Re: [x265] [PATCH] analysis: fix for rd-0 non-deterministic output

2015-08-03 Thread Steve Borho
On 07/28, as...@multicorewareinc.com wrote: # HG changeset patch # User Ashok Kumar Mishraas...@multicorewareinc.com # Date 1438080030 -19800 # Tue Jul 28 16:10:30 2015 +0530 # Node ID dbe8c629ccc726ece98ffbe4af5c78f8945e84a5 # Parent e08a245054434090ccb1fc1b985f955a66711157 analysis:

Re: [x265] x265 CPU utilization very low on a multi-numa sockets server

2015-08-03 Thread Steve Borho
On 08/03, Ximing Cheng wrote: I found the lookahead JobProvider only process its tasks on the threadpool zero (the first threadpool), this will destroy the load balance of the muti-threadpool system as the frame encoders are distributed on the muti-threadpool by round robin. The encoder could

[x265] [PATCH] pools: FE threads start from pool 1, since lookahead is assigned to pool 0

2015-08-03 Thread deepthi
# HG changeset patch # User Deepthi Nandakumar deep...@multicorewareinc.com # Date 1438650477 -19800 # Tue Aug 04 06:37:57 2015 +0530 # Node ID 38f5c6c98ebf2ae934bb512df39120dbfec14401 # Parent d5278c76d341b3bac405938dbfb64cb7e2d9bce5 pools: FE threads start from pool 1, since lookahead is

[x265] [PATCH] framedata: rely on thread pool getNumaNodeCount() and m_numaNode to work

2015-08-03 Thread Steve Borho
# HG changeset patch # User Steve Borho st...@borho.org # Date 1438659560 18000 # Mon Aug 03 22:39:20 2015 -0500 # Node ID a1b90e16cf25cb08f63866357566d0164f404cc9 # Parent 642e40276ab81696f5a6b342d8d71345f4e58339 framedata: rely on thread pool getNumaNodeCount() and m_numaNode to work diff

[x265] [PATCH 1 of 2 EXPERIMENTAL] slice: prep work for per-numa recon picture copies

2015-08-03 Thread Steve Borho
# HG changeset patch # User Steve Borho st...@borho.org # Date 1438642558 18000 # Mon Aug 03 17:55:58 2015 -0500 # Node ID 02e84edaa14399a3a68ade8617c63422f51a305b # Parent 1f161d9c6e35e32998d38ebf5b6dec96f1ef43e2 slice: prep work for per-numa recon picture copies Rename slice.m_refPicList

[x265] [PATCH] asm: avx2 code for pixelavg_pp 32xN 64xN, improved over 40% than SSE

2015-08-03 Thread dnyaneshwar
# HG changeset patch # User Dnyaneshwar G dnyanesh...@multicorewareinc.com # Date 1438596650 -19800 # Mon Aug 03 15:40:50 2015 +0530 # Node ID 43fe4ec1c13a2514030010c2cd699382b67f65cb # Parent a3b72e2a25a7fc544b1b76e872eda012035bf4ac asm: avx2 code for pixelavg_pp 32xN 64xN, improved over

Re: [x265] [PATCH 2 of 2] threadpool: fix calculation of JobProviders

2015-08-03 Thread Steve Borho
On 07/27, deep...@multicorewareinc.com wrote: # HG changeset patch # User Deepthi Nandakumar deep...@multicorewareinc.com # Date 1437986236 -19800 # Mon Jul 27 14:07:16 2015 +0530 # Node ID dc446bc5df507d857c3f72ba595a95e981c0258d # Parent eb6b04fc06a37a0cfbc70d30f364ec62cbb909d4

Re: [x265] [PATCH] asm: disabled avx2 primitives having less than 3% speed up over SSE

2015-08-03 Thread Steve Borho
On 08/03, dnyanesh...@multicorewareinc.com wrote: # HG changeset patch # User Dnyaneshwar G dnyanesh...@multicorewareinc.com # Date 1438601406 -19800 # Mon Aug 03 17:00:06 2015 +0530 # Node ID 324eedb6186497f8691e68095e0f31a8630268b8 # Parent 43fe4ec1c13a2514030010c2cd699382b67f65cb

[x265] [PATCH] vui: tweak the string name of ARIB STD-B67, to avoid possible future conflicts

2015-08-03 Thread Steve Borho
# HG changeset patch # User Steve Borho st...@borho.org # Date 1438631781 18000 # Mon Aug 03 14:56:21 2015 -0500 # Node ID 1f161d9c6e35e32998d38ebf5b6dec96f1ef43e2 # Parent d5278c76d341b3bac405938dbfb64cb7e2d9bce5 vui: tweak the string name of ARIB STD-B67, to avoid possible future conflicts