Does anyone have a rough ballpark figure of how much it would cost to develop SF9 (when it comes out) onto an ASIC which would be in a standalone box, able to be plugged into a PC?
I've heard ASIC costs are dropping and one friend was seriously considering raising some cash for this providing it wasn't in millions of dollars.
And any guesses on NPS?
Stockfish 9 ASIC
Moderators: hgm, Rebel, chrisw
-
- Posts: 1080
- Joined: Fri Sep 16, 2016 6:55 pm
- Location: USA/Minnesota
- Full name: Leo Anger
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: Stockfish 9 ASIC
You don't need an ASIC. You can take Xilinx Ultrascale+ Virtex eval board (they are 7k$ per piece). Implement on it movegen, qsearch + eval of SF, and make a version of MCTS SF running on regular PC.Werewolf wrote:Does anyone have a rough ballpark figure of how much it would cost to develop SF9 (when it comes out) onto an ASIC which would be in a standalone box, able to be plugged into a PC?
I've heard ASIC costs are dropping and one friend was seriously considering raising some cash for this providing it wasn't in millions of dollars.
And any guesses on NPS?
You plug 4 boards in PCIe gen 4 slot. Boards have their own hash.
You easily get 10 million nodes per each of the boards.
So effectively you'd get 40 million MCTS simulations per sec, each of the quality of A0 one.
From Fig 2. of A0 you could get the scaling, but roughly 300-400Elo over A0.
The whole hardware cost 30k$.
Designing power required 5000-10000 man hours or 2-3PY.
-
- Posts: 1796
- Joined: Thu Sep 18, 2008 10:24 pm
Re: Stockfish 9 ASIC
This looks like it requires specialist knowledge though. I was hoping to be able to handover code to a design team (IBM etc) and get them to develop an ASIC.Milos wrote:You don't need an ASIC. You can take Xilinx Ultrascale+ Virtex eval board (they are 7k$ per piece). Implement on it movegen, qsearch + eval of SF, and make a version of MCTS SF running on regular PC.Werewolf wrote:Does anyone have a rough ballpark figure of how much it would cost to develop SF9 (when it comes out) onto an ASIC which would be in a standalone box, able to be plugged into a PC?
I've heard ASIC costs are dropping and one friend was seriously considering raising some cash for this providing it wasn't in millions of dollars.
And any guesses on NPS?
You plug 4 boards in PCIe gen 4 slot. Boards have their own hash.
You easily get 10 million nodes per each of the boards.
So effectively you'd get 40 million MCTS simulations per sec, each of the quality of A0 one.
From Fig 2. of A0 you could get the scaling, but roughly 300-400Elo over A0.
The whole hardware cost 30k$.
Designing power required 5000-10000 man hours or 2-3PY.
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: Stockfish 9 ASIC
Designing digital core in ASIC is for an order of magnitude more complex than on FPGA.Werewolf wrote:This looks like it requires specialist knowledge though. I was hoping to be able to handover code to a design team (IBM etc) and get them to develop an ASIC.
-
- Posts: 273
- Joined: Wed Aug 24, 2016 9:49 pm
Re: Stockfish 9 ASIC
"Each of the qualitiy of A0 "Milos wrote:You don't need an ASIC. You can take Xilinx Ultrascale+ Virtex eval board (they are 7k$ per piece). Implement on it movegen, qsearch + eval of SF, and make a version of MCTS SF running on regular PC.Werewolf wrote:Does anyone have a rough ballpark figure of how much it would cost to develop SF9 (when it comes out) onto an ASIC which would be in a standalone box, able to be plugged into a PC?
I've heard ASIC costs are dropping and one friend was seriously considering raising some cash for this providing it wasn't in millions of dollars.
And any guesses on NPS?
You plug 4 boards in PCIe gen 4 slot. Boards have their own hash.
You easily get 10 million nodes per each of the boards.
So effectively you'd get 40 million MCTS simulations per sec, each of the quality of A0 one.
From Fig 2. of A0 you could get the scaling, but roughly 300-400Elo over A0.
The whole hardware cost 30k$.
Designing power required 5000-10000 man hours or 2-3PY.
You throw statements like that around without any justification
That's just impossible to know for now until we get our copies of A0
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: Stockfish 9 ASIC
If it was like that, any statement would be impossible since A0 would never gonna be released to public.CheckersGuy wrote:"Each of the qualitiy of A0 "
You throw statements like that around without any justification
That's just impossible to know for now until we get our copies of A0
But ofc it is possible to estimate performance of A0 NN based on Fig. 2 from the paper. A0 crosses SF performance at 400ms/move. That is equivalent to 32000 nodes evaluation. So running MCTS from the paper with qsearch of SF instead of NN and with 32000 qsearches per second vs. SF8 on 64 cores would give us an answer.
-
- Posts: 273
- Joined: Wed Aug 24, 2016 9:49 pm
Re: Stockfish 9 ASIC
Implement mcts SF first and show us some benchmarks and then make your pointMilos wrote:If it was like that, any statement would be impossible since A0 would never gonna be released to public.CheckersGuy wrote:"Each of the qualitiy of A0 "
You throw statements like that around without any justification
That's just impossible to know for now until we get our copies of A0
But ofc it is possible to estimate performance of A0 NN based on Fig. 2 from the paper. A0 crosses SF performance at 400ms/move. That is equivalent to 32000 nodes evaluation. So running MCTS from the paper with qsearch of SF instead of NN and with 32000 qsearches per second vs. SF8 on 64 cores would give us an answer.
-
- Posts: 4190
- Joined: Wed Nov 25, 2009 1:47 am
Re: Stockfish 9 ASIC
I'll first get Nature publication then I'll show you results .CheckersGuy wrote:Implement mcts SF first and show us some benchmarks and then make your point
I guess it will be enough to show results from the match with SF8 on 1 core, 32MB Hash, no opening book, no EGBT vs MC SF on 32 cores, egbt, 32GB Hash, playing from starting position .
-
- Posts: 3707
- Joined: Thu Mar 16, 2006 7:10 pm
Re: Stockfish 9 ASIC
Surely FPGA would be a much better idea. ASIC cannot be updated and for sure SF would need continuous tuning. Also the number of units that would be produced would be very few, thus would make no commercial sense to go ASIC. FPGA has been used in chess engines before and maybe A0 will make this platform interesting again.