how good is a GeForce GTX 1060 6GB for Leela ?

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

Moderators: hgm, Dann Corbit, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
jpqy
Posts: 532
Joined: Thu Apr 24, 2008 7:31 am
Location: Belgium

Re: how good is a GeForce GTX 1060 6GB for Leela ?

Post by jpqy » Tue May 01, 2018 3:11 pm

Milos..can you make a screen..

As these guys has better graphic cards and get lower nodes/sec. than you get.

https://docs.google.com/spreadsheets/d/ ... =857482380

Run it with ID229
Last edited by jpqy on Tue May 01, 2018 3:13 pm, edited 1 time in total.

Werewolf
Posts: 1334
Joined: Thu Sep 18, 2008 8:24 pm

Re: how good is a GeForce GTX 1060 6GB for Leela ?

Post by Werewolf » Tue May 01, 2018 3:13 pm

Dann Corbit wrote:Titan V has tensor cores.
But they are fiddly to use and you have to program especially for them.
The Titan V also "only" has 640 of them. I suspect its successor will cram in many more.

Werewolf
Posts: 1334
Joined: Thu Sep 18, 2008 8:24 pm

Re: how good is a GeForce GTX 1060 6GB for Leela ?

Post by Werewolf » Tue May 01, 2018 3:19 pm

Milos wrote:
Judging be the current proper benchmark (LC0 on cuDNN), Titan V is only 3.5 times faster than GTX 960, and 2.2 times 1080ti. And GTX 960 is at least 15 times cheaper than Titan V.
How do you work that out? The Titan V isn't 2.2x faster than a 1080 ti according to either the GFLOPS (12300 vs 10600 respectively) or the benchmarks here

https://docs.google.com/spreadsheets/d/ ... edit#gid=0

Unless I'm misreading them.

Dann Corbit
Posts: 11925
Joined: Wed Mar 08, 2006 7:57 pm
Location: Redmond, WA USA
Contact:

Re: how good is a GeForce GTX 1060 6GB for Leela ?

Post by Dann Corbit » Tue May 01, 2018 4:47 pm

Werewolf wrote:
Dann Corbit wrote:Titan V has tensor cores.
But they are fiddly to use and you have to program especially for them.
The Titan V also "only" has 640 of them. I suspect its successor will cram in many more.
They can multiply a small matrix in a single cycle (the tensor cores).
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.

Milos
Posts: 3988
Joined: Wed Nov 25, 2009 12:47 am

Re: how good is a GeForce GTX 1060 6GB for Leela ?

Post by Milos » Tue May 01, 2018 4:51 pm

Werewolf wrote:
Milos wrote:
Judging be the current proper benchmark (LC0 on cuDNN), Titan V is only 3.5 times faster than GTX 960, and 2.2 times 1080ti. And GTX 960 is at least 15 times cheaper than Titan V.
How do you work that out? The Titan V isn't 2.2x faster than a 1080 ti according to either the GFLOPS (12300 vs 10600 respectively) or the benchmarks here

https://docs.google.com/spreadsheets/d/ ... edit#gid=0

Unless I'm misreading them.
You should look at windows version of LC0-cudnn on Titan V since CUDA libs for windows are obviously better for tensor cores (Titan V) than linux ones.

Milos
Posts: 3988
Joined: Wed Nov 25, 2009 12:47 am

Re: how good is a GeForce GTX 1060 6GB for Leela ?

Post by Milos » Tue May 01, 2018 4:55 pm

Dann Corbit wrote:
Werewolf wrote:
Dann Corbit wrote:Titan V has tensor cores.
But they are fiddly to use and you have to program especially for them.
The Titan V also "only" has 640 of them. I suspect its successor will cram in many more.
They can multiply a small matrix in a single cycle (the tensor cores).
4x4 one to be precise. Since LC0 kernal is 3x3 there is roughly only 1/3 efficiency ((27+9*2)/(81+16*3) operations) when running LC0 only on tensor cores, assuming ofc that they are fully loaded and that cuDNN libs are efficient for them, which is a big question mark at the moment.

Albert Silver
Posts: 2964
Joined: Wed Mar 08, 2006 8:57 pm
Location: Rio de Janeiro, Brazil

Re: how good is a GeForce GTX 1060 6GB for Leela ?

Post by Albert Silver » Tue May 01, 2018 5:00 pm

Milos wrote:
Werewolf wrote:
Milos wrote:
Judging be the current proper benchmark (LC0 on cuDNN), Titan V is only 3.5 times faster than GTX 960, and 2.2 times 1080ti. And GTX 960 is at least 15 times cheaper than Titan V.
How do you work that out? The Titan V isn't 2.2x faster than a 1080 ti according to either the GFLOPS (12300 vs 10600 respectively) or the benchmarks here

https://docs.google.com/spreadsheets/d/ ... edit#gid=0

Unless I'm misreading them.
You should look at windows version of LC0-cudnn on Titan V since CUDA libs for windows are obviously better for tensor cores (Titan V) than linux ones.
Is it enough to download and install CUDA or do I need something else such as special commandline or executable? If so, can you point the way?
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."

Milos
Posts: 3988
Joined: Wed Nov 25, 2009 12:47 am

Re: how good is a GeForce GTX 1060 6GB for Leela ?

Post by Milos » Tue May 01, 2018 5:04 pm

Albert Silver wrote:
Milos wrote:
Werewolf wrote:
Milos wrote:
Judging be the current proper benchmark (LC0 on cuDNN), Titan V is only 3.5 times faster than GTX 960, and 2.2 times 1080ti. And GTX 960 is at least 15 times cheaper than Titan V.
How do you work that out? The Titan V isn't 2.2x faster than a 1080 ti according to either the GFLOPS (12300 vs 10600 respectively) or the benchmarks here

https://docs.google.com/spreadsheets/d/ ... edit#gid=0

Unless I'm misreading them.
You should look at windows version of LC0-cudnn on Titan V since CUDA libs for windows are obviously better for tensor cores (Titan V) than linux ones.
Is it enough to download and install CUDA or do I need something else such as special commandline or executable? If so, can you point the way?
You need to compile proper executable, however there are already precompiles available.
Look here:
https://github.com/mooskagh/leela-chess/tree/master/lc0

Albert Silver
Posts: 2964
Joined: Wed Mar 08, 2006 8:57 pm
Location: Rio de Janeiro, Brazil

Re: how good is a GeForce GTX 1060 6GB for Leela ?

Post by Albert Silver » Tue May 01, 2018 5:26 pm

Milos wrote:
Albert Silver wrote:
Milos wrote:
Werewolf wrote:
Milos wrote:
Judging be the current proper benchmark (LC0 on cuDNN), Titan V is only 3.5 times faster than GTX 960, and 2.2 times 1080ti. And GTX 960 is at least 15 times cheaper than Titan V.
How do you work that out? The Titan V isn't 2.2x faster than a 1080 ti according to either the GFLOPS (12300 vs 10600 respectively) or the benchmarks here

https://docs.google.com/spreadsheets/d/ ... edit#gid=0

Unless I'm misreading them.
You should look at windows version of LC0-cudnn on Titan V since CUDA libs for windows are obviously better for tensor cores (Titan V) than linux ones.
Is it enough to download and install CUDA or do I need something else such as special commandline or executable? If so, can you point the way?
You need to compile proper executable, however there are already precompiles available.
Look here:
https://github.com/mooskagh/leela-chess/tree/master/lc0
Ok, that worked, thanks. I had downloaded CUDA 9.1, so renamed the files to 90 where needed. How do I do a full-tune? Or is that no longer done?
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."

Milos
Posts: 3988
Joined: Wed Nov 25, 2009 12:47 am

Re: how good is a GeForce GTX 1060 6GB for Leela ?

Post by Milos » Tue May 01, 2018 5:27 pm

Albert Silver wrote:
Milos wrote:
Albert Silver wrote:
Milos wrote:
Werewolf wrote:
Milos wrote:
Judging be the current proper benchmark (LC0 on cuDNN), Titan V is only 3.5 times faster than GTX 960, and 2.2 times 1080ti. And GTX 960 is at least 15 times cheaper than Titan V.
How do you work that out? The Titan V isn't 2.2x faster than a 1080 ti according to either the GFLOPS (12300 vs 10600 respectively) or the benchmarks here

https://docs.google.com/spreadsheets/d/ ... edit#gid=0

Unless I'm misreading them.
You should look at windows version of LC0-cudnn on Titan V since CUDA libs for windows are obviously better for tensor cores (Titan V) than linux ones.
Is it enough to download and install CUDA or do I need something else such as special commandline or executable? If so, can you point the way?
You need to compile proper executable, however there are already precompiles available.
Look here:
https://github.com/mooskagh/leela-chess/tree/master/lc0
Ok, that worked, thanks. I had downloaded CUDA 9.1, so renamed the files to 90 where needed. How do I do a full-tune? Or is that no longer done?
Download 9.0 directly it is available from NVIDIA just search other releases.
Tuning is not required since cuDNN is already tuned to your specific GPU.

Post Reply