Re: End of Era is there: SF is finally beaten!
Posted: Sat Feb 16, 2019 12:14 pm
I don't think "Father's" tricks that worked so well on AB engines would hold up to the current version of LC0.
Indeed that was probably the most spectacular lc0 sufi win so far. On move 23 and after calculating ~16.6 billion nodes SF gave evaluation of just 0.49 And on move 41 the game was already adjudicated as a complete destruction of SF position. That is quite incredible. SF probably completely underestimated that line that was played in the game when white can just give up pawns to completely cramp SF position. Once the Queens are off SF actually realizes it's in deep trouble, but move before that it thinks the position is OK. So I'd like to see how many nodes would be necessary for SF to realize that Qf5 is actually losing and I tend to agree that 1000 core SF might not have cut it in a practical time limits. Maybe someone with powerful HW can test it.M ANSARI wrote: ↑Sat Feb 16, 2019 7:29 am Very true ... I think that SF even on 1000 cores would still lose to Lc0 some pretty spectacular games. I mean just look at yesterday's loss ... out of the opening and each engine plays a few moves by itself and you have this position
[d]r2q1k1r/3b1pp1/1p2p2p/p2pP2P/P1p2P2/3B4/2P1QBP1/R3K2R w KQ - 0 20
You want powerful hardware? Bluefish running on 192 threads and with 7-man tablebases didn't see it...mirek wrote: ↑Sat Feb 16, 2019 12:25 pmIndeed that was probably the most spectacular lc0 sufi win so far. On move 23 and after calculating ~16.6 billion nodes SF gave evaluation of just 0.49 And on move 41 the game was already adjudicated as a complete destruction of SF position. That is quite incredible. SF probably completely underestimated that line that was played in the game when white can just give up pawns to completely cramp SF position. Once the Queens are off SF actually realizes it's in deep trouble, but move before that it thinks the position is OK. So I'd like to see how many nodes would be necessary for SF to realize that Qf5 is actually losing and I tend to agree that 1000 core SF might not have cut it in a practical time limits. Maybe someone with powerful HW can test it.M ANSARI wrote: ↑Sat Feb 16, 2019 7:29 am Very true ... I think that SF even on 1000 cores would still lose to Lc0 some pretty spectacular games. I mean just look at yesterday's loss ... out of the opening and each engine plays a few moves by itself and you have this position
[d]r2q1k1r/3b1pp1/1p2p2p/p2pP2P/P1p2P2/3B4/2P1QBP1/R3K2R w KQ - 0 20
People are requesting for a bonus match between 176 thread Bluefish vs the same Leela running on 2 GPU. Aloril may probably set up that !!henk2 wrote: ↑Sat Feb 16, 2019 10:40 amA 1000 core Clusterfish may not be suffering from the same horizon effect Stock and Bluefish are.M ANSARI wrote: ↑Sat Feb 16, 2019 7:29 amMikeB wrote: ↑Sat Feb 16, 2019 6:49 amWhoever figures out how to combine the Chess CPU power of a Stockfish like engine with the Chess GPU of an Lc0 like engine will get there first, SO many computers today have 24 , 36 or even 72 cores - take the best x moves from Lc0 and dedicate an AB search on those moves using one of those CPUs with A/B search engine like SF. Someone with some coding skills should be looking at that, Good luck!corres wrote: ↑Fri Feb 15, 2019 6:24 pmNotecorres wrote: ↑Fri Feb 15, 2019 10:50 amNohow.Graham Banks wrote: ↑Fri Feb 15, 2019 10:16 am How can one know whether the engines are playing on equal terms?
How can you compare CPU and GPU and state you've found a balance?
There are only subjective methods to make comparison.
Moreover AB engines are made basically for playing middle games and endgames.
An AB engines will be banished from a competition if it has a built-in opening book.
An NN type engines has definitively a built-in opening + middle game + endgame book.
AB engines have their own benefit and their own drawback and NN type engines have these too.
It is obvious the development of hardware and software gives more opportunity for enhancing
the chess power of the NN type engines than for an AB type engines.
But the problem of chess can not be solved by an NN type engine either.
I think the performance of Stockfish against NN engines would be enhanced if developers of Stockfish would make test not only against the actual master of Stockfish but against the best NN engines and if they would modify in some measure the source of Stockfish according to the result of tests.
Until now to make these tests was problematic because the fast changing in the power of NN engines.
But to now the chess power of NN engines reach near a plateau so there is sense to make tests with NN type engines too.
Very true ... I think that SF even on 1000 cores would still lose to Lc0 some pretty spectacular games. I mean just look at yesterday's loss ... out of the opening and each engine plays a few moves by itself and you have this position
[d]r2q1k1r/3b1pp1/1p2p2p/p2pP2P/P1p2P2/3B4/2P1QBP1/R3K2R w KQ - 0 20
SF has reacted to Lc0 pawn attack on the Kingside by giving up a bishop temporarily to where it seemed like Lc0 would have to give it back for a couple of pawns. But here Lc0 uncorks Bg6!!! giving up the bishop without any pawn compensation.
[d]r2q1k1r/3b1pp1/1p2p1Bp/p2pP2P/P1p2P2/8/2P1QBP1/R3K2R b KQ - 0 20
It was really hard to see how this was going to work out well for Lc0 ... but the entire plan was to entomb the rook on h8 and the continuation for Lc0 was to give up a total of 3 pawn to make that happen. It somehow made it work and was even very happy to exchange queens and go for what seemed like a super slow strangulation 3 pawns down. If you want to understand why NN engines are extremely strong and very difficult for AB to handle, it is games like this. There is just no calculating through something like this.
Here is what it looked like after about 30 moves … YES … Lc0 is 3 pawns down but SF is totally helpless as the rook on h8 can't get developed!
[d]2r1b1kr/6p1/4P1Pp/1p1p1P2/p1p3p1/2P5/3K1B2/RR6 w - - 0 32
And the full game for anyone interested ... very powerful game done in A0 style !!!
[pgn]1. e4 e6 2. d4 d5 3. Nc3 Nf6 4. Bg5 Bb4 5. e5 h6 6. Be3 Ne4 7. Qg4 Kf8 8. a3 Bxc3+ 9. bxc3 Nxc3 10. Bd3 b6 11. h4 Nc6 12. h5 Bd7 13. Ne2 Nxe2 14. Qxe2 Ne7 15. a4 a5 16. f4 Nf5 17. Bf2 Nxd4 18. Bxd4 c5 19. Bf2 c4 20. Bg6 fxg6 21. hxg6 Kg8 22. c3 Qf8 23. Qg4 Qf5 24. Qxf5 exf5 25. Rb1 Rb8 26. g4 fxg4 27. e6 Bxa4 28. Kd2 Be8 29. f5 b5 30. Ra1 a4 31. Rhb1 Rc8 32. Bh4 g3 33. Ke3 Bc6 34. Bxg3 Kf8 35. Bd6+ Ke8 36. Rf1 Rd8 37. Bb4 d4+ 38. cxd4 Bd5 39. f6 Bxe6 40. f7+ Kd7 41. f8=R 1-0[/pgn]
After all, it would get 800-1000 million NPS.
A 1000 core Stockfish would be like regular stockfish getting 1450 minutes + 3 minutes per move vs Leela getting only 120 minutes + 15sec per move.
It could still lose but the ELO difference between 1000fish and Leela would be around 150-200. So Leela would be in deep trouble.
Will Leela use a new net vs Bluefish?Nay Lin Tun wrote: ↑Sat Feb 16, 2019 2:04 pmPeople are requesting for a bonus match between 176 thread Bluefish vs the same Leela running on 2 GPU. Aloril may probably set up that !!henk2 wrote: ↑Sat Feb 16, 2019 10:40 amA 1000 core Clusterfish may not be suffering from the same horizon effect Stock and Bluefish are.M ANSARI wrote: ↑Sat Feb 16, 2019 7:29 amMikeB wrote: ↑Sat Feb 16, 2019 6:49 amWhoever figures out how to combine the Chess CPU power of a Stockfish like engine with the Chess GPU of an Lc0 like engine will get there first, SO many computers today have 24 , 36 or even 72 cores - take the best x moves from Lc0 and dedicate an AB search on those moves using one of those CPUs with A/B search engine like SF. Someone with some coding skills should be looking at that, Good luck!corres wrote: ↑Fri Feb 15, 2019 6:24 pmNotecorres wrote: ↑Fri Feb 15, 2019 10:50 amNohow.Graham Banks wrote: ↑Fri Feb 15, 2019 10:16 am How can one know whether the engines are playing on equal terms?
How can you compare CPU and GPU and state you've found a balance?
There are only subjective methods to make comparison.
Moreover AB engines are made basically for playing middle games and endgames.
An AB engines will be banished from a competition if it has a built-in opening book.
An NN type engines has definitively a built-in opening + middle game + endgame book.
AB engines have their own benefit and their own drawback and NN type engines have these too.
It is obvious the development of hardware and software gives more opportunity for enhancing
the chess power of the NN type engines than for an AB type engines.
But the problem of chess can not be solved by an NN type engine either.
I think the performance of Stockfish against NN engines would be enhanced if developers of Stockfish would make test not only against the actual master of Stockfish but against the best NN engines and if they would modify in some measure the source of Stockfish according to the result of tests.
Until now to make these tests was problematic because the fast changing in the power of NN engines.
But to now the chess power of NN engines reach near a plateau so there is sense to make tests with NN type engines too.
Very true ... I think that SF even on 1000 cores would still lose to Lc0 some pretty spectacular games. I mean just look at yesterday's loss ... out of the opening and each engine plays a few moves by itself and you have this position
[d]r2q1k1r/3b1pp1/1p2p2p/p2pP2P/P1p2P2/3B4/2P1QBP1/R3K2R w KQ - 0 20
SF has reacted to Lc0 pawn attack on the Kingside by giving up a bishop temporarily to where it seemed like Lc0 would have to give it back for a couple of pawns. But here Lc0 uncorks Bg6!!! giving up the bishop without any pawn compensation.
[d]r2q1k1r/3b1pp1/1p2p1Bp/p2pP2P/P1p2P2/8/2P1QBP1/R3K2R b KQ - 0 20
It was really hard to see how this was going to work out well for Lc0 ... but the entire plan was to entomb the rook on h8 and the continuation for Lc0 was to give up a total of 3 pawn to make that happen. It somehow made it work and was even very happy to exchange queens and go for what seemed like a super slow strangulation 3 pawns down. If you want to understand why NN engines are extremely strong and very difficult for AB to handle, it is games like this. There is just no calculating through something like this.
Here is what it looked like after about 30 moves … YES … Lc0 is 3 pawns down but SF is totally helpless as the rook on h8 can't get developed!
[d]2r1b1kr/6p1/4P1Pp/1p1p1P2/p1p3p1/2P5/3K1B2/RR6 w - - 0 32
And the full game for anyone interested ... very powerful game done in A0 style !!!
[pgn]1. e4 e6 2. d4 d5 3. Nc3 Nf6 4. Bg5 Bb4 5. e5 h6 6. Be3 Ne4 7. Qg4 Kf8 8. a3 Bxc3+ 9. bxc3 Nxc3 10. Bd3 b6 11. h4 Nc6 12. h5 Bd7 13. Ne2 Nxe2 14. Qxe2 Ne7 15. a4 a5 16. f4 Nf5 17. Bf2 Nxd4 18. Bxd4 c5 19. Bf2 c4 20. Bg6 fxg6 21. hxg6 Kg8 22. c3 Qf8 23. Qg4 Qf5 24. Qxf5 exf5 25. Rb1 Rb8 26. g4 fxg4 27. e6 Bxa4 28. Kd2 Be8 29. f5 b5 30. Ra1 a4 31. Rhb1 Rc8 32. Bh4 g3 33. Ke3 Bc6 34. Bxg3 Kf8 35. Bd6+ Ke8 36. Rf1 Rd8 37. Bb4 d4+ 38. cxd4 Bd5 39. f6 Bxe6 40. f7+ Kd7 41. f8=R 1-0[/pgn]
After all, it would get 800-1000 million NPS.
A 1000 core Stockfish would be like regular stockfish getting 1450 minutes + 3 minutes per move vs Leela getting only 120 minutes + 15sec per move.
It could still lose but the ELO difference between 1000fish and Leela would be around 150-200. So Leela would be in deep trouble.
What is your bet?
176 Threads will win or 2 GPU will win? My bet is still on Leela.
Putting heavy hardware is not the solution of software problem. Even if you have 1,000,000 cores cpu running for 1 million years per move, horizon effect is still there(you just postpone the horizon effect from certain depth to certain depth). Beyond horizon, SF will still play like 1200 (his static positional evaluation is like 1200), and Leela may possibly win a few games.
corres wrote: ↑Fri Feb 15, 2019 6:24 pmNotecorres wrote: ↑Fri Feb 15, 2019 10:50 amNohow.Graham Banks wrote: ↑Fri Feb 15, 2019 10:16 am How can one know whether the engines are playing on equal terms?
How can you compare CPU and GPU and state you've found a balance?
There are only subjective methods to make comparison.
Moreover AB engines are made basically for playing middle games and endgames.
An AB engines will be banished from a competition if it has a built-in opening book.
An NN type engines has definitively a built-in opening + middle game + endgame book.
AB engines have their own benefit and their own drawback and NN type engines have these too.
It is obvious the development of hardware and software gives more opportunity for enhancing
the chess power of the NN type engines than for an AB type engines.
But the problem of chess can not be solved by an NN type engine either.
I think the performance of Stockfish against NN engines would be enhanced if developers of Stockfish would make test not only against the actual master of Stockfish but against the best NN engines and if they would modify in some measure the source of Stockfish according to the result of tests.
Until now to make these tests was problematic because the fast changing in the power of NN engines.
But to now the chess power of NN engines reach near a plateau so there is sense to make tests with NN type engines too.
There is no any "spectacular" and there is no any "plan" on the side of Leela.M ANSARI wrote: ↑Sat Feb 16, 2019 7:29 am ...
I think that SF even on 1000 cores would still lose to Lc0 some pretty spectacular games. I mean just look at yesterday's loss ... out of the opening and each engine plays a few moves by itself and you have this position
[d]r2q1k1r/3b1pp1/1p2p2p/p2pP2P/P1p2P2/3B4/2P1QBP1/R3K2R w KQ - 0 20
SF has reacted to Lc0 pawn attack on the Kingside by giving up a bishop temporarily to where it seemed like Lc0 would have to give it back for a couple of pawns. But here Lc0 uncorks Bg6!!! giving up the bishop without any pawn compensation.
[d]r2q1k1r/3b1pp1/1p2p1Bp/p2pP2P/P1p2P2/8/2P1QBP1/R3K2R b KQ - 0 20
It was really hard to see how this was going to work out well for Lc0 ... but the entire plan was to entomb the rook on h8 and the continuation for Lc0 was to give up a total of 3 pawn to make that happen. It somehow made it work and was even very happy to exchange queens and go for what seemed like a super slow strangulation 3 pawns down. If you want to understand why NN engines are extremely strong and very difficult for AB to handle, it is games like this. There is just no calculating through something like this.
Here is what it looked like after about 30 moves … YES … Lc0 is 3 pawns down but SF is totally helpless as the rook on h8 can't get developed!
[d]2r1b1kr/6p1/4P1Pp/1p1p1P2/p1p3p1/2P5/3K1B2/RR6 w - - 0 32
And the full game for anyone interested ... very powerful game done in A0 style !!!
[pgn]1. e4 e6 2. d4 d5 3. Nc3 Nf6 4. Bg5 Bb4 5. e5 h6 6. Be3 Ne4 7. Qg4 Kf8 8. a3 Bxc3+ 9. bxc3 Nxc3 10. Bd3 b6 11. h4 Nc6 12. h5 Bd7 13. Ne2 Nxe2 14. Qxe2 Ne7 15. a4 a5 16. f4 Nf5 17. Bf2 Nxd4 18. Bxd4 c5 19. Bf2 c4 20. Bg6 fxg6 21. hxg6 Kg8 22. c3 Qf8 23. Qg4 Qf5 24. Qxf5 exf5 25. Rb1 Rb8 26. g4 fxg4 27. e6 Bxa4 28. Kd2 Be8 29. f5 b5 30. Ra1 a4 31. Rhb1 Rc8 32. Bh4 g3 33. Ke3 Bc6 34. Bxg3 Kf8 35. Bd6+ Ke8 36. Rf1 Rd8 37. Bb4 d4+ 38. cxd4 Bd5 39. f6 Bxe6 40. f7+ Kd7 41. f8=R 1-0[/pgn]