TCEC S15, END of an ERA event is much more Brutal than I thought!

Discussion of anything and everything relating to chess playing software and machines.

Moderators: hgm, Harvey Williamson, bob

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Post Reply
Nay Lin Tun
Posts: 509
Joined: Mon Jan 16, 2012 5:34 am

TCEC S15, END of an ERA event is much more Brutal than I thought!

Post by Nay Lin Tun » Wed May 15, 2019 11:04 am

After 26 games in TCEC SUFI, Leela is leading with 15-11.

My prediction for TCEC was just 55-45 Leela win.
cap4.PNG
cap4.PNG (20.11 KiB) Viewed 3633 times

User avatar
Laskos
Posts: 9244
Joined: Wed Jul 26, 2006 8:21 pm
Full name: Kai Laskos

Re: TCEC S15, END of an ERA event is much more Brutal than I thought!

Post by Laskos » Wed May 15, 2019 12:03 pm

Nay Lin Tun wrote:
Wed May 15, 2019 11:04 am
After 26 games in TCEC SUFI, Leela is leading with 15-11.

My prediction for TCEC was just 55-45 Leela win.
cap4.PNG
Yes, I expected long ago 2:1 Win/Loss ratio for Leela, something on the lines +14 -7 =79. Let's see. I predicted that when the previous S14 was underway with 32930 net.

It IS an end of an era, if anything, the hardware for Leela is below the hardware for Stockfish in the current TCEC. GPU has much more room for improvement than CPU, we will assist in 1-2 years at a complete dominance strength-wise of NN-bases engines. FPGA might come next for chess engines, but it's a bit more involved to make them play chess.

Werewolf
Posts: 1183
Joined: Thu Sep 18, 2008 8:24 pm

Re: TCEC S15, END of an ERA event is much more Brutal than I thought!

Post by Werewolf » Wed May 15, 2019 12:10 pm

Laskos wrote:
Wed May 15, 2019 12:03 pm
Nay Lin Tun wrote:
Wed May 15, 2019 11:04 am
After 26 games in TCEC SUFI, Leela is leading with 15-11.

My prediction for TCEC was just 55-45 Leela win.
cap4.PNG
FPGA might come next for chess engines, but it's a bit more involved to make them play chess.
Not exactly fair for something like TCEC, but I think Stockfish's hardware saviour is a cluster. If a decent cluster was built with 1000+ cores there may be no version of Lc0 on any machine which could hold its own.

User avatar
George Tsavdaris
Posts: 1557
Joined: Thu Mar 09, 2006 11:35 am

Re: TCEC S15, END of an ERA event is much more Brutal than I thought!

Post by George Tsavdaris » Wed May 15, 2019 12:43 pm

Werewolf wrote:
Wed May 15, 2019 12:10 pm
Laskos wrote:
Wed May 15, 2019 12:03 pm
Nay Lin Tun wrote:
Wed May 15, 2019 11:04 am
After 26 games in TCEC SUFI, Leela is leading with 15-11.

My prediction for TCEC was just 55-45 Leela win.
cap4.PNG
FPGA might come next for chess engines, but it's a bit more involved to make them play chess.
Not exactly fair for something like TCEC, but I think Stockfish's hardware saviour is a cluster. If a decent cluster was built with 1000+ cores there may be no version of Lc0 on any machine which could hold its own.
But why you assume no diminishing returns of real strength with 1000 cores? Most probably 1000 cores compared to 43 as of now on TCEC Stockfish would not give a gigantic Elo boost but only small one.
They tested 384 threads(on 192 cores) vs 32 threads(cores) for Stockfish and it was +114 Elo.

Even worse, even MUCH worse i would say, 1000 cores system is a >300 000 $ one while current TCEC Leela's GPUs is just 2000 $.
After his son's birth they've asked him:
"Is it a boy or girl?"
YES! He replied.....

Nay Lin Tun
Posts: 509
Joined: Mon Jan 16, 2012 5:34 am

Re: TCEC S15, END of an ERA event is much more Brutal than I thought!

Post by Nay Lin Tun » Wed May 15, 2019 12:49 pm

Werewolf wrote:
Wed May 15, 2019 12:10 pm
Laskos wrote:
Wed May 15, 2019 12:03 pm
Nay Lin Tun wrote:
Wed May 15, 2019 11:04 am
After 26 games in TCEC SUFI, Leela is leading with 15-11.

My prediction for TCEC was just 55-45 Leela win.
cap4.PNG
FPGA might come next for chess engines, but it's a bit more involved to make them play chess.
Not exactly fair for something like TCEC, but I think Stockfish's hardware saviour is a cluster. If a decent cluster was built with 1000+ cores there may be no version of Lc0 on any machine which could hold its own.
Are you aware that 1000 cores= 22x44 cores only. That means it is about equivalent to 10x times Time control boost (because of SMP scaling whereas 2x TC is approx equal to 4x hardware especially beyond 32 cores).
You will be surprised that Leela actually already beat 44 cores (SF with 10x TC bonus ) in one pair of opening! 3 mins vs 30 mins.

User avatar
Laskos
Posts: 9244
Joined: Wed Jul 26, 2006 8:21 pm
Full name: Kai Laskos

Re: TCEC S15, END of an ERA event is much more Brutal than I thought!

Post by Laskos » Wed May 15, 2019 12:54 pm

George Tsavdaris wrote:
Wed May 15, 2019 12:43 pm
Werewolf wrote:
Wed May 15, 2019 12:10 pm
Laskos wrote:
Wed May 15, 2019 12:03 pm
Nay Lin Tun wrote:
Wed May 15, 2019 11:04 am
After 26 games in TCEC SUFI, Leela is leading with 15-11.

My prediction for TCEC was just 55-45 Leela win.
cap4.PNG
FPGA might come next for chess engines, but it's a bit more involved to make them play chess.
Not exactly fair for something like TCEC, but I think Stockfish's hardware saviour is a cluster. If a decent cluster was built with 1000+ cores there may be no version of Lc0 on any machine which could hold its own.
But why you assume no diminishing returns of real strength with 1000 cores? Most probably 1000 cores compared to 43 as of now on TCEC Stockfish would not give a gigantic Elo boost but only small one.
They tested 384 threads(on 192 cores) vs 32 threads(cores) for Stockfish and it was +114 Elo.

Even worse, even MUCH worse i would say, 1000 cores system is a >300 000 $ one while current TCEC Leela's GPUs is just 2000 $.
This thread of Peter Osterlund is helpful with Lazy SMP and clusters:
viewtopic.php?f=7&t=64824

The cluster latencies prevent high gain from doubling the number of nodes in the cluster. I guess an 1,000 core cluster will barely be 3x-4x times better in "effective speed" compared to the TCEC machine. And this will soon be not enough to beat T40 newer and improving nets even on only 2-4 GPUs. Maybe it's not enough already. Also, GPUs will improve solidly soon, and NN engines' prallelization to 4 or 8 GPUs too.

Interesting times, traditional engines will become more like a niche "puzzle solvers".

Leo
Posts: 790
Joined: Fri Sep 16, 2016 4:55 pm
Location: USA/Minnesota
Full name: Leo

Re: TCEC S15, END of an ERA event is much more Brutal than I thought!

Post by Leo » Wed May 15, 2019 2:22 pm

SF has a chance if LZ throughs away some games like it did last time.
BrainFish-2 190310 bmi2 Elo 3576.

glennsamuel32
Posts: 83
Joined: Sat Dec 04, 2010 4:31 pm
Location: 223

Re: TCEC S15, END of an ERA event is much more Brutal than I thought!

Post by glennsamuel32 » Wed May 15, 2019 3:35 pm

Nay Lin Tun wrote:
Wed May 15, 2019 12:49 pm
You will be surprised that Leela actually already beat 44 cores (SF with 10x TC bonus ) in one pair of opening! 3 mins vs 30 mins.
No point having a million cores searching the wrong lines.

Hai
Posts: 452
Joined: Sun Aug 04, 2013 11:19 am

Re: TCEC S15, END of an ERA event is much more Brutal than I thought!

Post by Hai » Wed May 15, 2019 4:50 pm

Laskos wrote:
Wed May 15, 2019 12:03 pm
Nay Lin Tun wrote:
Wed May 15, 2019 11:04 am
After 26 games in TCEC SUFI, Leela is leading with 15-11.

My prediction for TCEC was just 55-45 Leela win.
cap4.PNG
Yes, I expected long ago 2:1 Win/Loss ratio for Leela, something on the lines +14 -7 =79. Let's see. I predicted that when the previous S14 was underway with 32930 net.

It IS an end of an era, if anything, the hardware for Leela is below the hardware for Stockfish in the current TCEC. GPU has much more room for improvement than CPU, we will assist in 1-2 years at a complete dominance strength-wise of NN-bases engines. FPGA might come next for chess engines, but it's a bit more involved to make them play chess.
LC0 vs Stockfish will end: +16 =80 -4

It was a big mistake to take Stockfish and not Bluefish!

JJJ
Posts: 1277
Joined: Sat Apr 19, 2014 11:47 am

Re: TCEC S15, END of an ERA event is much more Brutal than I thought!

Post by JJJ » Wed May 15, 2019 5:09 pm

Stockfish is now the Komodo of lczero. It is first in rating list but loosing in direct confontation.
End of Era will be when Lczero will be the first in rating list as well.

Post Reply