summaryrefslogtreecommitdiffstats
path: root/libavcodec/h264_loopfilter.c
Commit message (Expand)AuthorAgeFilesLines
...
* Unroll loops in check_mv()Michael Niedermayer2010-01-281-14/+17
* Factor mv/ref compare code out.Michael Niedermayer2010-01-281-80/+26
* Simplify first edge filter condition.Michael Niedermayer2010-01-281-3/+1
* Cosmetics, mostly indention, 2 or so new fixme comments that i was to lazyMichael Niedermayer2010-01-281-128/+128
* Make the fast loop filter path work with unavailable left MBs.Michael Niedermayer2010-01-281-4/+12
* get rid of the start variable.Michael Niedermayer2010-01-281-10/+7
* Unroll main loop so the edge==0 case is seperate.Michael Niedermayer2010-01-281-27/+121
* Update comment.Michael Niedermayer2010-01-271-1/+1
* Use table to speedup access to non_zero_count in MBAFF with differing interla...Michael Niedermayer2010-01-271-1/+11
* Optimize loop filtering of the left edge in MBAFF.Michael Niedermayer2010-01-261-8/+9
* remove unneeded checkMichael Niedermayer2010-01-261-2/+0
* Use left_mb_xy from fill_caches instead of recalculating it.Michael Niedermayer2010-01-261-5/+3
* Simplify loop filter a little by using top/left_type.Michael Niedermayer2010-01-261-11/+9
* Remove all uses of slice_type* from the loop filter, also remove itsMichael Niedermayer2010-01-241-5/+5
* Move +52 from the loop filter to the alpha/beta offsets in the context.Michael Niedermayer2010-01-231-15/+15
* Set edges based on cbp and mv partitioning, not just skiped MBs.Michael Niedermayer2010-01-231-2/+2
* Optimize filter_mb_mbaff_edge*()Michael Niedermayer2010-01-231-14/+8
* Optmize 8x8dct check used to skip some borders in the loop filter.Michael Niedermayer2010-01-231-1/+1
* Move array specifiers outside DECLARE_ALIGNED() invocationsMåns Rullgård2010-01-221-4/+4
* Gcc idiocy fixes related to filter_mb_edge*.Michael Niedermayer2010-01-221-62/+62
* Make calculation of mask_edge free of branches, faster of course but probablyMichael Niedermayer2010-01-211-2/+3
* H.264: Declare bS with DECLARE_ALIGNED_8 for uint64_t casts.Alexander Strange2010-01-201-3/+3
* Simplify/Optimize another of the mbaff loop filter cases.Michael Niedermayer2010-01-201-9/+6
* Only calculate the second chroma qp if it differs from the firstin the mainMichael Niedermayer2010-01-201-8/+10
* Set bS with 64bits at a time.Michael Niedermayer2010-01-201-4/+5
* Merge multiple IS_* macro uses where possible.Michael Niedermayer2010-01-201-5/+3
* Simplify and optimize intra code in h264_loopfilter.cMichael Niedermayer2010-01-201-12/+5
* Sightly simplify initialization of int start.Michael Niedermayer2010-01-201-7/+3
* Reenable ff_h264_filter_mb_fast() for all slices it supported before.Michael Niedermayer2010-01-191-3/+0
* Fix compilation with -O0.Michael Niedermayer2010-01-181-4/+0
* Rather call filter_mb_mbaff_edge*v() more often than do extra calculationsMichael Niedermayer2010-01-181-23/+25
* Use h->slice_num where possible.Michael Niedermayer2010-01-181-4/+4
* Enable filter_mb_fast for CAVLC P slices.Michael Niedermayer2010-01-181-1/+1
* PAFF CABAC P slices seem to work as well, so enable them for ff_h264_filter_m...Michael Niedermayer2010-01-181-1/+1
* Reenable filter_mb_fast for I slices and progressive CABAC P slices.Michael Niedermayer2010-01-181-2/+4
* Move CAVLC 8x8 DCT special case from ff_h264_filter_mb() to fill_cachesMichael Niedermayer2010-01-181-37/+0
* Perform reference remapping at fill_cache() time instead of in theMichael Niedermayer2010-01-181-7/+4
* Move the qp check to skip the loop filter up.Michael Niedermayer2010-01-181-11/+0
* Reorganize how values are stored in h->non_zero_count.Michael Niedermayer2010-01-171-33/+2
* Rearchitecturing the stiched up goose part 1Michael Niedermayer2010-01-171-5/+35
* Comment for() ; outMichael Niedermayer2010-01-161-1/+1
* Mark a few functions as noinline, this makes ff_h264_filter_mb() a bit smallerMichael Niedermayer2010-01-161-4/+4
* Apply last 2 optimizations to similar code i forgot.Michael Niedermayer2010-01-161-4/+4
* Another microopt, 4 cpu cycles for avoidance of FFABS().Michael Niedermayer2010-01-161-2/+2
* Minor (2 cpu cycles) optimization ||->|.Michael Niedermayer2010-01-161-4/+4
* Avoid wasting 4 cpu cycles per MB in redundantly calculating qp_thresh.Michael Niedermayer2010-01-161-1/+1
* Split h264 loop filter off h264.c.Michael Niedermayer2010-01-121-0/+771
OpenPOWER on IntegriCloud