x265

log

age author description
Thu, 21 May 2015 16:34:48 +0530 Gopu Govindaswamy encoder: fix line feed issuedefault tip
Wed, 20 May 2015 18:16:40 +0530 Ashok Kumar Mishra Regression Test: added new command line --ref-limits in regression-tests.txt
Thu, 21 May 2015 12:04:46 +0530 Sumalatha Polureddy asm: avx2 code for sse_ss[64x64] for 10 bpp (7039 -> 4051)
Thu, 21 May 2015 11:58:50 +0530 Sumalatha Polureddy asm: avx2 code for sse_ss[32x32] for 10 bpp (1935 -> 1030)
Wed, 20 May 2015 12:17:44 -0500 Steve Borho doc: update --tune grain docs
Wed, 20 May 2015 11:53:06 -0500 Steve Borho Merge with stable
Wed, 20 May 2015 10:29:09 -0500 Steve Borho cli: delay calling showHelp until a param is allocated and defaultedstable
Tue, 19 May 2015 18:29:06 -0700 David T Yuen asm: interp_4tap_vert_pX_4xN sse2
Wed, 20 May 2015 10:29:09 -0500 Steve Borho cli: delay calling showHelp until a param is allocated and defaulted
Mon, 16 Mar 2015 20:19:33 -0500 Deepthi Nandakumar docs: document --limit-refs
Wed, 20 May 2015 16:10:42 +0530 Deepthi Nandakumar analysis: re-order cost calculation for early-outs
Mon, 18 May 2015 13:26:33 +0530 Ashok Kumar Mishra analysis: model the effectiveness of --limit-ref with RD 0/4
Mon, 18 May 2015 13:36:26 +0530 Ashok Kumar Mishra stats: with the CU reference limit, even 8x8 can have skipped motion searches
Mon, 18 May 2015 13:34:33 +0530 Ashok Kumar Mishra cli: connect --limit-refs to param.limitReferences
Mon, 18 May 2015 13:31:59 +0530 Ashok Kumar Mishra analysis: respect X265_REF_LIMIT_DEPTH with RD 0/4
Mon, 18 May 2015 13:24:42 +0530 Ashok Kumar Mishra stats: RD 0/4 profile effectiveness of avoiding intra if split CUs did not select it
Mon, 18 May 2015 13:22:19 +0530 Ashok Kumar Mishra analysis: skip intra in RD 0/4 if split was analyzed and no split CUs used intra
Mon, 18 May 2015 13:20:54 +0530 Ashok Kumar Mishra stats: profile effectiveness of reference limit masks
Mon, 18 May 2015 13:18:54 +0530 Ashok Kumar Mishra analysis: at RD 0/4 avoid motion references if not used by split blocks
Mon, 18 May 2015 12:46:18 +0530 Ashok Kumar Mishra analysis: re-order RD 0/4 analysis to do splits before ME or intra
Thu, 14 May 2015 11:36:52 +0530 Divya Manivannan asm: filter_vpp, filter_vps for 64xN in avx2
Wed, 20 May 2015 14:06:53 +0530 Rajesh Paulraj asm: avx2 10bit code for luma_hpp[4xN]
Wed, 20 May 2015 12:52:40 +0530 Dnyaneshwar G asm: removed duplicate constants in intrapred8.asm 8bpp, these constants are already defined into const-a.asm
Wed, 20 May 2015 12:49:59 +0530 Dnyaneshwar G asm: removed some duplicate constants in intrapred16.asm 16bpp
Wed, 20 May 2015 12:08:05 +0530 Deepthi Nandakumar param: tune grain disables rdoq-level. This provides better visual quality results
Wed, 20 May 2015 11:05:15 +0530 Sumalatha Polureddy asm: avx2 code for sad_x4[48x64] (33937 -> 15279) for 10 bpp
Tue, 19 May 2015 19:51:56 -0500 Steve Borho doc: fix formatting of code sample
Tue, 19 May 2015 17:04:04 +0530 Gopu Govindaswamy search: add lowres MV into search MV candidate list for search ME
Tue, 19 May 2015 17:47:36 +0530 Dnyaneshwar G asm: removed duplicate and redundant constants
Tue, 19 May 2015 14:30:03 +0530 Sumalatha Polureddy asm: avx2 code for sad_x4[64xN] for 10 bpp
Tue, 19 May 2015 13:59:32 +0530 Rajesh Paulraj asm: avx2 10bit code for luma_hpp[48x64] (82440.47 -> 44731.61)
Tue, 19 May 2015 14:11:35 +0530 Rajesh Paulraj asm: avx2 10bit code for luma_hpp[24x32] (18855.08 -> 10742.66)
Tue, 19 May 2015 13:10:20 +0530 Rajesh Paulraj asm: avx2 10bit code for luma_hpp[12x16] (5154.47 -> 3632.88)
Tue, 19 May 2015 12:55:49 +0530 Rajesh Paulraj asm: avx2 10bit code for luma_hpp[32xN],[64xN]
Tue, 19 May 2015 12:37:47 +0530 Rajesh Paulraj asm: avx2 10bit code for luma_hpp[16xN]
Tue, 19 May 2015 12:24:04 +0530 Rajesh Paulraj asm: avx2 10bit code for luma_hpp[8xN]
Tue, 19 May 2015 12:54:14 +0530 Sumalatha Polureddy asm: avx2 code for sad_x4[32xN] for 10 bpp
Tue, 19 May 2015 12:31:11 +0530 Sumalatha Polureddy asm: avx2 code for sad_x4[16xN] for 10 bpp
Mon, 18 May 2015 18:03:19 +0530 Dnyaneshwar G asm: avx2 code for psyCost_pp 8x8, 16x16, 32x32 & 64x64, improved over 40% than previous asm
Tue, 19 May 2015 10:40:00 +0530 Sumalatha Polureddy asm: avx2 code for sad_x3[48x64] for 10 bpp (25339 -> 11730)
Mon, 18 May 2015 18:24:08 -0500 Steve Borho Merge with stable
Thu, 14 May 2015 12:52:34 -0500 Steve Borho api: introduce a less version strict API query
Mon, 18 May 2015 18:18:40 -0500 Steve Borho Added tag 1.7 for changeset 8425278def1estable
Mon, 18 May 2015 13:39:44 -0500 Steve Borho api: fix x265.h documentation for x265_max_bit_depthstable 1.7
Fri, 15 May 2015 19:29:09 -0700 Min Chen improve by replace condition operator to mask based
Fri, 15 May 2015 17:30:24 -0700 Min Chen reuse coeffFlag to reduce memory operator on coeff[] memory
Fri, 15 May 2015 17:30:22 -0700 Min Chen modify logic to remove lastCG in Quant::signBitHidingHDQ()
Fri, 15 May 2015 17:30:19 -0700 Min Chen faster algorithm to find firstNZPosInCG & lastNZPosInCG in Quant::signBitHidingHDQ()
Mon, 18 May 2015 09:58:15 -0500 Min Chen improve Quant::signBitHidingHDQ by scanPosLast and findPosFirstLast
Mon, 18 May 2015 09:58:08 -0500 Min Chen asm: modify API on findPosFirstLast to support all zeros block
Mon, 18 May 2015 12:32:04 +0530 Sumalatha Polureddy asm: avx2 code for sad_x3[64xN] for 10 bpp
Mon, 18 May 2015 12:13:37 +0530 Sumalatha Polureddy asm: avx2code fore sad_x3[32xN] for 10bpp
Mon, 18 May 2015 12:03:30 +0530 Sumalatha Polureddy asm: avx2 code for sad_x3[16xN] for 10 bpp
Sun, 17 May 2015 19:41:24 -0700 David T Yuen Call macros to reduce code size of primitive setup
Sun, 17 May 2015 19:29:32 -0700 David T Yuen asm: interp_4tap_vert_ps_64xN and interp_4tap_vert_ps_48x64 sse2
Sun, 17 May 2015 19:22:41 -0700 David T Yuen asm: interp_4tap_vert_ps_32xN sse2
Sun, 17 May 2015 19:13:36 -0700 David T Yuen asm: interp_4tap_vert_ps_24xN sse2
Sun, 17 May 2015 19:06:51 -0700 David T Yuen asm: interp_4tap_vert_ps_16xN sse2
Sun, 17 May 2015 19:00:41 -0700 David T Yuen asm: interp_4tap_vert_ps_12xN sse2
Sun, 17 May 2015 18:53:44 -0700 David T Yuen asm: interp_4tap_vert_ps_8xN sse2