summaryrefslogtreecommitdiffstats
path: root/libavcodec/rv34dsp.h
Commit message (Collapse)AuthorAgeFilesLines
* Merge commit '368f50359eb328b0b9d67451f56fda20b3255f9a'Michael Niedermayer2014-05-301-1/+1
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * commit '368f50359eb328b0b9d67451f56fda20b3255f9a': dsputil: Split off quarterpel bits into their own context Conflicts: configure libavcodec/dsputil.c libavcodec/h263dec.c libavcodec/mpegvideo.c libavcodec/mpegvideo_enc.c libavcodec/vc1dec.c libavcodec/vc1dsp.c libavcodec/x86/dsputil_init.c libavcodec/x86/qpeldsp.asm Merged-by: Michael Niedermayer <michaelni@gmx.at>
| * dsputil: Split off quarterpel bits into their own contextDiego Biurrun2014-05-291-1/+1
| |
* | Merge commit '71617884a2a673908bd5c0f73d4f91fdca3da82a'Michael Niedermayer2014-01-151-0/+1
|\ \ | |/ | | | | | | | | | | * commit '71617884a2a673908bd5c0f73d4f91fdca3da82a': aarch64: h264 chroma motion compensation NEON optimizations Merged-by: Michael Niedermayer <michaelni@gmx.at>
| * aarch64: h264 chroma motion compensation NEON optimizationsJanne Grunau2014-01-151-0/+1
| | | | | | | | | | Since RV40 and VC-1 use almost the same algorithm so optimizations for those two decoders are easy to do and included.
* | Reinstate proper FFmpeg license for all files.Thilo Borgmann2013-08-301-4/+4
|/
* rv34: Drop now unnecessary dsputil dependenciesDiego Biurrun2013-02-061-7/+7
|
* dsputil: Separate h264chromaDiego Biurrun2013-02-061-0/+1
|
* Drop DCTELEM typedefDiego Biurrun2013-01-221-2/+2
| | | | | | It does not help as an abstraction and adds dsputil dependencies. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
* arm: call arm-specific rv34dsp init functions under if (ARCH_ARM)Jean-Baptiste Kempf2012-10-101-2/+2
| | | | | | | Assign NEON specific function pointers after runtime check via av_get_cpu_flags(). Signed-off-by: Janne Grunau <janne-libav@jannau.net>
* rv40dsp: implement prescaled versions for biweight.Christophe GISQUET2012-04-101-1/+6
| | | | | | | | | | Quite often, the original weights are multiple of 512. By prescaling them by 1/512 when they are computed (once per frame), no intermediate shifting is needed, and no prescaling on each call either. The x86 code already used that trick. Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
* rv34: change most "int stride" into "ptrdiff_t stride".Ronald S. Bultje2012-02-201-6/+6
| | | | | | This prevents having to sign-extend on 64-bit systems with 32-bit ints, such as x86-64. Also fixes crashes on systems where we don't do it and arguments are not in registers, such as Win64 for all weight functions.
* rv34: 1-pass inter MB reconstructionChristophe GISQUET2012-01-161-4/+3
| | | | Implement 1-pass inverse transform and reconstruction for inter blocks.
* rv34: Intra 16x16 handlingChristophe GISQUET2012-01-161-0/+7
| | | | | | | Extract processing of intra 16x16 blocks from intra macroblock processing. Also implement a function performing inverse transform and block reconstruction for DC-only blocks in 1 pass instead of 2.
* rv34: DC-only inverse transformChristophe GISQUET2012-01-121-0/+2
| | | | | | | | | | | | | | | When decoding coefficients, detect whether the block is DC-only, and take advantage of this knowledge to perform DC-only inverse transform. This is achieved by: - first, changing the 108x4 element modulo_three_table into a 108 element table (kind of base4), and accessing each value using mask and shifts. - then, checking low bits for 0 (as they represent the presence of higher frequency coefficients) Also provide x86 SIMD code for the DC-only inverse transform. Signed-off-by: Kostya Shishkov <kostya.shishkov@gmail.com>
* rv34: joint coefficient decoding and dequantizationChristophe GISQUET2012-01-041-1/+0
| | | | | | | | | | | Perform dequantization while decoding coefficients instead of performing it on the entire coefficients buffer. Since quantized coefficients are very sparse, this usually causes a small speedup. Speedup of around 1% on Panda board compared to the removed here neon code. Global speedup is probably around 3%. Signed-off-by: Kostya Shishkov <kostya.shishkov@gmail.com>
* rv40: rearrange loop filter functionsMans Rullgard2011-12-141-6/+15
| | | | | | | This splits the loop filter functions into smaller, more SIMD-friendly functions. Signed-off-by: Mans Rullgard <mans@mansr.com>
* rv34: move 4x4 dequant to RV34DSPContextMans Rullgard2011-12-131-0/+1
| | | | Signed-off-by: Mans Rullgard <mans@mansr.com>
* rv40: NEON optimised chroma MCJanne Grunau2011-12-061-0/+1
| | | | Signed-off-by: Mans Rullgard <mans@mansr.com>
* rv34: NEON optimised inverse transform functionsJanne Grunau2011-12-061-0/+2
| | | | Signed-off-by: Mans Rullgard <mans@mansr.com>
* rv40: move loop filter to rv34dsp contextJanne Grunau2011-11-301-0/+7
| | | | Signed-off-by: Mans Rullgard <mans@mansr.com>
* rv34: move inverse transform functions to DSP contextJanne Grunau2011-10-121-0/+4
|
* Add weighted motion compensation for RV40 B-framesKostya Shishkov2011-08-111-0/+6
| | | | Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
* Move RV3/4-specific DSP functions into their own contextKostya Shishkov2011-08-111-0/+44
Signed-off-by: Ronald S. Bultje <rsbultje@gmail.com>
OpenPOWER on IntegriCloud