Ethereal Pawn-King NN
Moderators: hgm, Rebel, chrisw
-
- Posts: 1871
- Joined: Sat Nov 25, 2017 2:28 pm
- Location: France
Re: Ethereal Pawn-King NN
Does you training pytorch code calling Ethereal search/qsearch/eval from outside or do you managed to use only pre-computed data for learning ?
-
- Posts: 1756
- Joined: Tue Apr 19, 2016 6:08 am
- Location: U.S.A
- Full name: Andrew Grant
Re: Ethereal Pawn-King NN
Pre computed data only. I store off a half dozen values about the position's evaluation. There is no interfacing between Ethereal and the Pytorch code. Which is why I'm not planning on sharing it at this time.
#WeAreAllDraude #JusticeForDraude #RememberDraude #LeptirBigUltra
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )
-
- Posts: 2439
- Joined: Sat Sep 03, 2011 7:25 am
- Location: Berlin, Germany
- Full name: Stefan Pohl
Re: Ethereal Pawn-King NN
Yes, please. I would like to do a 7000 games testrun for my ratinglist (need compile for AMD Ryzen). Because, at the moment there is no other test running, I could start the test immediately and the result would go online 2 days later.AndrewGrant wrote: ↑Sat Sep 19, 2020 7:34 pm If there is interest, I can generate some compilations for Windows
https://www.sp-cc.de
-
- Posts: 38
- Joined: Tue Jan 01, 2019 9:34 am
- Full name: Siddhartha Chaudhary
Re: Ethereal Pawn-King NN
lots of user waiting for android verison ,kindly share it also.
-
- Posts: 1871
- Joined: Sat Nov 25, 2017 2:28 pm
- Location: France
Re: Ethereal Pawn-King NN
I kinda think that is the way to go indeed. And this allows using python frameworks and gpu things, ...AndrewGrant wrote: ↑Sun Sep 20, 2020 12:13 pmPre computed data only. I store off a half dozen values about the position's evaluation. There is no interfacing between Ethereal and the Pytorch code. Which is why I'm not planning on sharing it at this time.
-
- Posts: 1756
- Joined: Tue Apr 19, 2016 6:08 am
- Location: U.S.A
- Full name: Andrew Grant
Re: Ethereal Pawn-King NN
So I kinda went AWOL in this thread, since I discovered a disconnect between training and actual implementation. I thought surely I could fix that quickly and gain a ton more elo. Turns out, not so much, at least for Standard. I did sort out FRC though.
Here are a bunch of binaries:
We have the usual NOPOPCNT, POPCNT, and PEXT, and Android ones. As well as SEE4.1 versions of both POPCNT and PEXT. I'm not explicitly using any fancy vector operations, but the compiler does do them for me in some cases. I suspect the SEE4.1s should be faster for those with modern architectures, but I do not know truthfully. This is something I will have to sort out before Ethereal 12.75, since I want to make sure I provide the (Windows) testers with the best binaries possible.
Here are a bunch of binaries:
We have the usual NOPOPCNT, POPCNT, and PEXT, and Android ones. As well as SEE4.1 versions of both POPCNT and PEXT. I'm not explicitly using any fancy vector operations, but the compiler does do them for me in some cases. I suspect the SEE4.1s should be faster for those with modern architectures, but I do not know truthfully. This is something I will have to sort out before Ethereal 12.75, since I want to make sure I provide the (Windows) testers with the best binaries possible.
#WeAreAllDraude #JusticeForDraude #RememberDraude #LeptirBigUltra
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )
-
- Posts: 2439
- Joined: Sat Sep 03, 2011 7:25 am
- Location: Berlin, Germany
- Full name: Stefan Pohl
Re: Ethereal Pawn-King NN
Cool! Thank you very much. Testrun will start tomorrow, when the Igel 2.8.0 testrun is finished.
I tried both popcount compiles on my AMD Ryzen 3900 CPU and can report, that the normal popcount compile is a little bit faster, than the popcount SEE4.1. But the difference is very small (below 2%). I will use the popcount compile for my testrun.
I tried both popcount compiles on my AMD Ryzen 3900 CPU and can report, that the normal popcount compile is a little bit faster, than the popcount SEE4.1. But the difference is very small (below 2%). I will use the popcount compile for my testrun.
-
- Posts: 1756
- Joined: Tue Apr 19, 2016 6:08 am
- Location: U.S.A
- Full name: Andrew Grant
Re: Ethereal Pawn-King NN
Thanks for the pending test, and thanks for the speed test.pohl4711 wrote: ↑Fri Sep 25, 2020 5:27 am Cool! Thank you very much. Testrun will start tomorrow, when the Igel 2.8.0 testrun is finished.
I tried both popcount compiles on my AMD Ryzen 3900 CPU and can report, that the normal popcount compile is a little bit faster, than the popcount SEE4.1. But the difference is very small (below 2%). I will use the popcount compile for my testrun.
#WeAreAllDraude #JusticeForDraude #RememberDraude #LeptirBigUltra
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )
-
- Posts: 4889
- Joined: Thu Mar 09, 2006 6:34 am
- Location: Pen Argyl, Pennsylvania
Re: Ethereal Pawn-King NN
Awesome , Windows with with above plus -mavx2 please. Thanks!peter wrote: ↑Sat Sep 19, 2020 8:22 pmGreat news, thank!AndrewGrant wrote: ↑Sat Sep 19, 2020 7:34 pm If there is interest, I can generate some compilations for Windows / Android users.
Windows SSE4.1-popcnt would be great.
Looking forward regards
-
- Posts: 1756
- Joined: Tue Apr 19, 2016 6:08 am
- Location: U.S.A
- Full name: Andrew Grant
Re: Ethereal Pawn-King NN
I'm assuming you have a Ryzen? If not, it should still work I imagine.
Thats compiled with march=znver1 as the target architecture.
#WeAreAllDraude #JusticeForDraude #RememberDraude #LeptirBigUltra
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )
"Those who can't do, clone instead" - Eduard ( A real life friend, not this forum's Eduard )