Måns Rullgård
275cfd1501
ARM: NEON optimised scalarproduct_float
...
Originally committed as revision 19971 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-09-22 20:37:55 +00:00
Måns Rullgård
1dee3e97c6
ARM: NEON optimisations for some dsputil functions
...
NEON versions of the following functions are added:
vector_fmul_scalar
vector_fmul_sv_scalar
sv_fmul_scalar
butterflies_float
Originally committed as revision 19957 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-09-22 00:48:48 +00:00
Måns Rullgård
d650574e68
ARM: merge two loops in ff_mdct_calc_neon
...
Originally committed as revision 19941 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-09-21 02:56:12 +00:00
Måns Rullgård
f7a3b6030c
ARM: interleave cos/sin tables for improved NEON MDCT
...
Originally committed as revision 19940 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-09-21 02:56:09 +00:00
Måns Rullgård
3572b281c8
ARM: remove broken IPP support
...
Originally committed as revision 19935 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-09-21 01:40:08 +00:00
Måns Rullgård
01b2214758
Merge FFTContext and MDCTContext
...
Originally committed as revision 19931 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-09-20 17:30:20 +00:00
Måns Rullgård
d25130eb23
ARM: do not use movw/movt for relocatable values with PIC
...
Originally committed as revision 19886 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-09-16 19:20:48 +00:00
Måns Rullgård
f486321395
Move per-arch fft init bits into the corresponding subdirs
...
Originally committed as revision 19864 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-09-15 21:14:14 +00:00
Måns Rullgård
9ecc414195
ARM: 10l: fix large FFTs
...
Originally committed as revision 19846 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-09-14 21:37:41 +00:00
Måns Rullgård
edc0f5dcba
ARM: NEON optimised MDCT
...
Originally committed as revision 19819 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-09-11 02:24:22 +00:00
Måns Rullgård
750f5034cf
ARM: faster NEON IMDCT
...
Originally committed as revision 19817 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-09-11 02:01:18 +00:00
Måns Rullgård
648d792042
ARM: NEON optimised FFT and MDCT
...
Vorbis and AC3 ~3x faster.
Parts by Naotoshi Nojiri, naonoj gmail
Originally committed as revision 19806 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-09-10 08:50:03 +00:00
Diego Biurrun
deb1b2b699
Add necessary #include for config.h.
...
Originally committed as revision 19692 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-08-24 10:59:14 +00:00
Måns Rullgård
9ae443f420
10L: remove instruction left over from debugging
...
Originally committed as revision 19638 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-08-14 01:05:48 +00:00
Måns Rullgård
e814015d69
ARM: NEON optimised vorbis_inverse_coupling
...
12% faster Vorbis decoding on Cortex-A8.
Originally committed as revision 19637 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-08-14 01:02:06 +00:00
Måns Rullgård
341f394f0d
ARM: cleaner selection of ELF-spefic assembler directives
...
Originally committed as revision 19522 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-07-27 22:55:55 +00:00
Martin Storsjö
e21a892163
Conditionally compile ELF-specific ARM assembly bits that fail on Windows CE.
...
patch by Martin Storsjö, martin martin st
Originally committed as revision 19514 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-07-27 12:53:44 +00:00
Diego Biurrun
7d90972c84
cosmetics: reindent/prettyprint after last commit
...
Originally committed as revision 19495 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-07-22 22:38:26 +00:00
Diego Biurrun
31cf61b447
Only compile in NEON optimizations for H.264 when the H.264 decoder is enabled.
...
Originally committed as revision 19494 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-07-22 22:33:33 +00:00
Diego Biurrun
99e5a9d1ea
Do not redundantly check for both CONFIG_THEORA_DECODER and CONFIG_VP3_DECODER.
...
The Theora decoder depends on the VP3 decoder.
Originally committed as revision 19492 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-07-22 22:27:10 +00:00
Måns Rullgård
0a8958c849
ARM: handle VFP register arguments in ff_vector_fmul_window_neon()
...
Originally committed as revision 19475 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-07-20 22:30:27 +00:00
Måns Rullgård
ce742de22c
ARM: check for VFP register arguments
...
Originally committed as revision 19474 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-07-20 22:30:24 +00:00
David Conrad
2483298ae2
ARM: NEON VP3 IDCT
...
15% faster VP3/Theora, 10% faster VP6
Originally committed as revision 19345 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-07-04 20:41:11 +00:00
Måns Rullgård
2da4e5e3e1
ARM: slightly faster NEON H264 horizontal loop filter
...
Originally committed as revision 19216 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-06-17 22:33:04 +00:00
Måns Rullgård
c9311a12d5
ARM: add some PLD in NEON IDCT
...
Originally committed as revision 18972 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-05-28 17:19:28 +00:00
David Conrad
548a99742c
ARM: actually add VP3 loop filter
...
Originally committed as revision 18917 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-05-23 18:47:26 +00:00
David Conrad
6db8697a39
ARM: NEON VP3 Loop Filter
...
Originally committed as revision 18916 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-05-23 18:36:20 +00:00
David Conrad
d647ed789f
ARM: Use fewer register in NEON put_pixels _y2 and _xy2
...
Approved by Mans on IRC
Originally committed as revision 18713 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-04-29 11:38:09 +00:00
David Conrad
428bf2ac88
ARM: NEON put_pixels_clamped
...
Originally committed as revision 18712 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-04-29 11:31:43 +00:00
David Conrad
d8f3f340ad
Add guaranteed alignment for loading dest pixels in avg_pixels16_neon
...
Originally committed as revision 18535 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-04-16 08:39:13 +00:00
David Conrad
cc2e555420
ARM: NEON optimized put_signed_pixels_clamped
...
Originally committed as revision 18333 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-04-04 21:02:48 +00:00
Måns Rullgård
08e12b2240
ARM: NEON optimised add_pixels_clamped
...
Based on patch by David Conrad.
Originally committed as revision 18332 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-04-04 20:18:58 +00:00
Måns Rullgård
35690321a7
ARM: disable inline asm for armcc
...
Originally committed as revision 17831 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-03-05 21:20:13 +00:00
Måns Rullgård
4cd19f6e78
ARM: fix missing MUL16() return type
...
Originally committed as revision 17679 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-03-01 12:11:02 +00:00
Måns Rullgård
fe7f149ed8
ARM: fix corner-case overflow in H.264 weighted prediction
...
Originally committed as revision 17657 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-02-28 13:48:54 +00:00
Måns Rullgård
e1f7cb7fa0
ARM: NEON optimised vector_fmul_window
...
Originally committed as revision 16868 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-30 23:13:19 +00:00
Måns Rullgård
dd927e2e62
ARM: NEON optimised vector_fmul
...
Originally committed as revision 16867 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-30 23:13:15 +00:00
Måns Rullgård
ca6532f620
ARM: remove some unused macro arguments
...
Originally committed as revision 16824 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-27 16:34:10 +00:00
Måns Rullgård
d8f9269dc6
ARM: reorder some instructions in put_pixels*_arm for speed gains
...
Originally committed as revision 16823 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-27 16:06:51 +00:00
Måns Rullgård
00c5727d90
ARM: replace jump tables with conditional branches
...
Originally committed as revision 16822 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-27 16:06:47 +00:00
Måns Rullgård
d9e68f5c1a
ARM: replace explicit literal loads with ldr Rd, =lit
...
Originally committed as revision 16821 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-27 16:06:44 +00:00
Måns Rullgård
fc252eba02
ARM: change alignment of loops in put_pixels*_arm to 32
...
Originally committed as revision 16820 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-27 16:06:41 +00:00
Måns Rullgård
4f928a4d2d
ARM: optimised mid_pred()
...
Originally committed as revision 16819 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-27 16:06:38 +00:00
Måns Rullgård
1214bd86dc
ARM: allow register operands for shifts in MULL()
...
Originally committed as revision 16818 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-27 16:06:34 +00:00
Måns Rullgård
bd53b426b7
ARM: NEON optimised H.264 weighted prediction
...
Originally committed as revision 16771 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-25 13:04:45 +00:00
Måns Rullgård
5a29589b81
ARM: NEON optimised H.264 biweighted prediction
...
Originally committed as revision 16770 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-25 13:04:41 +00:00
Diego Biurrun
406792e7b0
cosmetics: Remove pointless period after copyright statement non-sentences.
...
Originally committed as revision 16684 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-19 15:46:40 +00:00
Måns Rullgård
77c4537313
ARM: simplify ff_put/avg_h264_chroma_mc4/8_neon definitions, no code change
...
Originally committed as revision 16677 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-18 20:43:11 +00:00
Aurelien Jacobs
49fb20cb8a
replace all occurrence of ENABLE_ by the corresponding CONFIG_, HAVE_ or ARCH_
...
and remove all ENABLE_ definitions.
Originally committed as revision 16600 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-14 17:19:17 +00:00
Aurelien Jacobs
b250f9c66d
Change semantic of CONFIG_*, HAVE_* and ARCH_*.
...
They are now always defined to either 0 or 1.
Originally committed as revision 16590 to svn://svn.ffmpeg.org/ffmpeg/trunk
2009-01-13 23:44:16 +00:00