Final Release of Ethereal, V12.75

[nabildanial]

Here is a compile using the "make release" flag.

I've deleted my compile since Andrew has released the official(?) one.

[AndrewGrant]

Here is a compile using the "make release" flag.

I've deleted my compile since Andrew has released the official(?) one.

Sure. We can use the word official for the Ethereal 12.75 SF-NNUE.

So I took a trick that I learned from some forum, and then saw put into practice in Cfish. Which is to look at the things defined when march=native is used, and then set the flags for vector maths basedon those. Its a brilliant trick. However, it assumes march=native. When you built for release, march=native was not set, and those flags were not updated. So you were using the slowest possible Ethereal compile. I imagine it was 2x or even 4x as slow.

[Rebel]

Ethereal 12.75 SF-NNUE +172

http://rebel13.nl/dump/mrl-lcx.html

Would you be interested in adding Stockfish 12 Classical to your list? I'm interested in that Ethereal without NNUE actually beats out Komodo and Houdini. Maybe an indicator that Ethereal's evaluation is very solid? I would not be surprised if it beats Komodo's. They've got more knowledge, but I'm confident mine is tuned better.

Compare with - http://rebel13.nl/download/srl-1000.html

Both 3171 -> draw

[Guenther]

Here is a compile using the "make release" flag.

I've deleted my compile since Andrew has released the official(?) one.

I have compiled one yesterday for people w/o popcount (but still SSE 4.1), because there is no such
in the 'official' download at all. If someone is interested or needs it, just PM me.

[Sylwy]

Yeah, this is a fine compile. Thank you !


The yesterday compile (nabildanial):


I resumed my match at TC=4'+2"

[nabildanial]

Yeah, this is a fine compile. Thank you !


The yesterday compile (nabildanial):


I resumed my match at TC=4'+2"

Welp, that was a huge slowdown! Sorry I didn't test the compile, I assumed the "make release" was the appropriate compile flag for it, because you know, it says release on it haha.

[Frank Quisinsky]

Hi Andrew,

thanks for your Ethereal version.
Time for a new FCP Tourney, but the old tourney is not ready yet.

Later ...

Best
Frank

[Madeleine Birchfield]

It looks like Andrew Grant might not be done with Ethereal yet:

https://github.com/AndyGrant/EtherealDe ... cffe1887ae
https://github.com/AndyGrant/EtherealDe ... cf421653a2

[MikeB]

It looks like Andrew Grant might not be done with Ethereal yet:

https://github.com/AndyGrant/EtherealDe ... cffe1887ae
https://github.com/AndyGrant/EtherealDe ... cf421653a2

Once it gets in your blood, it's hard to get out. "Chess programmers never die, they simply fade away."

[Madeleine Birchfield]

It looks like Andrew Grant might not be done with Ethereal yet:

https://github.com/AndyGrant/EtherealDe ... cffe1887ae
https://github.com/AndyGrant/EtherealDe ... cf421653a2

Once it gets in your blood, it's hard to get out. "Chess programmers never die, they simply fade away."

A few weeks ago, when everybody else was posting about Ethereal's final release version 12.75, Andrew Grant announced that he was writing his own neural network trainer, and then Halogen 7 came on the scene with a NNUE network that was trained on his trainer. So I thought, well, Andrew Grant probably doesn't want to get rid of his hard work on Ethereal's handcrafted evaluation function after trumpeting how much Ethereal's handcrafted evaluation function meant to him, so that is the reason why this was the final release of Ethereal, and his future would be working on Halogen with Kieren Pearson. But then earlier today he said that he wasn't working on Halogen; he was just testing his trainer with Halogen, which then brings up the question, then why did he write the trainer in the first place? Turns out in the dev version of Ethereal, he replaced whatever previous code he was using for endgames with a NNUE net, presumably trained using his trainer.