INT8 is much better than FP16.
Some days ago at TCEC:
Scorpio INT8 vs LCZero1pct v0.21.2-n42547 +0 =4 -0
Scorpio INT8 vs LCZeroCPU v0.21.2-nLD2 +0 =4 -0
Now Scorpio INT8 vs LCZeroCPU v0.21.2-nLD2 +1 =1 -0
Will LC0 ever use INT8 instead of FP16?
ScorpioNN v2.9.0-n_maddex_INT8 is great:)
Moderators: hgm, Rebel, chrisw
-
- Posts: 12540
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: ScorpioNN v2.9.0-n_maddex_INT8 is great:)
I don't think we can conclude superiority from ten games.
Logically, though, faster is better. I guess that if Scorpio starts drilling LC0 into the ground, they will look at what Scorpio is doing and try to imitate it.
Logically, though, faster is better. I guess that if Scorpio starts drilling LC0 into the ground, they will look at what Scorpio is doing and try to imitate it.
Taking ideas is not a vice, it is a virtue. We have another word for this. It is called learning.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
-
- Posts: 5582
- Joined: Wed Sep 05, 2018 2:16 am
- Location: Moving
- Full name: Jorge Picado
Re: ScorpioNN v2.9.0-n_maddex_INT8 is great:)
You are aware that LCZero1pct v0.21.2-n42547 was only using 1 pct or percent, LOOK CLOSELY.... LCZero1pct, and...... in this case LCZeroCPU v0.21.2-nLD2 +1 =1 -0 was using the cpu with a smaller Net, NOT the GPU version, therefore, the cpu version performs much worse at least 400 Elo lower than the GPU version at 100% percent
Do NOT worry and be happy, we all live a short life
-
- Posts: 10282
- Joined: Thu Mar 09, 2006 12:37 am
- Location: Tel-Aviv Israel
Re: ScorpioNN v2.9.0-n_maddex_INT8 is great:)
Ethereal 11.50 lost 2.5-1.5 against LCZeroCPU v0.21.2-nLD2 so I guess that the difference between the cpu version and the gpu version is less than 400 elo.Chessqueen wrote: ↑Fri Jul 12, 2019 6:45 am
You are aware that LCZero1pct v0.21.2-n42547 was only using 1 pct or percent, LOOK CLOSELY.... LCZero1pct, and...... in this case LCZeroCPU v0.21.2-nLD2 +1 =1 -0 was using the cpu with a smaller Net, NOT the GPU version, therefore, the cpu version performs much worse at least 400 Elo lower than the GPU version at 100% percent
Edit:Xiphos0.5.3 also drew 2-2 against the same cpu version and Xiphos0.5 is number 5 in the CCRL 40/40 rating list
-
- Posts: 1631
- Joined: Tue Aug 21, 2018 7:52 pm
- Full name: Dietrich Kappe
Re: ScorpioNN v2.9.0-n_maddex_INT8 is great:)
ScorpioNN is good and might make it to DivP. The weakest part is probably the NN. It needed another 10-20 million self-play games to catch up to t30, but I wasn’t willing to shell out on vast.ai resources to get there. So until someone cooks up a better net, it’s likely to be a bit weaker than lc0/Allie/etc.
Also, Scorpio uses custom TB’s which are not present on TCEC, so it is essentially playing without them.
Also, Scorpio uses custom TB’s which are not present on TCEC, so it is essentially playing without them.
Fat Titz by Stockfish, the engine with the bodaciously big net. Remember: size matters. If you want to learn more about this engine just google for "Fat Titz".
-
- Posts: 1242
- Joined: Sat Jul 05, 2014 7:54 am
- Location: Southwest USA
Re: ScorpioNN v2.9.0-n_maddex_INT8 is great:)
Scorpio NN settings are very complex.ditto for Nebiyu chess.....having trouble getting the NN's to interface properly with the engines...actually LC0 is easier to set up these days! Think a Scorpio NN autodetect feature is called for..dkappe wrote: ↑Fri Jul 12, 2019 4:35 pm ScorpioNN is good and might make it to DivP. The weakest part is probably the NN. It needed another 10-20 million self-play games to catch up to t30, but I wasn’t willing to shell out on vast.ai resources to get there. So until someone cooks up a better net, it’s likely to be a bit weaker than lc0/Allie/etc.
Also, Scorpio uses custom TB’s which are not present on TCEC, so it is essentially playing without them.