During the pandemic I rediscovered chess and played a lot of games with my friends.
Then I started to program my first engine python-smallbrain in python, with the help of python-chess.
I quickly realized how slow python is for chess engine programming, so I started to learn C++.
My first try was cppsmallbrain, though after some time I found the code very buggy and ugly.
So I started Smallbrain from scratch, during that time, I also joined Stockfish development.
After some time I began implementing a NNUE into Smallbrain, with the help of Luecx from Koivisto.
As of now Smallbrain has a NNUE trained on 500m depth 9 fens generated with the built in data generator and using CudAD trainer to ultimately train the network.
The latest development version support for FRC has been added, the neural network has been retrained
with additional FRC data while being on par in classical.
Compile it using the Makefile in ./src
make
.\smallbrain.exe bench
compare the Bench with the Bench in the commit messages, they should be the same.
or download the latest the latest executable directly over Github.
At the bottom you should be able to find multiple different compiles, choose one that doesnt crash.
Ordered by performance you should try x86-64-avx2 first then x86-64-modern and at last x86-64.
| Name | Elo | + | - |
|---|---|---|---|
| Smallbrain 6.0 4CPU | 3309 | +24 | −23 |
| Smallbrain 6.0 | 3227 | +23 | −23 |
| Smallbrain 5.0 4CPU | 3211 | +23 | −23 |
| Smallbrain 5.0 | 3137 | +20 | −20 |
| Smallbrain 4.0 | 2978 | +25 | −25 |
| Smallbrain 2.0 | 2277 | +28 | −29 |
| Smallbrain 1.1 | 2224 | +29 | −30 |
| Name | Elo | + | - |
|---|---|---|---|
| Smallbrain 6.0 | 3336 | +18 | −18 |
| Smallbrain 5.0 | 3199 | +18 | −18 |
| Smallbrain 4.0 | 3005 | +18 | −18 |
| Smallbrain 3.0 | 2921 | +20 | −20 |
| Smallbrain 1.1 | 2174 | +20 | −20 |
| no | Program | Elo | + | - | Games | Score | Av.Op. | Draws |
|---|---|---|---|---|---|---|---|---|
| 34 | Smallbrain 6.0 avx2 | 3345 | 7 | 7 | 9000 | 52.1% | 3331 | 49.9% |
| no | Program | Elo | + | - | Games | Score | Av.Op. | Draws |
|---|---|---|---|---|---|---|---|---|
| 271 | Smallbrain 6.0NN x64 1CPU | 3203 | 16 | 16 | 1300 | 42.8% | 3258 | 51.2% |
-
Hash
The size of the hash table in MB. -
Threads
The number of threads used for search. -
EvalFile
The neural net used for the evaluation,
currently only default.nnue exist. -
SyzygyPath
Path to the syzygy files.
-
go perft <depth>
calculates perft from a set position up to depth. -
print
prints the current board -
captures
prints all legal captures for a set position. -
moves
prints all legal moves for a set position. -
rep
checks for threefold repetition in a position -
eval
prints the evaluation of the board. -
perft
tests all perft position.
- Evaluation
- As of v6.0 the NNUE training dataset was regenerated using depth 9 selfplay games + random 8 piece combinations.
* .\smallbrain.exe -gen -threads \<int> -book \<path/to/book> -tb \<path/to/tb> -depth \<int>
- Example:
.\smallbrain.exe -gen -threads 30 -book E:\Github\Smallbrain\src\data\DFRC_openings.epd -tb E:/Chess/345
.\smallbrain.exe -gen -threads 30 -tb E:/Chess/345