Spaghet BologNNese 1.0

I am pleased to release Spaghet BologNNese 1.0, which is up 150 selfplay elo stronger depending on the opening book.

I've implemented:

• Output buckets (8 linear buckets)
• SIMD Inference, which is about a 20% speedup
• Lazy SMP multithreading

Estimated CCRL Elo: ~3500

Features to look forward to in the next release:

• Thread Voting
• King buckets
• Quadratic output buckets

Progression Tests

STC Pohl:

Elo   | 151.82 +- 10.56 (95%)
Conf  | 8.0+0.08s Threads=1 Hash=8MB
Games | N: 1508 W: 762 L: 142 D: 604
Penta | [0, 16, 215, 410, 113]
https://chess.aronpetkovski.com/test/2143/

LTC Pohl:

Elo   | 147.44 +- 10.90 (95%)
Conf  | 40.0+0.40s Threads=1 Hash=64MB
Games | N: 1006 W: 476 L: 73 D: 457
Penta | [0, 9, 122, 332, 40]

STC 8moves:

Elo   | 139.12 +- 10.45 (95%)
Conf  | 8.0+0.08s Threads=1 Hash=8MB
Games | N: 1504 W: 609 L: 37 D: 858
Penta | [0, 13, 263, 367, 109]

LTC 8moves:

Elo   | 109.83 +- 10.96 (95%)
Conf  | 40.0+0.40s Threads=1 Hash=64MB
Games | N: 1000 W: 322 L: 16 D: 662
Penta | [0, 7, 218, 237, 38]

SPECIAL THANKS:

• @aronpetko
• @xu-shawn
• @Yoshie2000
• @ArjunBasandrai
• @gab8192
• @Haxk20
• @Vast342

for sharing an instance, hardware, and ideas,

• Zuppa
• fireandice
• Ciekce
• Vast
• Somelizard

for helping me with NNUE and other search features,
and @noobpwnftw for generously donating hardware to furybench.

Spaghet MariNNara 1.0

This release marks the inclusion of NNUE, with the architecture being (768 -> 2048)x2 -> 1 and trained on Leela data

This release also has improved readability due to my search_stack rewrite

Notable search features include:

• Singular Extensions
• Multicut
• Continuation History
• Capture History
• Better TT replacement

Estimated CCRL Elo: ~3450 (tested against PlentyChess 0.2.1)

Features to look forward to in the next major release:

• Multithreading
• Output Buckets
• SIMD NNUE inference

The old version of Spaghet fails to make a single draw against this update, so there will be no progtest

SPECIAL THANKS:

• fury
• shawn_xu
• Yoshie2000
• Arjun Basandrai
• gabe

for sharing an instance, hardware, and ideas,

• Zuppa
• fireandice
• Ciekce
• Vast
• Somelizard

for helping me with NNUE and other search features.

Spaghet Pesto 1.0

~2750 CCRL

(Compared to unofficial version 0.1)
+148 STC
+124 LTC