[x265] [PATCH] stats: fix use of uninitialized pixels in maximum and average luma level calculation

# HG changeset patch # User Kavitha Sampath kavi...@multicorewareinc.com # Date 1439450035 -19800 # Thu Aug 13 12:43:55 2015 +0530 # Node ID ac3966a43ba77b609d0e209df80f3a3aac234c08 # Parent bc5a7c2ac38b06d2a232b983f10bc0394d252ad7 stats: fix use of uninitialized pixels in maximum and

Re: [x265] [PATCH 3 of 4] asm: fix bug in macro vpbroadcastd for case ymm, xmm

Hi Min, This still generates wrong code for case ymm, xmm (as %ifidni %2,xm will be false always). How about the below code ? %macro vpbroadcastd 2-3 ;; incresed one argument for case ymm, xmm %ifid %3 ; case vpbroadcastd ymm, ymm, xmm vpbroadcastd %1, %3 %elifid

[x265] [PATCH] quantOffsets: move allocation to frame::create

# HG changeset patch # User Deepthi Nandakumar deep...@multicorewareinc.com # Date 1439460179 -19800 # Thu Aug 13 15:32:59 2015 +0530 # Node ID 9d6ab81073afab38821da2f0b3f9c31fd77df93a # Parent bc5a7c2ac38b06d2a232b983f10bc0394d252ad7 quantOffsets: move allocation to frame::create diff -r

[x265] [PATCH] stats: fix use of uninitialized pixels in maximum and average luma level calculation

# HG changeset patch # User Kavitha Sampath kavi...@multicorewareinc.com # Date 1439458769 -19800 # Thu Aug 13 15:09:29 2015 +0530 # Node ID 27226b1c447f4df9cde5b7688f34fb8b7a86e193 # Parent bc5a7c2ac38b06d2a232b983f10bc0394d252ad7 stats: fix use of uninitialized pixels in maximum and

Re: [x265] [PATCH 2 of 4] improve ctuLumaLevel logic by Sad and CMOV

yes deepthi I will update the change in copyFromPic. On Thu, Aug 13, 2015 at 4:08 PM, Deepthi Nandakumar deep...@multicorewareinc.com wrote: Kavitha, Can you please pull this neat optimization of Min's into picyuv::copyFromPicture? On Thu, Aug 13, 2015 at 8:52 AM, Min Chen

[x265] [PATCH 2 of 4] asm: AVX2 asm for intra_ang_32 mode 6, improved over 48% than SSE asm

# HG changeset patch # User Dnyaneshwar G dnyanesh...@multicorewareinc.com # Date 1439366905 -19800 # Wed Aug 12 13:38:25 2015 +0530 # Node ID 643a001494a42e65366cfa3e468cc0858955095f # Parent 07110baa95f1d53c8100929b16eafba3b16138d6 asm: AVX2 asm for intra_ang_32 mode 6, improved over 48%

[x265] [PATCH 3 of 4] asm: AVX2 asm for intra_ang_32 mode 7, improved over 40% than SSE asm

# HG changeset patch # User Dnyaneshwar G dnyanesh...@multicorewareinc.com # Date 1439373105 -19800 # Wed Aug 12 15:21:45 2015 +0530 # Node ID c12d411014f68affea550ee640e26ba61f51e509 # Parent 643a001494a42e65366cfa3e468cc0858955095f asm: AVX2 asm for intra_ang_32 mode 7, improved over 40%

[x265] [PATCH 1 of 4] asm: AVX2 asm for intra_ang_32 mode 5, improved over 48% than SSE asm

# HG changeset patch # User Dnyaneshwar G dnyanesh...@multicorewareinc.com # Date 1439297628 -19800 # Tue Aug 11 18:23:48 2015 +0530 # Node ID 07110baa95f1d53c8100929b16eafba3b16138d6 # Parent bc5a7c2ac38b06d2a232b983f10bc0394d252ad7 asm: AVX2 asm for intra_ang_32 mode 5, improved over 48%

Re: [x265] [PATCH 4 of 4] Statistics maxLumaLevel in Frame Level

It is right place, we can make a new asm for it, thanks At 2015-08-13 18:32:15,Deepthi Nandakumar deep...@multicorewareinc.com wrote: Min, Kavitha's patch moved maxLumaLevel into copyFromPicture, which is the right place for this, since maxLumaLevel is calculated from input pic. On Thu,

Re: [x265] [PATCH] stats: fix use of uninitialized pixels in maximum and average luma level calculation

On 08/14, Deepthi Nandakumar wrote: I did a double take on the if (padx) part as well, then figured it works since padx is guaranteed to be non-zero (because of padx++). Min, can you do a quick profile on whether it is better to do this outside the padx loop, for the whole frame, or inside

Re: [x265] [PATCH] stats: fix use of uninitialized pixels in maximum and average luma level calculation

I did a double take on the if (padx) part as well, then figured it works since padx is guaranteed to be non-zero (because of padx++). Min, can you do a quick profile on whether it is better to do this outside the padx loop, for the whole frame, or inside the padx loop, one row at a time? On Thu,

Re: [x265] Why does cuTree function calculate the averageDuration by while loop

On 08/14, Ximing Cheng wrote: Hi, the source code in lookahead cuTree function has to calculate the averageDuration by a while loop each time, why not use double averageDuration = (double)m_param-fpsDenom / m_param-fpsNum; in the initial function of lookahead? Thanks! The cu-tree code was

[x265] [PATCH] getopt: remove double underscores from prototype arguments (fixes #162)

# HG changeset patch # User Steve Borho st...@borho.org # Date 1439523373 -19800 # Fri Aug 14 09:06:13 2015 +0530 # Node ID 25ddcc4f9f0ce7822373a74484ad237bc04e2b78 # Parent bc5a7c2ac38b06d2a232b983f10bc0394d252ad7 getopt: remove double underscores from prototype arguments (fixes #162) It

[x265] [PATCH] doc: fix typos and improve readability of threading chapter

# HG changeset patch # User Steve Borho st...@borho.org # Date 1439526505 -19800 # Fri Aug 14 09:58:25 2015 +0530 # Branch stable # Node ID 1b8ff853ad41b3a033b3c98213e9e51f37401b3e # Parent 567f9b1263a27b9384f10662c169615e62b8e2b3 doc: fix typos and improve readability of threading chapter

[x265] Why does cuTree function calculate the averageDuration by while loop

Hi, the source code in lookahead cuTree function has to calculate the averageDuration by a while loop each time, why not use double averageDuration = (double)m_param-fpsDenom / m_param-fpsNum; in the initial function of lookahead? Thanks! ___ x265-devel

[x265] [PATCH] picyuv: cleanup, remove always on padx, pady conditionals

# HG changeset patch # User Deepthi Nandakumar deep...@multicorewareinc.com # Date 1439530515 -19800 # Fri Aug 14 11:05:15 2015 +0530 # Node ID b4ef42c9a18922a48f44799b3d9f8d3e2f6912f2 # Parent 409d6f7461223eddc17db7a45747b2b6450ff10c picyuv: cleanup, remove always on padx, pady conditionals