x265

log

age author description
Fri, 24 Apr 2015 16:07:42 -0500 Steve Borho search: rename setQP() method to setLambdaFromQPdefault tip
Fri, 24 Apr 2015 16:05:19 -0500 Steve Borho analysis: nits
Fri, 24 Apr 2015 19:22:48 +0530 Rajesh Paulraj asm: avx2 10bit code for add_ps for chroma sizes 16xN, 32xN, reuse luma code
Fri, 24 Apr 2015 19:20:36 +0530 Rajesh Paulraj asm: avx2 10bit code for add_ps[16x16],[32x32],[64x64]
Fri, 24 Apr 2015 14:10:55 +0530 Divya Manivannan asm: add pixel restoration part in saoCuOrgE2 primitive
Fri, 24 Apr 2015 13:47:58 +0530 Divya Manivannan asm: avx2 code for sign primitive: improve 204c->114c
Fri, 24 Apr 2015 16:44:32 +0530 Sumalatha Polureddy asm: avx2 code for chroma vps filter for i444
Fri, 24 Apr 2015 15:32:14 +0530 Sumalatha Polureddy asm: avx2 code for chroma vps filter for i422
Fri, 24 Apr 2015 13:49:59 +0530 Sumalatha Polureddy asm: avx2 code for chroma vsp filter for i444
Fri, 24 Apr 2015 12:07:52 +0530 Sumalatha Polureddy asm: avx2 code for chroma vsp filter for i422
Fri, 24 Apr 2015 21:46:01 +0800 Min Chen rdoQuant: optimize getSigCtxInc()
Fri, 24 Apr 2015 21:45:58 +0800 Min Chen rdoQuant: split coeff cost into psy and non-psy path
Fri, 24 Apr 2015 21:45:55 +0800 Min Chen fix build fault on WinXP
Thu, 23 Apr 2015 12:32:49 -0500 Steve Borho smoke-test: set a higher VBV tolerance for the smoke test
Thu, 23 Apr 2015 19:10:41 +0530 Rajesh Paulraj asm: avx2 10bit code for sub_ps for chroma sizes 16xN, 32xN, reuse luma code
Thu, 23 Apr 2015 19:07:34 +0530 Rajesh Paulraj asm: avx2 10bit code for sub_ps[16x16],[32x32],[64x64]
Thu, 23 Apr 2015 18:48:23 +0530 Divya Manivannan asm: saoCuOrgE2[1] avx2 code: improve 449c->292c
Thu, 23 Apr 2015 18:40:34 +0530 Divya Manivannan asm: saoCuOrgE2[0] avx2 code: improve 154c->128c
Thu, 23 Apr 2015 18:13:13 +0530 Divya Manivannan sao: modify saoCuOrgE2 primitive to handle width=16 separately
Thu, 23 Apr 2015 15:17:45 +0530 Sumalatha Polureddy asm: avx2 code for chroma vss filter for i444
Thu, 23 Apr 2015 12:20:44 +0530 Sumalatha Polureddy asm: avx2 code chroma vss filter for i422
Wed, 22 Apr 2015 21:35:55 -0500 Steve Borho cli: document --qpstep
Wed, 22 Apr 2015 14:06:20 -0700 David T Yuen Invoke macro to setup sse2 intrapred dc and planar primitives
Wed, 22 Apr 2015 15:22:56 -0500 Steve Borho Merge with stable
Wed, 22 Apr 2015 15:22:03 -0500 Steve Borho doc: correct --qpstepstable
Wed, 22 Apr 2015 11:06:24 -0500 Steve Borho threadpool: use Win7 version macro directly, for more clarity
Wed, 22 Apr 2015 21:31:23 +0800 Min Chen testbench: fix table fault when trSize more than 8
Wed, 22 Apr 2015 21:31:19 +0800 Min Chen asm: avx2+-bmi2 version of scanPosLast, 27.6k -> 6.8k cycles
Wed, 22 Apr 2015 21:31:15 +0800 Min Chen testbench: fix testbench crash when no coeff in block
Wed, 22 Apr 2015 21:31:11 +0800 Min Chen testbench: support BMI2
Wed, 22 Apr 2015 21:30:37 +0800 Min Chen asm: rename findPosLast to scanPosLast and modify its API
Wed, 22 Apr 2015 21:30:33 +0800 Min Chen asm: fix bug in generic version findPosLast_x64 and improve testbench on it
Wed, 22 Apr 2015 19:52:06 +0530 Rajesh Paulraj asm: avx2 10bit code for scale2D_64to32
Wed, 22 Apr 2015 11:27:39 +0530 Dnyaneshwar G asm: avx2 code for satd_48x64 and 64xN, improved over +AH4-50% than SSE
Wed, 22 Apr 2015 11:19:18 +0530 Dnyaneshwar G asm: avx2 code for satd_16xN, improved over +AH4-50% than SSE code
Wed, 22 Apr 2015 12:25:09 +0530 Divya Manivannan asm: saoCuOrgE3 avx2 code for width>16: improve 508c->427c
Wed, 22 Apr 2015 11:59:36 +0530 Divya Manivannan sao: remove saoCuOrgE3_2Rows function and modify saoCuOrgE3 primitive to handle width=16 seperately
Tue, 21 Apr 2015 20:37:47 -0700 David T Yuen asm: interp_4tap_horiz_pp sse3
Wed, 22 Apr 2015 00:00:39 -0500 Steve Borho Merge with stable
Tue, 21 Apr 2015 23:50:09 -0500 Steve Borho doc: correct frame thread docsstable
Tue, 21 Apr 2015 13:42:36 -0500 Steve Borho threadpool: fix 'enumeral and non-enumeral type in conditional ...' warnings
Tue, 21 Apr 2015 13:28:37 -0500 Steve Borho asm: disable new findPosLast - it is causing check failures / crashes
Tue, 21 Apr 2015 15:05:18 +0530 Gopu Govindaswamy slicetype: select best mvp using neighbor mvs satd cost for Lowres ME
Tue, 21 Apr 2015 14:25:14 +0530 Dnyaneshwar G asm: new optimized algorithm for satd, improved +AH4-25% over previous algorithm
Tue, 21 Apr 2015 14:46:26 +0530 Sumalatha Polureddy asm: avx code for chroma satd functions for all partitions of 422
Tue, 21 Apr 2015 14:35:30 +0800 Min Chen asm: generic x64 version of findPosLast
Mon, 20 Apr 2015 14:51:02 -0500 Steve Borho doc: if you break cpu auto-detection, you get to keep both halves
Mon, 20 Apr 2015 19:58:29 +0800 Min Chen asm: ssse3 version of findPosFirstLast, 365c -> 75c
Sun, 19 Apr 2015 16:44:04 +0800 Min Chen rdoQuant: move cgRdStats.sigCost0 outside from loop
Fri, 17 Apr 2015 21:31:26 +0800 Min Chen rdoQuant: fast zero-coeff path
Fri, 17 Apr 2015 21:31:23 +0800 Min Chen rdoQuant: improve coeff group block clean code
Fri, 17 Apr 2015 21:31:19 +0800 Min Chen rdoQuant: fast zero cost compute path
Mon, 20 Apr 2015 12:41:16 +0800 Min Chen rdoQuant: improve encoder +AH4-3.5% by modify all zero-coeff group scan and cost compute logic
Mon, 20 Apr 2015 18:54:53 +0530 Divya Manivannan sao: modify saoCuOrgE3_2Rows C code and add sse4 code
Thu, 09 Apr 2015 00:48:54 -0400 Steve Borho tests: add coverage for --qg-size
Thu, 09 Apr 2015 11:30:33 -0500 Steve Borho param: show quant-group size in logs, move AQ config into its own line
Thu, 09 Apr 2015 11:31:48 -0500 Steve Borho encoder: give param->rc.qgSize a sane default when dqp is not used
Thu, 09 Apr 2015 11:20:57 -0500 Steve Borho encoder: ignore param->rc.qgSize when delta-qp coding is disabled
Wed, 08 Apr 2015 11:52:50 +0530 Deepthi Nandakumar search: add RDcost measurement of DeltaQP to lower rdLevels
Sat, 18 Apr 2015 10:56:21 +0530 Deepthi Nandakumar entropy: after encodeCU, the CU structures need to be reset with the right QP