2b5269b51c
moving lps state transition code a little up in the branched asm code (1% faster on P3)
...
Originally committed as revision 6658 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-11 16:39:50 +00:00
b99f3cabed
write cabac low and range variables as early as possible to prevent stalls from reading them before they where written, the P4 is said to disslike that alot, on P3 its 2% faster (START/STOP_TIMER over decode_residual)
...
Originally committed as revision 6657 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-11 16:11:41 +00:00
d17faef011
use ecx instead of cl (no speed change on P3 but might avoid partial register stalls on some cpus)
...
Originally committed as revision 6656 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-11 15:20:08 +00:00
d61c4e731e
make state transition tables global as they are constant and the code is slightly faster that way
...
Originally committed as revision 6655 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-11 14:44:17 +00:00
5f3eca121e
10l
...
Originally committed as revision 6654 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-11 13:25:29 +00:00
0fa352c7e6
make lps_range a global table its constant anyway (saves 1 addition for accessing it)
...
Originally committed as revision 6653 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-11 13:21:42 +00:00
3650b43959
enable CMOV_IS_FAST as its faster or equal speed on every cpu (duron, athlon, PM, P3) from which ive seen benchmarks, it might be slower on P4 but noone has posted benchmarks ...
...
Originally committed as revision 6652 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-11 12:23:40 +00:00
6ab312daa2
doxy
...
Originally committed as revision 6647 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-11 10:29:00 +00:00
dadb850a50
Move CFLAGS handling to common.mak.
...
Originally committed as revision 6642 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-11 08:30:13 +00:00
a33fe57287
Switch to the LGPL as agreed to by the author according to the
...
initial commit log message.
Originally committed as revision 6641 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-11 07:47:59 +00:00
3689cf1649
Targa image decoder
...
Originally committed as revision 6640 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-11 04:15:04 +00:00
15e35274d8
Rename SIGN macro to the more fitting UNFOLD.
...
Originally committed as revision 6626 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-10 12:07:25 +00:00
0bc2e7f081
BRANCHLESS_CABAD --> BRANCHLESS_CABAC_DECODER
...
Originally committed as revision 6623 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-10 08:16:41 +00:00
ab5a1435ec
Move TRANSPOSE8 macro to dsputil_altivec.h.
...
(was duplicated in libavcodec/ppc/vc1dsp_altivec.c
nd libavcodec/ppc/mpegvideo_altivec.c, and will be
used in upcoming routines for h264_altivec.c)
Originally committed as revision 6621 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-10 08:01:19 +00:00
9ed92c65f1
moving another bit&1 out, this is as fast as with it in there, but it makes more sense with it outside of the loop
...
Originally committed as revision 6618 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-10 06:56:51 +00:00
f1b37db48d
move the &1 out of the asm so gcc can optimize it away in inlined cases (yes this is slightly faster)
...
Originally committed as revision 6616 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-10 01:17:39 +00:00
ab0151d163
replace a few and/sub/... by cmov
...
this is faster on P3, should be faster on AMD, and should be slower on P4
its disabled by default (benchmarks welcome so we know when to enable it)
Originally committed as revision 6615 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-10 01:08:39 +00:00
a6672acf45
reading 8bit mem into a 8bit register needs 2 uops on P4, 8bit->32bit with zero extension needs just 1
...
Originally committed as revision 6612 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 21:57:10 +00:00
2d3df05ca0
on the P4 inc needs twice as much time a add
...
Originally committed as revision 6611 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 21:39:07 +00:00
2ee9dc65be
10l
...
Originally committed as revision 6610 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 21:21:10 +00:00
7822e1c1ff
reverse remainder of the failed attempt to optimize *state=c->mps_state[s]
...
Originally committed as revision 6609 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 21:14:16 +00:00
ef0090a998
x86 branchless cabac decoder
...
slightly faster on P3
Originally committed as revision 6608 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 20:51:33 +00:00
2e1aee80f4
optimize branchless C CABAC decoder
...
Originally committed as revision 6607 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 20:44:11 +00:00
b420448e38
removing ALTIVEC_USE_REFERENCE_C_CODE, since has no use anymore
...
Originally committed as revision 6606 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 18:29:46 +00:00
1c2a417f6a
move outcommented START/STOP_TIMER to a hopefully better place for benchmarking ...
...
Originally committed as revision 6605 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 18:20:00 +00:00
30dc5f56ad
drop failed attempt to optimize *state= c->mps_state[s];
...
Originally committed as revision 6604 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 15:52:17 +00:00
c56d23dacf
10l bugfix for some disabled code
...
Originally committed as revision 6603 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 14:15:53 +00:00
f7d0b68361
first try of a handwritten get_cabac() for x86, this is 10-20% faster on P3 depening on if you try to subtract the START/STOP_TIMER overhead
...
Originally committed as revision 6602 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 14:15:14 +00:00
441e8fe9c9
add_bytes passes tests
...
Originally committed as revision 6600 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 13:37:43 +00:00
5bbe2a5292
remove bytestream_end checks, seems to work fine without them and the bitstream reader doesnt check for the end either
...
Originally committed as revision 6599 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 12:25:24 +00:00
462209fe10
fix AC3 5.1 being decoded as mono
...
patch by Andrea Gianarro % giandrea AH gmail P com %
Original thread:
Date: Oct 9, 2006 11:55 AM
Subject: [Ffmpeg-devel] AC3 5:1 decoding as mono
Originally committed as revision 6598 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 11:36:42 +00:00
bca519e0f6
Fix GPL/LGPL license version mismatch.
...
Originally committed as revision 6597 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 07:31:27 +00:00
c010d69a75
decrease ff_h264_norm_shift[] size
...
Originally committed as revision 6596 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-09 00:59:42 +00:00
158256a13a
Fixes:
...
rv10.c:494: warning: implicit declaration of function ‘ff_mpeg4_init_direct_mv’
Approved by Michael.
Originally committed as revision 6595 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-08 21:26:19 +00:00
6ff042699f
cleanup
...
Originally committed as revision 6594 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-08 21:26:08 +00:00
a10c779f76
Fixes:
...
opt.c:327: warning: no return statement in function returning non-void
opt_list return value is never checked.
Approved by Michael.
Originally committed as revision 6593 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-08 21:25:22 +00:00
69261768d3
Fixes:
...
parser.c:555: warning: implicit declaration of function ‘ff_cavs_find_frame_end’
Approved by Michael.
Originally committed as revision 6592 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-08 21:23:57 +00:00
621d92940e
Fixes:
...
mpegvideo.h:777: warning: ‘inline’ is not at beginning of declaration
motion_est_template.c:236: warning: ‘inline’ is not at beginning of declaration
Approved by Diego.
Originally committed as revision 6591 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-08 21:11:03 +00:00
214019ed32
Avoid void *-arithmetic
...
Originally committed as revision 6590 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-08 14:32:27 +00:00
75336fc885
Non Altivec optimizations already present at the top
...
Originally committed as revision 6588 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-08 13:55:02 +00:00
260ceb6322
branchless renormalization (1% faster get_cabac) old branchless renormalization wasnt faster because gcc was scared of the shift variable (missusing bit variable now)
...
Originally committed as revision 6587 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-08 13:20:22 +00:00
99ce10873d
5% faster get_cabac()
...
Originally committed as revision 6586 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-08 11:24:37 +00:00
e16c407a81
output typo fixes
...
Originally committed as revision 6585 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-08 10:11:58 +00:00
cad35abc0a
Compilation fix: pix_abs16x16_c was undeclared.
...
Originally committed as revision 6584 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-08 09:41:00 +00:00
8823419fc1
Compilation fix, printf gets redefined to please_use_av_log.
...
Originally committed as revision 6583 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-08 09:38:22 +00:00
400d0f8e47
disable benchmarking code
...
disable asm optims as the fastest depends on cpu type
Originally committed as revision 6582 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-07 22:37:34 +00:00
4310580db5
renorm_cabac_decoder_once START/STOP_TIMER scores for athlon
...
Originally committed as revision 6581 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-07 22:34:32 +00:00
87ea51e0b5
fix the dcbz check and move it in configure
...
Originally committed as revision 6580 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-07 19:14:25 +00:00
5659b509c7
refill cabac variables in 16bit steps, 3% faster get_cabac()
...
Originally committed as revision 6578 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-07 15:44:14 +00:00
b78e7197a8
Change license headers to say 'FFmpeg' instead of 'this program/this library'
...
and fix GPL/LGPL version mismatches.
Originally committed as revision 6577 to svn://svn.ffmpeg.org/ffmpeg/trunk
2006-10-07 15:30:46 +00:00
Michael Niedermayer
Diego Biurrun
Kostya Shishkov
Guillaume Poirier
Luca Barbato
Andrea Gianarro
Dominik Mierzejewski
Reimar Döffinger