Page 4 of 13

Re: this will be the merge of a lifetime : SF 80 Elo+

Posted: Thu Aug 06, 2020 9:03 am
by M ANSARI
Is there anyway to run the NN evaluation on a programmable customized daughter card and get it to run faster or more efficiently? It is funny as everyone had been looking for a way to run Lc0 on GPU while having some sort of safety net to prevent Lc0 tactical weakness ... I guess using an AB engine with a Lc0 evaluation to cover for positional weakness works better! It sure makes using an engine for analysis much more useful as with Lc0 you always needed a sanity check to make sure no cheap tricks were missed. This is probably just the beginning of an arms race and most likely there will be specific NN modules that concentrate on certain openings or certain stages of the game. An engine that can on the fly choose between several smaller targeted nets (depending on what is needed ) will be able to run those nets much faster ... so theoretical should have a strong advantage. Now that I think about it this would be really good for Chess 960 as you can make a custom net for every starting position and then once the game goes along switch to another net.

Re: this will be the merge of a lifetime : SF 80 Elo+

Posted: Thu Aug 06, 2020 9:53 am
by Ovyron
Cornfed wrote: Thu Aug 06, 2020 2:02 am
Ovyron wrote: Wed Aug 05, 2020 12:41 pm This is the breakthrough I've been predicting for years! It finally happened, and I'm just glad chess looks very healthy after it (draw rates have gone down! Some lines are proving to be playable again!)
Until everyone uses these?
Everyone is already using these, when Eman Enigma 1.00 (closed source stockfish clone) appeared NNUE got widespread adoption. It's sad that now the most used engine in the world is an illegal one (you can't have its source), but at this point all NNUE clones are basically the same, what matters mostly is the net you use (the biggest impact.) I've been beating people that use Eman Enigma 1.10 that use much faster hardware than mine, because of their poor choice of net (I assume, since they're outsearching me with their NNUE, yet my eval is superior allowing the win.)

The effect seen has mimicked the world's capitalist economy, the guys with most elo gained more when switching to NNUE and became unreachable, the weakest ones sank more (I'm on this group :mrgreen: ). The ones in the middle sunk, then went back to where they were after fixing their openings (critical, because lines that were very solid before became suicidal now).

I'm an atheist but this bible passage speaks volumes about how the elo of everyone behaved after NNUE:

For whoever has will be given more, and they will have an abundance. Whoever does not have, even what they have will be taken from them. Matthew 25:29

Re: this will be the merge of a lifetime : SF 80 Elo+

Posted: Thu Aug 06, 2020 10:46 am
by Zenmastur
Ovyron wrote: Thu Aug 06, 2020 9:53 am
Cornfed wrote: Thu Aug 06, 2020 2:02 am
Ovyron wrote: Wed Aug 05, 2020 12:41 pm This is the breakthrough I've been predicting for years! It finally happened, and I'm just glad chess looks very healthy after it (draw rates have gone down! Some lines are proving to be playable again!)
Until everyone uses these?
Everyone is already using these, when Eman Enigma 1.00 (closed source stockfish clone) appeared NNUE got widespread adoption. It's sad that now the most used engine in the world is an illegal one (you can't have its source), but at this point all NNUE clones are basically the same, what matters mostly is the net you use (the biggest impact.) I've been beating people that use Eman Enigma 1.10 that use much faster hardware than mine, because of their poor choice of net (I assume, since they're outsearching me with their NNUE, yet my eval is superior allowing the win.)

The effect seen has mimicked the world's capitalist economy, the guys with most elo gained more when switching to NNUE and became unreachable, the weakest ones sank more (I'm on this group :mrgreen: ). The ones in the middle sunk, then went back to where they were after fixing their openings (critical, because lines that were very solid before became suicidal now).

I'm an atheist but this bible passage speaks volumes about how the elo of everyone behaved after NNUE:

For whoever has will be given more, and they will have an abundance. Whoever does not have, even what they have will be taken from them. Matthew 25:29
What I think is/will happen is that many people that used to use SF and have switched to SF-NNUE haven't changed the way they analyze. Things you could do with SF don't always work well with SF-NNUE and some things SF couldn't do or couldn't do very well SF-NNUE can. Learning when to do what will take some time.

Re: this will be the merge of a lifetime : SF 80 Elo+

Posted: Thu Aug 06, 2020 10:55 am
by Ovyron
Zenmastur wrote: Thu Aug 06, 2020 10:46 am What I think is/will happen is that many people that used to use SF and have switched to SF-NNUE haven't changed the way they analyze. Things you could do with SF don't always work well with SF-NNUE and some things SF couldn't do or couldn't do very well SF-NNUE can. Learning when to do what will take some time.
For what it's worth I'm no longer sure I could hold on a game against you. I've seen 2.00 positions from 1 net while another shows 0.00, and the 0.00 one can outsearch it and it doesn't matter. With your hardware superiority you could find the true eval of some net while I'm greatly misevaluating, and you could be reaching a strength that would just be outside of reach.

With NNUE I felt like jumping from 4 core analysis to 16core analysis of Stockfish dev or something, with you jumping from higher the potential is mind-boggling. Though a handicap game where you're stuck with Stockfish-dev (regular eval) and I can use NNUE would be interesting, perhaps I could win that one.

Re: this will be the merge of a lifetime : SF 80 Elo+

Posted: Thu Aug 06, 2020 2:32 pm
by MikeB
Ovyron wrote: Thu Aug 06, 2020 9:53 am

For whoever has will be given more, and they will have an abundance. Whoever does not have, even what they have will be taken from them. Matthew 25:29
Amen - I love it when I see an atheist quoting the Bible ... an old friend of my said this once - lets just say the atheist view is correct - well ,when we die, we die and and we all go back to dust
. But just say there is a God, then atheist gets to spend his eternal years in hell and the rest of us are in the Glory of God for eternal time - what would a risk averse person do?

Re: this will be the merge of a lifetime : SF 80 Elo+

Posted: Thu Aug 06, 2020 2:36 pm
by Ovyron
MikeB wrote: Thu Aug 06, 2020 2:32 pm . But just say there is a God, then atheist gets to spend his eternal years in hell and the rest of us are in the Glory of God for eternal time - what would a risk averse person do?
Can do: there is a God. It's me :lol:

Re: this will be the merge of a lifetime : SF 80 Elo+

Posted: Thu Aug 06, 2020 4:22 pm
by Vinvin
MikeB wrote: Thu Aug 06, 2020 2:32 pm . But just say there is a God, then atheist gets to spend his eternal years in hell and the rest of us are in the Glory of God for eternal time - what would a risk averse person do?
It's the well known : "Pascal's wager" https://en.wikipedia.org/wiki/Pascal%27s_wager

My variants are :
"If there are 1000 gods but you're not sure, what would a risk to believe in these 1000 gods ?"
"If there are 1 million gods but you're not sure, what would a risk to believe in these 1 million gods ?"
"If the real god is the Flying Spaghetti Monster, what would a risk to believe in the Flying Spaghetti Monster god ?"
God has always been a nonsense a will stay a nonsense forever.

Re: this will be the merge of a lifetime : SF 80 Elo+

Posted: Thu Aug 06, 2020 5:17 pm
by Jhoravi
Excuse me for my ignorance but how is the Net used by SF-NNUE being trained? Is it borrowed from LC0 Nets?

Re: this will be the merge of a lifetime : SF 80 Elo+

Posted: Thu Aug 06, 2020 6:09 pm
by zullil
Jhoravi wrote: Thu Aug 06, 2020 5:17 pm Excuse me for my ignorance but how is the Net used by SF-NNUE being trained? Is it borrowed from LC0 Nets?
Some info about training at https://github.com/nodchip/Stockfish

No connection to Lc0 nets.

Re: this will be the merge of a lifetime : SF 80 Elo+

Posted: Thu Aug 06, 2020 7:16 pm
by Jouni
And now 6.8. NNUE is merged: Stockfish 060820 by the Stockfish developers (see AUTHORS file) :!: