I ran the executables in arena.
Depth...Time Nodes......nps......score...PV
30/35 07:26 843.637k 1.888k +0,19 d2-d4 d7-d5 Sg1-f3
So I get 1888k nodes/sec instead of 1663k nodes/sec
regards
Bernhard
Stockfish haswell optimized build
Moderators: hgm, Rebel, chrisw
-
Vinvin
- Posts: 5228
- Joined: Thu Mar 09, 2006 9:40 am
- Full name: Vincent Lejeune
Re: Some numbers
Try the "bench" command to get more accurate results.BBauer wrote:I ran the executables in arena.
Depth...Time Nodes......nps......score...PV
30/35 07:26 843.637k 1.888k +0,19 d2-d4 d7-d5 Sg1-f3
So I get 1888k nodes/sec instead of 1663k nodes/sec
regards
Bernhard
-
syzygy
- Posts: 5566
- Joined: Tue Feb 28, 2012 11:56 pm
Re: Some numbers
No, you have added -fno-tree-pre on gcc-4.8, as I once recommended on this forum. That is indepedent of -march=native.BBauer wrote:So the native compile gives a 10% speedup.