Life In 19x19

LZv17 #219 vs LZ (MiniGo training data) ( https://github.com/leela-zero/leela-zero/issues/2509 )
2x1080ti, v 2400
C:\APPS\l0gpu17\validation.exe -k lz247-minigo17 -s "0:1" -g 5 -n C:\APPS\net\901e04de.gz -o "-g -v 2400 --gpu 0 --gpu 1 -r 5 -t 2 --batchsize 1 --noponder -q -d --timemanage off ...

Сity legend check (l0XXX 1600 visits vs elfv2 3200 visits):

2 x 1080ti

[Engine_Master]
enginedir = C:\APPS\l0gpu17\
engine = leelaz.exe -g --gpu 0 --gpu 1 -t 24 --batchsize 12 -r 5 --noponder --timemanage off --precision single
weightdir = C:\APPS\net\
weight = 05dbca15.gz
name = ELFV2

[Engine ...

The main question is what is more important to us - victory or honesty?

So you have shown that by increasing the number of threads manually way above the default of the program (which should be the optimum in most cases) you make it play worse?

EDIT:
Or do you want to say that the 20-ish block ELF2 network scales better with threads? Does the 40b network regress with ...

NBC, if you're using visit parity you shouldn't use ponder. The time to reach that number of visits varies by position. Time parity matches can use ponder on separate hardware though, similar to how Alphago was tested.
Why not? I'm using separate GPU for each net.

There's a thread on GitHub with ...

Is the difference in speed between the ELF network and the 40b network really 2x for you?
I know that theoretically that could be true, but if ive understood correctly, the difference isnt nearly that large in practise?


If you load the 40b network in leela, and write netbench 50000 and then load ...

Visit parity match
LZ0v17 #219 (1600 visits) vs Elfv2 (3200 visits) 1x1080ti per side + ponder
Part1 - #219 (GPU0) vs Elfv2 (GPU1)
C:\APPS\l0gpu17\validation.exe -k 219-elfv2-1gpu -s "0:1" -g 6 -n C:\APPS\net\00ff08eb.gz -o "-g -v 1600 --gpu 0 -t 24 -q -d --timemanage off --precision single -w" -n ...

Visit parity match with statistically significant result :salute:
LZ0v17 #219 (1600 visits) vs Elfv2 (3200 visits) 2x1080ti
C:\APPS\l0gpu17\validation.exe -k 219-elfv2 -s "0:1" -g 6 -n C:\APPS\net\00ff08eb.gz -o "-g -v 1600 --gpu 0 --gpu 1 --noponder -t 24 -q -d --timemanage off --precision single ...

splee99 wrote:I think one computer only has one interface bus between the CPU and the GPU. So that part is actually shared and the bot using less interface time will take more advantage.

For 3200 visits and gpu(!) client? it's funny is not it?

hoa803 wrote:My suspicion is that time parity might be correct with two entirely separate machines, with the same hardware, and using ponder.

What do you think about test with one computer, ponder, one dedicated gpu for each side? I believe that this will be a more or less honest test.

Time parity match with statistically significant result :salute:
(part II).
LZ0v17 #219 vs Elfv2
2x1080ti, 10s per move.
C:\APPS\l0gpu17\validation.exe -k 219elfv2-10s -s "0:10" -g 6 -n C:\APPS\net\00ff08eb.gz -o "-g --gpu 0 --gpu 1 --noponder -t 24 -q -d --precision single -w" -n C:\APPS\net ...

It might provoke an interesting discussion - the folks on GitHub don't feel the time parity matches are a good measure of engine strength, but rather visits. I don't claim to totally understand the reasoning but it might be worth looking into.
i think these visit's tests are "сферический конь в ...

Time parity match with statistically significant result :salute: (part I).
LZ0v17 #219 vs Elfv2
2x1080ti, 30s per move.

C:\APPS\l0gpu17\validation.exe -k 219elfv2-30s -s "0:10" -g 6 -n C:\APPS\net\00ff08eb.gz -o "-g --gpu 0 --gpu 1 --noponder -t 24 -q -d --precision single -w" -n C:\APPS\net ...

Yes, you are right. All these tests are just rubbish in terms of mathematical statistics. And poor Lee Sedol still has chances to defeat Alfago .
And you are right again:

hoa803 wrote:It's still fun to do the matches, though.

nbc44: about how many playouts per move are Elf and LZ getting at these time settings on your hardware? I'm guessing at least 60k for LZ and double that for Elf?
B/W/B/W...
250613 visits, 84820075 nodes, 250612 playouts, 2078 n/s
190448 visits, 65159316 nodes, 190447 playouts, 2653 n/s
77923 ...