Ethereal 13.25 (NNUE) has been released. In addition to the usual updates to the search and evaluation algorithms, Ethereal is new using a newly trained NNUE, which factors in game results to achieve smoother and more stable evaluations in the endgame. Ethereal continues its legacy of stability and reliability for analysis and engine play.
Ethereal 13.25 (NNUE) includes two NNUE Networks for evaluation. These Networks are the second of their kind, boasting themselves as the only other high level NNUEs not derived from, trained on, nor duplicated from the works of the Stockfish team. With it, Ethereal adds new ideas and techniques to extend existing machine learning algorithms, and adds original practices into the implementation. These new approaches in software design allow for older processors to outperform NNUEs found in other engines, while still harnessing the full power of the AVX/AVX2 instruction sets for CPUs with support.
Additionally, Ethereal is the first engine to offer a secondary Network trained exclusively for Fischer Random Chess (FRC). This Network outperforms the standard Network by significant margins in FRC play, showcasing a creative style by Ethereal, not reliant on Opening Theory. These Neural Networks offer up to +60 elo over Ethereal 13.00 in self-play for Standard Chess, the culmination of over 317,000,000 games played between various versions of Ethereal.
The commercial NNUE version requires a CPU with the SSSE3 instruction set (which almost all CPUs have), and will not run on systems lacking these instructions. AVX/AVX2 have become ubiquitous in modern processor design, and are necessary to capitalize on the full strength of Neural Network technology. If you are unsure if your system is supported, please reach out to me via email at andrew@grantnet.us for assistance.
Stripe will verify your payment of $40 USD. Afterwards, you will receive an email from andrew@grantnet.us or andrewgrantethereal@gmail.com within 24 hours containing a download link for the Standard/Fischer NNUE Networks, as well as the binary or executable files for Windows and Linux. You should select the binary matching your Operating System. Users with Intel CPUs containing BMI2 support (Also known as PEXT), should use the pext binary for optimal performance. AMD CPU users should use the popcnt binary, unless they have a 5XXX series Ryzen. AVX2 binaries will be the fastest, followed by AVX, and finally SSSE3. You should use the fastest your CPU allows.
If Stripe is not possible for you, PayPal is also an option. Using PayPal as a merchant account proved to be unworkable. However, you can send a payment of $40 USD to andrew@grantnet.us via the "Send & Request" button. This process is not yet automated, so I will have to build and send binaries by hand. If you are able to use Stripe, that is my preference. PayPal charges greater fees for foreign currency conversions, and I do not pass any fees on to the buyer.
If you purchased Ethereal 13.00, you should have received an email containing updates to 13.25. If you did not, and the email cannot be found in your spam folder, please reach out to me via andrew@grantnet.us or andrewgrantethereal@gmail.com.
---
Code: Select all
// Regression test using a drawish book
ELO | 57.45 +- 1.78 (95%)
CONF | 60.0+0.60s Threads=1 Hash=64MB
GAMES | N: 40000 W: 9019 L: 2465 D: 28516
http://chess.grantnet.us/test/12863/
While Ethereal without NNUE still exists, and can be compiled directly from the source with ease, I have not provided binary files. This is because the strength of NNUE makes the standard version obsolete for high tier game-play, like rating lists, tournaments, and correspondence analysis. In the future I may add support for machines lacking AVX2 support, but have not done so at this time. All new CPUs being released contain the instruction set for many years now. As Neural Network technology takes over computer chess, those lacking modern vector support will have difficulty seeing the same gains as those with advanced vector support.