AMD Threadripper 2990x seems out what is the gain vs 1950x ?

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

Moderators: bob, hgm, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
jpqy
Posts: 523
Joined: Thu Apr 24, 2008 7:31 am
Location: Belgium

Re: AMD Threadripper 2990x seems out what is the gain vs 1950x ?

Post by jpqy » Mon Nov 19, 2018 7:32 am

Here you have some benches and a compare :

http://www.ipmanchess.yolasite.com/amd- ... -bench.php

JP.

Leo
Posts: 843
Joined: Fri Sep 16, 2016 4:55 pm
Location: USA/Minnesota
Full name: Leo

Re: AMD Threadripper 2990x seems out what is the gain vs 1950x ?

Post by Leo » Mon Nov 19, 2018 9:38 pm

jpqy wrote:
Mon Nov 19, 2018 7:32 am
Here you have some benches and a compare :

http://www.ipmanchess.yolasite.com/amd- ... -bench.php

JP.
Thanks. Pretty impressive. About 8 years ago 30,000 nps was really good.
Advanced Micro Devices fan.

Michael Sherwin
Posts: 3046
Joined: Fri May 26, 2006 1:00 am
Location: WY, USA
Full name: Michael Sherwin

Re: AMD Threadripper 2990x seems out what is the gain vs 1950x ?

Post by Michael Sherwin » Sun Nov 25, 2018 8:06 pm

To gain the best advantage of the Threadripper 2990wx in a bitboard engine avoid magic bitboards or any other memory intensive variation. Also a smaller hash might result in better node/second performance. The reason for this is that there is a memory access bottleneck imposed on the 16 additional cores that is so inefficient that 32 cores can in memory intensive programs run slower than 16 cores.
I hate if statements. Pawns demand if statements. Therefore I hate pawns.

Leo
Posts: 843
Joined: Fri Sep 16, 2016 4:55 pm
Location: USA/Minnesota
Full name: Leo

Re: AMD Threadripper 2990x seems out what is the gain vs 1950x ?

Post by Leo » Sun Nov 25, 2018 8:13 pm

Michael Sherwin wrote:
Sun Nov 25, 2018 8:06 pm
To gain the best advantage of the Threadripper 2990wx in a bitboard engine avoid magic bitboards or any other memory intensive variation. Also a smaller hash might result in better node/second performance. The reason for this is that there is a memory access bottleneck imposed on the 16 additional cores that is so inefficient that 32 cores can in memory intensive programs run slower than 16 cores.
Is Stockfish a bitboard engine? What is a magic bitboard? What size hash would you recommend?
Advanced Micro Devices fan.

Werewolf
Posts: 1198
Joined: Thu Sep 18, 2008 8:24 pm

Re: AMD Threadripper 2990x seems out what is the gain vs 1950x ?

Post by Werewolf » Sun Nov 25, 2018 8:29 pm

Dann Corbit wrote:
Thu Aug 16, 2018 6:22 pm
The 32 core threadripper also has stunted memory access.
Presumably EPYC doesn't.

Michael Sherwin
Posts: 3046
Joined: Fri May 26, 2006 1:00 am
Location: WY, USA
Full name: Michael Sherwin

Re: AMD Threadripper 2990x seems out what is the gain vs 1950x ?

Post by Michael Sherwin » Sun Nov 25, 2018 8:43 pm

Leo wrote:
Sun Nov 25, 2018 8:13 pm
Michael Sherwin wrote:
Sun Nov 25, 2018 8:06 pm
To gain the best advantage of the Threadripper 2990wx in a bitboard engine avoid magic bitboards or any other memory intensive variation. Also a smaller hash might result in better node/second performance. The reason for this is that there is a memory access bottleneck imposed on the 16 additional cores that is so inefficient that 32 cores can in memory intensive programs run slower than 16 cores.
Is Stockfish a bitboard engine? What is a magic bitboard? What size hash would you recommend?
Is Stockfish a bitboard engine? Yes Although I have not investigated what kind.

What is a magic bitboard? I don't have that definition in memory anymore, LOL. Anyway Crafty uses magic bitboards and does terrible nodes/second compared to Stockfish which I believe is not magic bitboard.

What size hash for stockfish? Trial and error would be the answer there as I do not have a 2990wx system.
I hate if statements. Pawns demand if statements. Therefore I hate pawns.

mar
Posts: 2010
Joined: Fri Nov 26, 2010 1:00 pm
Location: Czech Republic
Full name: Martin Sedlak

Re: AMD Threadripper 2990x seems out what is the gain vs 1950x ?

Post by mar » Sun Nov 25, 2018 10:07 pm

Michael Sherwin wrote:
Sun Nov 25, 2018 8:43 pm
Anyway Crafty uses magic bitboards and does terrible nodes/second compared to Stockfish
Do you have any data on that? I remember Crafty actually had probably the highest nps I ever saw (not so long ago).
Anyway - comparing nps of two different engines is irrelevant, also it doesn't correlate well with elo,
an engine with half/quarter the nps of another can still be hundreds of elo stronger.
Martin Sedlak

Michael Sherwin
Posts: 3046
Joined: Fri May 26, 2006 1:00 am
Location: WY, USA
Full name: Michael Sherwin

Re: AMD Threadripper 2990x seems out what is the gain vs 1950x ?

Post by Michael Sherwin » Sun Nov 25, 2018 10:23 pm

mar wrote:
Sun Nov 25, 2018 10:07 pm
Michael Sherwin wrote:
Sun Nov 25, 2018 8:43 pm
Anyway Crafty uses magic bitboards and does terrible nodes/second compared to Stockfish
Do you have any data on that? I remember Crafty actually had probably the highest nps I ever saw (not so long ago).
Anyway - comparing nps of two different engines is irrelevant, also it doesn't correlate well with elo,
an engine with half/quarter the nps of another can still be hundreds of elo stronger.
Crafty on a 32 core TR 2990wx is not faster than on a 16 core TR 2950x while SF gains about 65% more nodes per second moving from the TR 2950 to the TR 2990wx. The reason that SF does not double it's node rate from the 50 to the 90 is because the hashtable still weighs on the memory bottleneck. So to try to be clear there is no comparison being done directly between SF and Crafty. The comparison is between Crafty and Crafty and between SF and SF on the different processors.
I hate if statements. Pawns demand if statements. Therefore I hate pawns.

Dann Corbit
Posts: 10188
Joined: Wed Mar 08, 2006 7:57 pm
Location: Redmond, WA USA
Contact:

Re: AMD Threadripper 2990x seems out what is the gain vs 1950x ?

Post by Dann Corbit » Mon Nov 26, 2018 7:32 pm

Werewolf wrote:
Sun Nov 25, 2018 8:29 pm
Dann Corbit wrote:
Thu Aug 16, 2018 6:22 pm
The 32 core threadripper also has stunted memory access.
Presumably EPYC doesn't.
Correct. Epyc has twice the memory bandwidth.
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.

Post Reply