Calculate Elo increased based on having 8, 16 or 32 cores ?

[Chessqueen]

Using the same GHz speed can somebody calculate how much Elo is gained by Stockfish or Komodo by doubling the cores lets say from 4 to 8 or from 8 to 16 cores. ?

[Chessqueen]

Using the same GHz speed can somebody calculate how much Elo is gained by Stockfish or Komodo by doubling the cores lets say from 4 to 8 or from 8 to 16 cores. ?

I thought that Larry Kaufman already figured the rating increased of Komodo based on doubling the number of cores

[yurikvelo]

http://talkchess.com/forum3/viewtopic.php?t=74188

[lkaufman]

http://talkchess.com/forum3/viewtopic.php?t=74188

Those results were pre-NNUE, so may be outdated now. Most likely doubling of threads will show smaller elo gains now with NNUE, since the level on one thread is much higher to start with. Also those results were at a very fast tc, not representative of play at time controls actually used by anyone, so probably too high for that reason as well. But they do show that benefit drops sharply beyond 16 threads.

[Chessqueen]

http://talkchess.com/forum3/viewtopic.php?t=74188

Those results were pre-NNUE, so may be outdated now. Most likely doubling of threads will show smaller elo gains now with NNUE, since the level on one thread is much higher to start with. Also those results were at a very fast TC, not representative of play at time controls actually used by anyone, so probably too high for that reason as well. But they do show that benefit drops sharply beyond 16 threads.

That is what I thought that after 16 threads the benefit or Elo gain drops significantly.