Statistics
| Branch: | Revision:

ffmpeg / libavcodec / i386 @ 07787186

# Date Author Comment
07787186 08/28/2002 08:15 AM Dominik Mierzejewski

warning patch by (Dominik Mierzejewski <dominik at rangers dot eu dot org>)

Originally committed as revision 872 to svn://svn.ffmpeg.org/ffmpeg/trunk

9f361534 08/20/2002 07:23 PM Michael Niedermayer

dont trash mm0, its still used in the next iteration of the loop (fixes strange horizontal lines on some blocks in b frames on mmx only cpus)

Originally committed as revision 855 to svn://svn.ffmpeg.org/ffmpeg/trunk

87f8cab4 08/06/2002 11:51 PM Michael Niedermayer

mpeg4 mpeg quantizer encoding

Originally committed as revision 844 to svn://svn.ffmpeg.org/ffmpeg/trunk

4afeaec9 07/21/2002 12:48 AM Michael Niedermayer

pix_abs mmx2 isnt bit-exact ...

Originally committed as revision 781 to svn://svn.ffmpeg.org/ffmpeg/trunk

39825f31 06/03/2002 05:35 PM Zdenek Kabelac
  • reimplemented remaing avg_ pixel functions
  • modified PAVGB mmx macro to select mmx register with FE constant

Originally committed as revision 657 to svn://svn.ffmpeg.org/ffmpeg/trunk

d3cd0742 06/03/2002 05:31 PM Zdenek Kabelac
  • implemented remaing avg_ pixel functions (these are not used offen)

Originally committed as revision 656 to svn://svn.ffmpeg.org/ffmpeg/trunk

fca0f0e5 05/30/2002 03:14 PM Zdenek Kabelac
  • removed MANGLE from macros for setting constants
  • using MOVQ_WONE/MOVQ_BFE as two instruction instead of static memory value access
    as its always faster
  • PAVGB_MMX macro is using now mm6 -> mm7 is unmodified
  • replaced original pixels_xy2_mmx with new faster and equal implementation...
ff965706 05/29/2002 08:00 PM Zdenek Kabelac
  • using unrolled loops seems to help to MMX Celerons
  • calculating average in parallel to use two MMX units
  • disabled xy2 put code - it's producing rouding errors

Originally committed as revision 626 to svn://svn.ffmpeg.org/ffmpeg/trunk

6aa6ea8e 05/29/2002 07:57 PM Zdenek Kabelac
  • reenabled original xy2 put routine - rounding error is really bad with
    the new code
  • added PAVGP macros for parallel processing to safe few more cycles on
    celerons

Originally committed as revision 625 to svn://svn.ffmpeg.org/ffmpeg/trunk

91abb473 05/29/2002 05:16 PM Zdenek Kabelac
  • code with new PAVGB for MMX only CPU splited into separate file
    and being compiled in the same way as _avg.h
  • PAVG_MMX macros accept also output parameter
  • implemented faster put_pixels_xy2, but it has slightly smaller precission.
    But there is not visible difference in the image quality - might be eventualy...
def60345 05/29/2002 02:29 PM Zdenek Kabelac

Originally committed as revision 623 to svn://svn.ffmpeg.org/ffmpeg/trunk

541027e2 05/29/2002 02:20 PM Zdenek Kabelac
  • cosmetic minor change

Originally committed as revision 622 to svn://svn.ffmpeg.org/ffmpeg/trunk

d17b6f0b 05/29/2002 08:31 AM Zdenek Kabelac
  • optimized remaing avg_pixels_xy2

Originally committed as revision 621 to svn://svn.ffmpeg.org/ffmpeg/trunk

e9c0a38f 05/28/2002 04:35 PM Zdenek Kabelac
  • optimized avg_* functions (except xy2)
  • minor speedup for put_pixels_x2 & cleanup

Originally committed as revision 619 to svn://svn.ffmpeg.org/ffmpeg/trunk

c0eb0bb7 05/27/2002 02:09 PM Zdenek Kabelac
  • more PIC friendly and faster code

Originally committed as revision 616 to svn://svn.ffmpeg.org/ffmpeg/trunk

5f623001 05/27/2002 11:32 AM Zdenek Kabelac
  • removed TESTCPU_MAIN - not needed for testing

Originally committed as revision 615 to svn://svn.ffmpeg.org/ffmpeg/trunk

e5f3d22d 05/27/2002 08:37 AM Zdenek Kabelac
  • undefine local defines when they are no longer needed

Originally committed as revision 612 to svn://svn.ffmpeg.org/ffmpeg/trunk

30eb0396 05/27/2002 08:31 AM Zdenek Kabelac
  • avoids double inclusion of this header
    (how about making all headers in ffmpeg working this way ?)

Originally committed as revision 609 to svn://svn.ffmpeg.org/ffmpeg/trunk

ff4ec49e 05/25/2002 10:45 PM Fabrice Bellard

license/copyright change

Originally committed as revision 599 to svn://svn.ffmpeg.org/ffmpeg/trunk

52af45ad 05/23/2002 04:19 PM Zdenek Kabelac
  • baling 8 seems to have the same speed

Originally committed as revision 575 to svn://svn.ffmpeg.org/ffmpeg/trunk

fbdedc17 05/23/2002 03:57 PM Zdenek Kabelac
  • always baling even though it seems to produce sometime worse
    results then for -fPIC compilation - don't ask me why...

Originally committed as revision 573 to svn://svn.ffmpeg.org/ffmpeg/trunk

31ddcf98 05/23/2002 03:48 PM Zdenek Kabelac
  • cleanup for put_pixels_mmx

Originally committed as revision 572 to svn://svn.ffmpeg.org/ffmpeg/trunk

ec9a41f5 05/23/2002 01:34 PM Zdenek Kabelac
  • somewhat more advanced test suit for dsp code - for now i386 only
    cd test ; make dsptest ; ./dsptest

Originally committed as revision 568 to svn://svn.ffmpeg.org/ffmpeg/trunk

6efad6fd 05/23/2002 12:17 PM Zdenek Kabelac
  • align the source initialy address

Originally committed as revision 567 to svn://svn.ffmpeg.org/ffmpeg/trunk

2bd978bd 05/23/2002 10:10 AM Zdenek Kabelac
  • fixed contrains and avoid usage of scale index access

Originally committed as revision 566 to svn://svn.ffmpeg.org/ffmpeg/trunk

dcb9cd4b 05/23/2002 10:09 AM Zdenek Kabelac
  • added simple test main - see comments about how to
    compile - should be probably made as a regression test

Originally committed as revision 565 to svn://svn.ffmpeg.org/ffmpeg/trunk

ba0420d8 05/22/2002 11:18 PM Michael Niedermayer

using 1 operand less and slightly faster put_pixels_y2

Originally committed as revision 564 to svn://svn.ffmpeg.org/ffmpeg/trunk

a213d664 05/22/2002 08:46 PM Zdenek Kabelac
  • fix for -fPIC compilation - compiles with 2.95.2 as well - any
    other compiler shows any problem here ??

Originally committed as revision 563 to svn://svn.ffmpeg.org/ffmpeg/trunk

4f12a497 05/20/2002 04:25 PM Fabrice Bellard

removed unused code

Originally committed as revision 543 to svn://svn.ffmpeg.org/ffmpeg/trunk

61a4e8ae 05/18/2002 10:59 PM Fabrice Bellard

removed debug function

Originally committed as revision 519 to svn://svn.ffmpeg.org/ffmpeg/trunk

92415510 05/18/2002 10:49 PM Fabrice Bellard

tried to avoid gcc 2.95.2 bug by puting explicit register constraints - added comment about rounding bug in some functions (need to correct or suppress them for regression tests)

Originally committed as revision 515 to svn://svn.ffmpeg.org/ffmpeg/trunk

a7bd8797 05/17/2002 01:01 PM Michael Niedermayer

shared lib support (req by kabi) ...

Originally committed as revision 510 to svn://svn.ffmpeg.org/ffmpeg/trunk

607dce96 05/17/2002 01:04 AM Michael Niedermayer

hopefully faster mmx2&3dnow MC

Originally committed as revision 506 to svn://svn.ffmpeg.org/ffmpeg/trunk

ccf589a8 05/02/2002 01:35 PM Michael Niedermayer

C4=16383 for the c version too and even for some outcommented code

Originally committed as revision 433 to svn://svn.ffmpeg.org/ffmpeg/trunk

9e1795dd 05/02/2002 12:51 PM Michael Niedermayer

set C4 to 16383

Originally committed as revision 432 to svn://svn.ffmpeg.org/ffmpeg/trunk

ef5b1b5a 05/02/2002 04:39 AM Juanjo

- Advanced Intra Coding (AIC) support for H.263+ encoder, just DC by now.
- Bug fix H.263+ AIC tables.
- Warning fixes.

Originally committed as revision 431 to svn://svn.ffmpeg.org/ffmpeg/trunk

d7e9533a 04/27/2002 12:30 PM Michael Niedermayer

fixed msmpeg4 infinite loop if buggy stream
rewrote quantizer
fixed bias (+10% compression/quality for h263 like codecs)
qscale=1 support
mpeg1 intra frames looks far less blocky
added codec_id field

Originally committed as revision 423 to svn://svn.ffmpeg.org/ffmpeg/trunk

cd8e5f96 04/24/2002 12:18 PM Zdenek Kabelac
  • fixes problem with -funroll-loops and buggy gcc compiler

Originally committed as revision 421 to svn://svn.ffmpeg.org/ffmpeg/trunk

ba8d0be9 04/21/2002 10:41 PM Michael Niedermayer

rounding bugfix

Originally committed as revision 409 to svn://svn.ffmpeg.org/ffmpeg/trunk

9dbf1ddd 04/17/2002 04:30 PM Michael Niedermayer

mpeg2/mpeg4 dequantizer support (c & mmx)
mpeg1 dequantizer optimizations

Originally committed as revision 404 to svn://svn.ffmpeg.org/ffmpeg/trunk

9dbcbd92 04/17/2002 04:32 AM Michael Niedermayer

fixed mpeg4 time stuff on encoding
mpeg4 b-frame enoding support
removed old, out-commented ratecontrol
reuse motion compensation code between encoding & decoding
prefix newly added global functions with ff_ to reduce namespace polution
b-frame ME (unfinished, but working)...

3bf43d42 04/07/2002 02:03 AM Michael Niedermayer

mpeg4 mpeg quantizer support

Originally committed as revision 381 to svn://svn.ffmpeg.org/ffmpeg/trunk

649c00c9 03/28/2002 01:41 PM Michael Niedermayer

sizeof(s->block) isnt 64*6*2 anymore bugfix
mpeg12 decoding optimization

Originally committed as revision 364 to svn://svn.ffmpeg.org/ffmpeg/trunk

ba6802de 03/27/2002 09:25 PM Michael Niedermayer

4MV motion estimation (not finished yet)
SAD functions rewritten (8x8 support & MMX2 optimizations)
HQ inter/intra decission
msmpeg4 encoding bugfix (MV where too long)

Originally committed as revision 362 to svn://svn.ffmpeg.org/ffmpeg/trunk

43f1708f 02/26/2002 10:14 PM Juanjo

- Added PSNR feature to libavcodec and ffmpeg. By now just Y PSNR until I'm
sure it works ok. Also it's slow, so use it only when you really need to
measure quality.
- Fix libavcodec Makefile to enable profiling.

Originally committed as revision 314 to svn://svn.ffmpeg.org/ffmpeg/trunk

e7774f11 02/22/2002 03:35 AM Juanjo

- Bug fix on RTYPE (rounding type) not being honoured by H.263+ decoder.

Originally committed as revision 312 to svn://svn.ffmpeg.org/ffmpeg/trunk

9e15ad28 02/19/2002 07:23 PM Juanjo

- Bug fixes in H.263+ Advanced INTRA Coding decoder.
- H.263+ should be able to decode streams with AIC now :)

Originally committed as revision 311 to svn://svn.ffmpeg.org/ffmpeg/trunk

d140623f 02/18/2002 07:33 PM Juanjo

- H.263+ decoder support for Advanded INTRA Coding (buggy)

Originally committed as revision 310 to svn://svn.ffmpeg.org/ffmpeg/trunk

d6a4c0b1 02/18/2002 09:40 AM Zdenek Kabelac
  • some modifications to allow gcc to compile same code for -fPIC
    - introduced MOVQ_WONE, MOVQ_WTWO
  • unrolled put_pixels_clamped_mmx
  • added .baling where the jump address would be compiled on odd address
  • added some testing code to disable all these routines (for time measurement)...
3cb32e3d 02/09/2002 01:25 AM Arpi

PATCH by Rik Snel <>
this includes the range for quantized dct coefficients in dct_quantize() (-1023...1023)

Originally committed as revision 291 to svn://svn.ffmpeg.org/ffmpeg/trunk

5dfd24ac 01/28/2002 07:34 PM Arpi

workaround gcc bug "m" (0)
avoiding useage of ebx

Originally committed as revision 283 to svn://svn.ffmpeg.org/ffmpeg/trunk

2f349de2 01/27/2002 01:30 PM Michael Niedermayer

(commit by michael)
mmx & mmx2 quantizer
c dct permutation bugfix
dont copy input on intra only encodings if it can be avoided
dont draw edges on intra only stuff

Originally committed as revision 281 to svn://svn.ffmpeg.org/ffmpeg/trunk

4bdd9157 01/20/2002 02:30 PM Nick Kurshev

Cygwin's mangling by Felix Buenemann <>

Originally committed as revision 273 to svn://svn.ffmpeg.org/ffmpeg/trunk

0a8d8945 01/17/2002 08:00 PM Michael Niedermayer

(commit by michael)
faster simple idct in MMX

Originally committed as revision 269 to svn://svn.ffmpeg.org/ffmpeg/trunk

3d9fccbf 01/15/2002 04:07 AM Michael Niedermayer

(commit by michael)
draw_edges_mmx()

Originally committed as revision 266 to svn://svn.ffmpeg.org/ffmpeg/trunk

badaf88e 01/13/2002 04:59 AM Michael Niedermayer

(commit by michael)
dequantizers skip trailing zeros
msmpeg4 non-intra decoder has its dequantizer "build in" now

Originally committed as revision 260 to svn://svn.ffmpeg.org/ffmpeg/trunk

f4470e09 01/10/2002 12:41 AM Michael Niedermayer

print cpu flags

Originally committed as revision 248 to svn://svn.ffmpeg.org/ffmpeg/trunk

37e8dcda 12/09/2001 12:39 PM Arpi

new IDCT code by Michael Niedermayer () - #define SIMPLE_IDCT to enable

Originally committed as revision 235 to svn://svn.ffmpeg.org/ffmpeg/trunk

d962f6fd 12/09/2001 12:04 PM Arpi

new IDCT code by Michael Niedermayer () - #define SIMPLE_IDCT to enable

Originally committed as revision 234 to svn://svn.ffmpeg.org/ffmpeg/trunk

f12e206b 11/11/2001 05:55 PM Nick Kurshev

Let loops will be aligned

Originally committed as revision 213 to svn://svn.ffmpeg.org/ffmpeg/trunk

a822a479 11/10/2001 02:36 PM Nick Kurshev

fixed gcc-3.0.x compilation (by Michael Niedermayer)

Originally committed as revision 211 to svn://svn.ffmpeg.org/ffmpeg/trunk

7f3f5ec8 11/03/2001 02:22 AM Arpi

dct_unquantize_h263_mmx() by Michael Niedermayer <>

Originally committed as revision 205 to svn://svn.ffmpeg.org/ffmpeg/trunk

a74127c0 08/15/2001 10:33 PM Fabrice Bellard

win32 fixes

Originally committed as revision 110 to svn://svn.ffmpeg.org/ffmpeg/trunk

64ccc83c 08/15/2001 10:26 PM Fabrice Bellard

removed

Originally committed as revision 105 to svn://svn.ffmpeg.org/ffmpeg/trunk

694ec061 08/15/2001 10:25 PM Fabrice Bellard

suppressed nasm dependancy - rewrote forward DCT and motion estimation code

Originally committed as revision 104 to svn://svn.ffmpeg.org/ffmpeg/trunk

c10e9f70 08/08/2001 04:26 PM Nick Kurshev

Portability and testing issues

Originally committed as revision 55 to svn://svn.ffmpeg.org/ffmpeg/trunk

8def0299 08/07/2001 10:49 PM Fabrice Bellard

added mmx idct

Originally committed as revision 53 to svn://svn.ffmpeg.org/ffmpeg/trunk

fe97c87d 08/07/2001 10:40 PM Fabrice Bellard

updated mmx macros

Originally committed as revision 42 to svn://svn.ffmpeg.org/ffmpeg/trunk

f33802a0 08/07/2001 10:40 PM Fabrice Bellard

added idct mmx code

Originally committed as revision 41 to svn://svn.ffmpeg.org/ffmpeg/trunk

1d20b11a 08/05/2001 04:49 PM Nick Kurshev

Suppressing external gas stuff to improve portability to Win32

Originally committed as revision 33 to svn://svn.ffmpeg.org/ffmpeg/trunk

4af7bcc1 08/03/2001 06:33 PM Arpi

MMX/MMXEXT iDCT support, using external functions currently defined in libmpeg2
Gives average 13-20% mpeg decoding speedup on x86 systems.

Originally committed as revision 30 to svn://svn.ffmpeg.org/ffmpeg/trunk

96f4e513 07/30/2001 11:51 PM Fabrice Bellard

added external cpuid code to solve -fPIC and gcc unclear constraints problems

Originally committed as revision 25 to svn://svn.ffmpeg.org/ffmpeg/trunk

35b2a786 07/30/2001 11:28 PM Fabrice Bellard

renamed - use of s->dct_unquantize function pointer - SHOULD add faster h263 mmx specific unquantization stuff

Originally committed as revision 23 to svn://svn.ffmpeg.org/ffmpeg/trunk

a9b3f630 07/30/2001 09:04 AM Nick Kurshev

Sync with mplayer's stuff

Originally committed as revision 14 to svn://svn.ffmpeg.org/ffmpeg/trunk

7d650cb5 07/24/2001 08:38 PM Fabrice Bellard

suppressed no longer needed emms()

Originally committed as revision 11 to svn://svn.ffmpeg.org/ffmpeg/trunk

a9e3707d 07/24/2001 08:37 PM Fabrice Bellard

fixed cpuid macro to allow PIC compiling

Originally committed as revision 10 to svn://svn.ffmpeg.org/ffmpeg/trunk

de6d9b64 07/22/2001 02:18 PM Fabrice Bellard

Initial revision

Originally committed as revision 5 to svn://svn.ffmpeg.org/ffmpeg/trunk