People insist on believing nodes per second as a trust worthy benchmark for Stockfish, and other chess engines. But nothing can be further from the truth.
I will show that nodes per second is a meaningless stat in judging hardware speed for Stockfish. By showing my $1500 Laptop is far superior in running Stockfish then my Threadripper.
The test was run with the Stockfish bench mark command for Stockfish 15.
bench 1024 32 26 default depth nnue - Threadripper
bench 1024 8 26 default depth nnue - $1500 Laptop.
Theadripper Results.
NPS = 21,956,331
$1500 Laptop Results.
NPS = 13,699,948
The Threadripper is 1.6x faster in NPS. If your conclusion is the Threadripper is the faster computer running Stockfish. You would be dead wrong.
Solve time to complete the benchmark.
$1500 Laptop Total Solve Time Results.
Total Time (ms) 110,731
Threadripper Total Solve Time Results.
Total Time (ms) 199,936
The $1500 Laptop is 1.8x faster in completing the benchmark test.
How is this possible?
The answer is in how wildly inefficient Stockfish becomes as you add more and more threads.
Total Nodes searched for Threadripper.
Nodes Search 4,389,861,054
Total Nodes searched for $1500 Laptop.
Nodes Searched 1,517,009,043
The $1500 Laptop had to search 2.9x less nodes to complete the benchmark, and the Laptop cores are faster.
Threadripper results.
$1500 Laptop results.
Home 