Page 1 of 4
Stockfish 8 - Double time control vs. 2 threads
Posted: Tue Nov 15, 2016 8:26 pm
by fastgm
Stockfish 8
1 thread (5 minutes + 3 seconds) vs. 2 threads (2.5 minutes + 1.5 seconds)
Code: Select all
Program Elo + - Games Score Av.Op. Draws
----------------------------------------------------------------------------------------
1 Stockfish 8 - 1 thread 5' + 3" : 3003 5 5 3000 51.0 % 2997 85.2 %
2 Stockfish 8 - 2 threads 2.5' + 1.5" : 2997 5 5 3000 49.0 % 3003 85.2 %
Av.Op. Elo = 3000
Result : 1529.0/3000 (+251,=2556,-193)
Perf. : 51.0 %
Margins :
68 % : (+ 0.3,- 0.3 %) -> [ 50.6, 51.3 %]
95 % : (+ 0.7,- 0.7 %) -> [ 50.3, 51.7 %]
99.7 % : (+ 1.0,- 1.0 %) -> [ 49.9, 52.0 %]
Elo : 3007
Margins :
68 % : (+ 2,- 2) -> [3004,3009]
95 % : (+ 5,- 5) -> [3002,3012]
99.7 % : (+ 7,- 7) -> [3000,3014]
Games : 3000 (finished)
White Wins : 341 (11.4 %)
Black Wins : 103 ( 3.4 %)
Draws : 2556 (85.2 %)
White Perf. : 54.0 %
Black Perf. : 46.0 %
Individual statistics:
1 Stockfish 8 - 1 thread 5' + 3" : 3003 3000 (+251,=2556,-193), 51.0 %
2 Stockfish 8 - 2 threads 2.5' + 1.5" : 2997 3000 (+193,=2556,-251), 49.0 %
Re: Stockfish 8 - Double time control vs. 2 threads
Posted: Wed Nov 16, 2016 8:51 pm
by ernest
Very interesting, Andreas, thanks !!!
Re: Stockfish 8 - Double time control vs. 2 threads
Posted: Wed Nov 16, 2016 9:34 pm
by Laskos
Interesting as usual, thanks! From your previous thread we already know that doubling time at this time control is worth about 90 ELO points. Here the difference is 6+/-5 ELO points. Means 0.067 doublings. This means that the effective speed-up 1 -> 2 threads is 2^(1-0.067) ~ 1.91. For the first time it is measured so precisely for Lazy SMP engine. With YBW SMP like in Crafty time-to-depth can be used.
Re: Stockfish 8 - Double time control vs. 2 threads
Posted: Wed Nov 16, 2016 11:22 pm
by ernest
Laskos wrote:Interesting as usual, thanks! From your previous thread we already know that doubling time at this time control is worth about 90 ELO points. Here the difference is 6+/-5 ELO points. Means 0.067 doublings. This means that the effective speed-up 1 -> 2 threads is 2^(1-0.067) ~ 1.91. For the first time it is measured so precisely for Lazy SMP engine. With YBW SMP like in Crafty time-to-depth can be used.
These numbers, 90 Elo and 1.91, seem high.
Is it because they result from games engine vs same engine ?
Re: Stockfish 8 - Double time control vs. 2 threads
Posted: Thu Nov 17, 2016 9:06 am
by Laskos
ernest wrote:Laskos wrote:Interesting as usual, thanks! From your previous thread we already know that doubling time at this time control is worth about 90 ELO points. Here the difference is 6+/-5 ELO points. Means 0.067 doublings. This means that the effective speed-up 1 -> 2 threads is 2^(1-0.067) ~ 1.91. For the first time it is measured so precisely for Lazy SMP engine. With YBW SMP like in Crafty time-to-depth can be used.
These numbers, 90 Elo and 1.91, seem high.
Is it because they result from games engine vs same engine ?
The results of Komodo 9.3 self-play, which I would think also apply to Srockfish 8 self-play, were presented by Andreas here:
http://www.talkchess.com/forum/viewtopi ... 84&start=0
At this time control, about 93 ELO points for doublig of Komodo, hence 1.91 effective speed-up 1->2 threads for Stockfish 8. It's not unexpected, 1->2 threads scale very well, with Lazy or YBW SMP, but Andreas' measurement is the most precise one up to date for Lazy SMP. It can only be measured through games, not NPS, time-to-depth and other easier methods.
Re: Stockfish 8 - Double time control vs. 2 threads
Posted: Fri Nov 18, 2016 12:05 pm
by Werewolf
Laskos wrote:Interesting as usual, thanks! From your previous thread we already know that doubling time at this time control is worth about 90 ELO points. Here the difference is 6+/-5 ELO points. Means 0.067 doublings. This means that the effective speed-up 1 -> 2 threads is 2^(1-0.067) ~ 1.91. For the first time it is measured so precisely for Lazy SMP engine. With YBW SMP like in Crafty time-to-depth can be used.
Wow. That's a big upgrade from the standard a few years ago when Rybka ruled: "A doubling of cores is 1.7x faster"
This may have huge implications for hyper threading and monstrously big machines with high core counts.
Stockfish 8 - Quadruple time control vs. 4 threads
Posted: Tue Nov 22, 2016 6:36 pm
by fastgm
Stockfish 8
1 thread (5 minutes + 3 seconds) vs. 4 threads (75 seconds + 0.75 seconds)
Code: Select all
Program Elo + - Games Score Av.Op. Draws
----------------------------------------------------------------------------------------
1 Stockfish 8 - 1 thread 5' + 3" : 3009 5 5 3000 52.6 % 2991 83.9 %
2 Stockfish 8 - 4 threads 75" + 0.75" : 2991 5 5 3000 47.4 % 3009 83.9 %
Wins = 320
Draws = 2516
Losses = 164
Av.Op. Elo = 3000
Result : 1578.0/3000 (+320,=2516,-164)
Perf. : 52.6 %
Margins :
68 % : (+ 0.4,- 0.4 %) -> [ 52.2, 53.0 %]
95 % : (+ 0.7,- 0.7 %) -> [ 51.9, 53.3 %]
99.7 % : (+ 1.1,- 1.1 %) -> [ 51.5, 53.7 %]
Elo : 3018
Margins :
68 % : (+ 3,- 3) -> [3016,3021]
95 % : (+ 5,- 5) -> [3013,3023]
99.7 % : (+ 8,- 7) -> [3011,3026]
Games : 3000 (finished)
White Wins : 362 (12.1 %)
Black Wins : 122 ( 4.1 %)
Draws : 2516 (83.9 %)
White Perf. : 54.0 %
Black Perf. : 46.0 %
Individual statistics:
1 Stockfish 8 - 1 thread 5' + 3" : 3009 3000 (+320,=2516,-164), 52.6 %
2 Stockfish 8 - 4 threads 75" + 0.75" : 2991 3000 (+164,=2516,-320), 47.4 %
Engine Depth Time Games Moves Average
---------------------------------------------------------------------------------
Stockfish 8 - 1 thread 5' + 3" 28.60 349:27:58 3000 188602 6.67
Stockfish 8 - 4 threads 75" + 0.75" 26.32 90:17:50 3000 188629 1.72
Re: Stockfish 8 - Quadruple time control vs. 4 threads
Posted: Tue Nov 22, 2016 8:52 pm
by Laskos
fastgm wrote:Stockfish 8
1 thread (5 minutes + 3 seconds) vs. 4 threads (75 seconds + 0.75 seconds)
Code: Select all
Program Elo + - Games Score Av.Op. Draws
----------------------------------------------------------------------------------------
1 Stockfish 8 - 1 thread 5' + 3" : 3009 5 5 3000 52.6 % 2991 83.9 %
2 Stockfish 8 - 4 threads 75" + 0.75" : 2991 5 5 3000 47.4 % 3009 83.9 %
Wins = 320
Draws = 2516
Losses = 164
Av.Op. Elo = 3000
Result : 1578.0/3000 (+320,=2516,-164)
Perf. : 52.6 %
Margins :
68 % : (+ 0.4,- 0.4 %) -> [ 52.2, 53.0 %]
95 % : (+ 0.7,- 0.7 %) -> [ 51.9, 53.3 %]
99.7 % : (+ 1.1,- 1.1 %) -> [ 51.5, 53.7 %]
Elo : 3018
Margins :
68 % : (+ 3,- 3) -> [3016,3021]
95 % : (+ 5,- 5) -> [3013,3023]
99.7 % : (+ 8,- 7) -> [3011,3026]
Games : 3000 (finished)
White Wins : 362 (12.1 %)
Black Wins : 122 ( 4.1 %)
Draws : 2516 (83.9 %)
White Perf. : 54.0 %
Black Perf. : 46.0 %
Individual statistics:
1 Stockfish 8 - 1 thread 5' + 3" : 3009 3000 (+320,=2516,-164), 52.6 %
2 Stockfish 8 - 4 threads 75" + 0.75" : 2991 3000 (+164,=2516,-320), 47.4 %
Engine Depth Time Games Moves Average
---------------------------------------------------------------------------------
Stockfish 8 - 1 thread 5' + 3" 28.60 349:27:58 3000 188602 6.67
Stockfish 8 - 4 threads 75" + 0.75" 26.32 90:17:50 3000 188629 1.72
Another important post, thanks. Factor of 4 in time is 2 doublings, from your data in another thread, the first one is worth 101 ELO points, the second 93 ELO points. In total 194 ELO points for quadrupling. The difference in this test is 18 ELO points, or 18/194 ~ 0.0928 quadruplings. The speed-up 1 --> 4 threads is 4^(1-0.0928) ~
3.52. Again, the most precise measurement for Lazy SMP.
So,
1 --> 2 threads:
1.91
1 --> 4 threads:
3.52
Re: Stockfish 8 - Quadruple time control vs. 4 threads
Posted: Wed Nov 23, 2016 4:05 am
by Milos
Laskos wrote:
So,
1 --> 2 threads: 1.91
1 --> 4 threads: 3.52
What I find amazing is that if you calculate efficiency according to Amdahl's Law it is exactly 95.5% both when going from 1->2 and 1->4 cores. Matching is on the second decimal!!! Amazing.
Re: Stockfish 8 - Quadruple time control vs. 4 threads
Posted: Wed Nov 23, 2016 4:11 pm
by Laskos
Milos wrote:Laskos wrote:
So,
1 --> 2 threads: 1.91
1 --> 4 threads: 3.52
What I find amazing is that if you calculate efficiency according to Amdahl's Law it is exactly 95.5% both when going from 1->2 and 1->4 cores. Matching is on the second decimal!!! Amazing.
Very interesting observation. And in line to Amdahl's fit I did for Komodo 9.3 using Andreas' results:
http://www.talkchess.com/forum/viewtopi ... 4&start=45
Andreas posts very important, hardcore results which use huge CPU time.
From your observation, the predictions would be:
1 --> 8 threads: 6.1
1 --> 16 threads: 9.55
1 --> 32 threads: 13.4
That is somewhat higher than the old YBW numbers.