4	2.5x faster compute_autocorr() overall flac encoding: 15-50% faster on core2, 8-30% on k8, 2-20% on p4 (depending on compression_level) Originally committed as revision 10606 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Panagiotis Issaris	9846cbdb13	cosmetics: typos Originally committed as revision 10602 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Panagiotis Issaris	93f0c0a4ca	Remove redundant test. Originally committed as revision 10601 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Vitor Sessak	3a7f5d072a	AMV audio decoder Originally committed as revision 10598 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	815d96a65d	oops, revert unrelated change Originally committed as revision 10597 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	dc44d4ad64	unroll encode_residual_lpc(). speedup varies between 1.2x and 1.8x depending on lpc order. Originally committed as revision 10596 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Jeff Downs	2ddcf84bb7	h264/PAFF preparation: use DELAYED_PIC_REF to mark non-refs frames as held for delayed output patch by Jeff Downs, heydowns a borg d com original thread: Subject: [FFmpeg-devel] [PATCH] Implement PAFF in H.264 Date: 18/09/07 20:30 Originally committed as revision 10592 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	0d2caa37c5	oops, potential overflow on really large blocks Originally committed as revision 10587 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	bd49d4fd49	optimize decode_subframe_lpc() 50%/67%/43% faster on core2/k8/p4, making flac decoding overall 24%/25%/11% faster Originally committed as revision 10586 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Loren Merritt	f74471e043	optimize encode_residual_lpc() 37%/45%/90% faster on core2/k8/p4, making flac encoding overall 15%/17%/40% faster at compression_level>=8 (less at low levels). Originally committed as revision 10585 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Aurelien Jacobs	7ecae905b6	simplify Originally committed as revision 10584 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Aurelien Jacobs	d7af6a9de4	rename one variable to be consistent with the rest of the file Originally committed as revision 10583 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Aurelien Jacobs	442b145abb	consistent spelling: plan => plane Originally committed as revision 10582 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Aurelien Jacobs	d3f9edbafa	simplify Originally committed as revision 10576 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Aurelien Jacobs	f62a2b61f9	cosmetic: indent Originally committed as revision 10575 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Aurelien Jacobs	91fc2cf150	add a new vp6a codec (add alpha plan support to vp6) Originally committed as revision 10574 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Andreas Öman	58f66029b6	reindent Originally committed as revision 10573 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Diego Biurrun	e0a5d77132	Replace HAVE_BFIN with ARCH_BFIN. Blackfin is a CPU architecture, not an instruction set extension and configure sets ARCH_BFIN, not HAVE_BFIN. Originally committed as revision 10572 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Aurelien Jacobs	247df384ec	move all model related tables into their own struct Originally committed as revision 10571 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Diego Biurrun	1218a7e33d	cosmetics: Sort CODEC_ID list. Originally committed as revision 10570 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Aurelien Jacobs	a7d70d88df	rename vp56_b6to3 to vp56_b2p Originally committed as revision 10569 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Aurelien Jacobs	1457516f70	some simplifications and uniformisation Originally committed as revision 10568 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Kostya Shishkov	81fc2f37db	Remove check for input buffer size as it does not guarantee that decoder will not run out of output buffer bounds (and all suspected decoders have their own checks now). Originally committed as revision 10567 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Aurelien Jacobs	b70335a28d	add support for yuva420p colorspace (yuv420p + alpha) Originally committed as revision 10565 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Andreas Öman	1136d34a44	factor out dequant table lookup outside loops, gives a 1-2% speed-up patch by Andreas Öman %andreas A olebyn P nu% original thread: Date: Sep 24, 2007 12:59 PM Subject: [FFmpeg-devel] [PATCH] h264: factor out dequant table lookup outside loops Originally committed as revision 10564 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Kostya Shishkov	4783cf0d09	Do not try to decode more data than output buffer may hold Originally committed as revision 10560 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Diego Biurrun	8b505fc689	VIS-specific code should be enabled conditional to HAVE_VIS, not ARCH_SPARC. Originally committed as revision 10559 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Michael Niedermayer	ff193e6419	some experimental iterative quantization code disabled as it is VERY slow gain is 0.1-0.2 psnr at low qp Originally committed as revision 10556 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Diego Biurrun	8b03def65f	Move VIS CFLAGS settings into configure. Originally committed as revision 10555 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Diego Biurrun	b146873c94	VIS-specific code should be compiled conditional to HAVE_VIS, not ARCH_SPARC. Originally committed as revision 10554 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Kostya Shishkov	ac14047927	Fix decoding of VMDs representing sprites (Last Dynasty, Woodruff). Fixes issue 101 Originally committed as revision 10552 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Reimar Döffinger	61858a76f2	Apply skip_loop_filter before checking if we can parallelize with the selected loop filter Originally committed as revision 10549 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Kostya Shishkov	a2085a7e9d	Guard against output buffer overflows Originally committed as revision 10548 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Kostya Shishkov	675a0583b4	Do not decode more data than output buffer may hold Originally committed as revision 10547 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Baptiste Coudurier	32bbb99d0a	HDYC fourcc, sample hdyc/Test2.avi Originally committed as revision 10541 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Andreas Öman	a27d6e714f	Simplify H.264 decode_cabac_mb_cbp_luma(), giving a ~0.5% speedup. patch by Andreas Öman, andreas olebyn nu Date: Thu, 20 Sep 2007 12:59:19 +0200 Subject: [FFmpeg-devel] [PATCH] simplify h264's decode_cabac_mb_cbp_luma() Originally committed as revision 10537 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Aurelien Jacobs	dee15eceae	allcodecs.h and allformats.h are not used anymore Originally committed as revision 10536 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago
Aurelien Jacobs	d999cff5a3	remove last dependencies on allformats.h and allcodecs.h Originally committed as revision 10535 to svn://svn.ffmpeg.org/ffmpeg/trunk	17 years ago

... 4 5 6 7 8 ...

5875 Commits (da71cdadc25d5c852b4efdddb719c3a7c637e8ed)