Commits · 6e7315f4a18bedc1ca15eb87f830b1e99686814e · Linshizhi / ffmpeg.wasm-core

11 Aug, 2011 1 commit
- Move RV3/4-specific DSP functions into their own context · d241f51e
  Kostya Shishkov authored 13 years ago
```
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
```
  d241f51e
29 Jul, 2011 1 commit
- H.264: tweak some other x86 asm for Atom · a3bf7b86
  Jason Garrett-Glaser authored 13 years ago
  
  a3bf7b86
21 Jul, 2011 1 commit
- dsputil: update per-arch init funcs for non-h264 high bit depth · a617c6aa
  Mans Rullgard authored 13 years ago
```
Signed-off-by: Mans Rullgard <mans@mansr.com>
```
  a617c6aa
20 Jul, 2011 1 commit
- simple_idct: add 10-bit version · e7a972e1
  Mans Rullgard authored 13 years ago
```
Signed-off-by: Mans Rullgard <mans@mansr.com>
```
  e7a972e1
18 Jul, 2011 1 commit
- dsputil: remove disabled code · 65083b49
  Diego Biurrun authored 13 years ago
  
  65083b49
10 Jul, 2011 1 commit

dsputil: remove ff_emulated_edge_mc macro used in one place · 710b8df9

Mans Rullgard authored 13 years ago

This macro can cause problems in conjunction with the bitdepth
template expansion.  It was presumably added to keep source
compatibility when high bitdepth support was added.  However,
emulated_edge_mc is a dsputil pointer and should not be called
directly, so there is little reason to keep such a macro.
Signed-off-by: Mans Rullgard <mans@mansr.com>

710b8df9

08 Jul, 2011 1 commit

H.264: Add x86 assembly for 10-bit H.264 predict functions · c0483d0c

Daniel Kang authored 13 years ago

Mainly ported from 8-bit H.264 predict.

Some code ported from x264. LGPL ok by author.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

c0483d0c

04 Jul, 2011 3 commits
- YASM: Shut up unused variable compiler warning with --disable-yasm. · 3c7c16fd
  Daniel Kang authored 13 years ago
```
Signed-off-by: Diego Biurrun <diego@biurrun.de>
```
  3c7c16fd
- Fix build with --disable-yasm. · 58f7aad0
  Daniel Kang authored 13 years ago
```
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
```
  58f7aad0
- dsputil_mmx: try to fix compilation without yasm. · 88963996
  Michael Niedermayer authored 13 years ago
```
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
```
  88963996
03 Jul, 2011 1 commit

H.264: Add x86 assembly for 10-bit H.264 qpel functions. · 9bfa5363

Daniel Kang authored 13 years ago

Mainly ported from 8-bit H.264 qpel.

Some code ported from x264. LGPL ok by author.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

9bfa5363

01 Jul, 2011 1 commit
- ac3enc: add int32_t array clipping function to DSPUtil, including x86 versions. · 6054cd25
  Justin Ruggles authored 13 years ago
  
  6054cd25
28 Jun, 2011 1 commit

configure: Drop check for availability of ten assembler operands. · d2ee495f

Diego Biurrun authored 13 years ago

This was done to support gcc 2.95, which is an old legacy compiler
that fails to compile the current codebase anyway.

d2ee495f

18 Jun, 2011 2 commits
- Fix build if yasm is not available. · ed63f527
  Ronald S. Bultje authored 13 years ago
  
  ed63f527
- H.264: Add x86 assembly for 10-bit MC Chroma H.264 functions. · f188a1e0
  Daniel Kang authored 13 years ago
```
Mainly ported from 8-bit H.264 MC Chroma.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
```
  f188a1e0
14 Jun, 2011 1 commit

4:4:4 H.264 decoding support · c90b9442

Jason Garrett-Glaser authored 13 years ago

Note: this is 4:4:4 from the 2007 spec revision, not the previous (now deprecated) 4:4:4 mode in H.264.

c90b9442

13 Jun, 2011 2 commits
- Roll back 4:4:4 H.264 for now · 504811ba
  Jason Garrett-Glaser authored 13 years ago
```
Needs some ARM/PPC asm modifications.
```
  504811ba
- 4:4:4 H.264 decoding support · c9c49387
  Jason Garrett-Glaser authored 13 years ago
```
Note: this is 4:4:4 from the 2007 spec revision, not the previous (now deprecated) 4:4:4 mode in H.264.
```
  c9c49387
11 May, 2011 1 commit
- Port x86 10-bit H.264 deblock asm from x264 · 9f3d6ca4
  Jason Garrett-Glaser authored 13 years ago
  
  9f3d6ca4
10 May, 2011 1 commit

Adds 8-, 9- and 10-bit versions of some of the functions used by the h264 decoder. · 19a0729b

Oskar Arvidsson authored 13 years ago

This patch lets e.g. dsputil_init chose dsp functions with respect to
the bit depth to decode. The naming scheme of bit depth dependent
functions is <base name>_<bit depth>[_<prefix>] (i.e. the old
clear_blocks_c is now named clear_blocks_8_c).

Note: Some of the functions for high bit depth is not dependent on the
bit depth, but only on the pixel size. This leaves some room for
optimizing binary size.

Preparatory patch for high bit depth h264 decoding support.
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>

19a0729b

27 Apr, 2011 1 commit
- Move png mmx functions into x86/png_mmx.c, remove them from DSPContext. · 6d4c49a2
  Baptiste Coudurier authored 13 years ago
```
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>
```
  6d4c49a2
10 Apr, 2011 1 commit

Adds 8-, 9- and 10-bit versions of some of the functions used by the h264 decoder. · 8dbe5856

Oskar Arvidsson authored 13 years ago

This patch lets e.g. dsputil_init chose dsp functions with respect to
the bit depth to decode. The naming scheme of bit depth dependent
functions is <base name>_<bit depth>[_<prefix>] (i.e. the old
clear_blocks_c is now named clear_blocks_8_c).

Note: Some of the functions for high bit depth is not dependent on the
bit depth, but only on the pixel size. This leaves some room for
optimizing binary size.

Preparatory patch for high bit depth h264 decoding support.
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

8dbe5856

26 Mar, 2011 1 commit
- dsputil: allow to skip drawing of top/bottom edges. · 1500be13
  Alexander Strange authored 13 years ago
  
  1500be13
23 Mar, 2011 1 commit
- Add apply_window_int16() to DSPContext with x86-optimized versions and use it · e6e98234
  Justin Ruggles authored 13 years ago
```
in the ac3_fixed encoder.
```
  e6e98234
22 Mar, 2011 1 commit
- Fake-Merge remote-tracking branch 'ffmpeg-mt/master' · d375c104
  Michael Niedermayer authored 13 years ago
  
  d375c104
19 Mar, 2011 1 commit
- Replace FFmpeg with Libav in licence headers · 2912e87a
  Mans Rullgard authored 13 years ago
```
Signed-off-by: Mans Rullgard <mans@mansr.com>
```
  2912e87a
20 Feb, 2011 1 commit
- dsputil_mmx.c: remove ff_vector128. · 6a717eb4
  Ronald S. Bultje authored 14 years ago
```
Remove ff_vector128, it is identical to ff_pb_80.
(cherry picked from commit bf6fa732)
```
  6a717eb4
19 Feb, 2011 1 commit
- dsputil_mmx.c: remove ff_vector128. · bf6fa732
  Ronald S. Bultje authored 14 years ago
```
Remove ff_vector128, it is identical to ff_pb_80.
```
  bf6fa732
18 Feb, 2011 1 commit
- dsputil: move VC1-specific stuff into VC1DSPContext. · 9a1ced32
  Ronald S. Bultje authored 14 years ago
```
(cherry picked from commit 12802ec0)
```
  9a1ced32
17 Feb, 2011 1 commit
- dsputil: move VC1-specific stuff into VC1DSPContext. · 12802ec0
  Ronald S. Bultje authored 14 years ago
  
  12802ec0
04 Feb, 2011 1 commit

Separate format conversion DSP functions from DSPContext. · fe2ff6d2

Justin Ruggles authored 14 years ago

This will be beneficial for use with the audio conversion API without
requiring it to depend on all of dsputil.
Signed-off-by: Mans Rullgard <mans@mansr.com>
(cherry picked from commit c73d99e6)

fe2ff6d2

02 Feb, 2011 4 commits

Separate format conversion DSP functions from DSPContext. · c73d99e6

Justin Ruggles authored 14 years ago

This will be beneficial for use with the audio conversion API without
requiring it to depend on all of dsputil.
Signed-off-by: Mans Rullgard <mans@mansr.com>

c73d99e6

Implement a SIMD version of emulated_edge_mc() for x86. · baffa091

Ronald S. Bultje authored 14 years ago

From ~550 cycles (C version) to 170 (SSE/x86-64), 206 (MMX/x86-32)
and 196 (SSE2/x86-32) cycles.
(cherry picked from commit 81f2a3f4)

baffa091

cosmetics: indentation · 389b5bfa

Justin Ruggles authored 14 years ago

Signed-off-by: Mans Rullgard <mans@mansr.com>
(cherry picked from commit d19b744a)

389b5bfa

Remove unneeded add bias from 3 functions. · a8ae4e0e

Justin Ruggles authored 14 years ago

DSPContext.vector_fmul_window()
DCADSPContext.lfe_fir()
SynthFilterContext.synth_filter_float()
Signed-off-by: Mans Rullgard <mans@mansr.com>
(cherry picked from commit 80ba1ddb)

a8ae4e0e

01 Feb, 2011 1 commit
- Implement a SIMD version of emulated_edge_mc() for x86. · 81f2a3f4
  Ronald S. Bultje authored 14 years ago
```
From ~550 cycles (C version) to 170 (SSE/x86-64), 206 (MMX/x86-32)
and 196 (SSE2/x86-32) cycles.
```
  81f2a3f4
31 Jan, 2011 2 commits

cosmetics: indentation · d19b744a
Justin Ruggles authored 14 years ago
```
Signed-off-by: Mans Rullgard <mans@mansr.com>
```
d19b744a

Remove unneeded add bias from 3 functions. · 80ba1ddb

Justin Ruggles authored 14 years ago

DSPContext.vector_fmul_window()
DCADSPContext.lfe_fir()
SynthFilterContext.synth_filter_float()
Signed-off-by: Mans Rullgard <mans@mansr.com>

80ba1ddb

23 Jan, 2011 1 commit
- Change DSPContext.vector_fmul() from dst=dst*src to dest=src0*src1. · 015f9f1a
  Justin Ruggles authored 14 years ago
```
Signed-off-by: Mans Rullgard <mans@mansr.com>
(cherry picked from commit 6eabb0d3)
```
  015f9f1a
22 Jan, 2011 1 commit
- Change DSPContext.vector_fmul() from dst=dst*src to dest=src0*src1. · 6eabb0d3
  Justin Ruggles authored 14 years ago
```
Signed-off-by: Mans Rullgard <mans@mansr.com>
```
  6eabb0d3