| Finished | ||||||
|---|---|---|---|---|---|---|
| World | Reckless | tt-depth-lmr | diff | 8.0+0.08 | LLR: 2.92 (-2.25, 2.89) [0.00, 4.00] Games: 35428 W: 8452 L: 8212 D: 18764 Ptnml(0-2): 124, 4242, 8759, 4448, 141 | |
| World | Reckless | tt-clusters-2 | diff | 8.0+0.08 | LLR: 2.90 (-2.25, 2.89) [0.00, 4.00] Games: 2974 W: 759 L: 622 D: 1593 Ptnml(0-2): 6, 285, 777, 404, 15 | [2 threads, 2MB] implement clusters and ditch atomics |
| World | Reckless | tt-clusters-2 | diff | 8.0+0.08 | LLR: 3.00 (-2.25, 2.89) [0.00, 4.00] Games: 5012 W: 1268 L: 1116 D: 2628 Ptnml(0-2): 22, 521, 1274, 661, 28 | [1 thread, 2 MB] implement clusters and ditch atomics |
| World | Reckless | simplify-rfp-shift | diff | 8.0+0.08 | LLR: 2.90 (-2.25, 2.89) [-5.00, 0.00] Games: 15422 W: 3698 L: 3650 D: 8074 Ptnml(0-2): 72, 1851, 3808, 1917, 63 | remove const offset -20 in RFP |
| World | Reckless | alex | diff | N=25000 | Elo: 94.02 +- 3.77 (95%) [N=16000] Games: 17654 W: 8319 L: 3655 D: 5680 Ptnml(0-2): 188, 949, 3203, 2985, 1502 | |
| World | Reckless | threats-by-type | diff | N=25000 | LLR: 4.32 (-2.25, 2.89) [0.00, 4.00] Games: 13726 W: 4350 L: 4037 D: 5339 Ptnml(0-2): 366, 1541, 2840, 1646, 470 | 7% slowdown in STC, try fixed nodes |
| Styxdo | Reckless | main | diff | 8.0+0.08 | LLR: 2.92 (-2.25, 2.89) [0.00, 4.00] Games: 14308 W: 3451 L: 3283 D: 7574 Ptnml(0-2): 54, 1484, 3911, 1650, 55 | Summary: S1=50 (halved), batch_per_batchsize=12208 (doubled) S2=200 (doubled), batch_per_batchsize=2500(halved) |
| World | Reckless | hindsight-lmr | diff | 8.0+0.08 | LLR: 3.04 (-2.25, 2.89) [0.00, 4.00] Games: 26350 W: 6332 L: 6113 D: 13905 Ptnml(0-2): 111, 3092, 6554, 3303, 115 | decrease node depth if static score in LMR search gets worse |
| World | Reckless | linear-cutoff-count-lmr | diff | 8.0+0.08 | LLR: 3.05 (-2.25, 2.89) [0.00, 4.00] Games: 19856 W: 4816 L: 4615 D: 10425 Ptnml(0-2): 101, 2292, 4932, 2511, 92 | |
| World | Reckless | null-move-history | diff | 8.0+0.08 | LLR: 2.94 (-2.25, 2.89) [0.00, 4.00] Games: 52018 W: 12534 L: 12241 D: 27243 Ptnml(0-2): 244, 6121, 12991, 6404, 249 | adjust nmp margin by null move history (indexed by stm & previous move) |
| Peregr | Reckless | the_ultimate_patch | diff | 8.0+0.08 | LLR: 2.90 (-2.25, 2.89) [0.00, 4.00] Games: 11022 W: 2765 L: 2598 D: 5659 Ptnml(0-2): 56, 1231, 2774, 1390, 60 | Reduce PV less on larger window |
| Styxdo | Reckless | nmp_verification_search | diff | 8.0+0.08 | LLR: 3.24 (-2.25, 2.89) [-5.00, 0.00] Games: 10258 W: 2467 L: 2387 D: 5404 Ptnml(0-2): 41, 1230, 2510, 1304, 44 | Verification Search in nmp |
| World | Reckless | lmp-qsearch | diff | 8.0+0.08 | LLR: 2.96 (-2.25, 2.89) [0.00, 4.00] Games: 10770 W: 2661 L: 2490 D: 5619 Ptnml(0-2): 52, 1246, 2625, 1403, 59 | search 2 moves in qsearch at most |
| World | Reckless | l1-640 | diff | 8.0+0.08 | LLR: 2.89 (-2.25, 2.89) [0.00, 4.00] Games: 6676 W: 1758 L: 1603 D: 3315 Ptnml(0-2): 36, 725, 1668, 866, 43 | |
| World | Reckless | simd-force-v3 | diff | 8.0+0.08 | LLR: 2.92 (-2.25, 2.89) [-5.00, 0.00] Games: 8926 W: 2128 L: 2059 D: 4739 Ptnml(0-2): 34, 939, 2447, 1010, 33 | test AVX2 against main (enforce v3) |
| World | Reckless | simd-force-v2 | diff | 8.0+0.08 | LLR: 2.89 (-2.25, 2.89) [0.00, 4.00] Games: 1328 W: 387 L: 250 D: 691 Ptnml(0-2): 3, 92, 346, 211, 12 | test SSE4.1 against main (enforce v2) |
| World | Reckless | simplify-nmp-formula | diff | 8.0+0.08 | LLR: 2.90 (-2.25, 2.89) [-4.50, 0.00] Games: 11966 W: 2889 L: 2815 D: 6262 Ptnml(0-2): 50, 1291, 3231, 1357, 54 | simplify NMP formula regarding TT move |
| Peregr | Reckless | more_nmp | diff | 8.0+0.08 | LLR: 2.89 (-2.25, 2.89) [-5.00, 0.00] Games: 18664 W: 4444 L: 4409 D: 9811 Ptnml(0-2): 90, 2202, 4714, 2235, 91 | simplify this depth guard? |
| Peregr | Reckless | lmr_ttpv2 | diff | 8.0+0.08 | LLR: 2.94 (-2.25, 2.89) [0.00, 4.00] Games: 105460 W: 25237 L: 24780 D: 55443 Ptnml(0-2): 499, 12566, 26163, 12983, 519 | safer for ltc |
| World | Reckless | L1-640 | diff | N=25000 | LLR: 2.91 (-2.25, 2.89) [0.00, 4.00] Games: 4374 W: 1474 L: 1274 D: 1626 Ptnml(0-2): 135, 455, 841, 587, 169 | train NNUE with 128 more neurons in L1 |
| World | Reckless | fix-evasion-scoring | diff | 8.0+0.08 | LLR: 2.93 (-2.25, 2.89) [-5.00, 0.00] Games: 15214 W: 3552 L: 3505 D: 8157 Ptnml(0-2): 51, 1637, 4209, 1634, 76 | there was a hack to use the pawn value as the captured piece in noisy move scoring (since the ep square is empty). but this breaks promotions (their empty square is actually empty), so fix it |
| World | Reckless | nnue-refactoring | diff | 8.0+0.08 | LLR: 2.98 (-2.25, 2.89) [-10.00, 0.00] Games: 9938 W: 2334 L: 2353 D: 5251 Ptnml(0-2): 26, 1064, 2808, 1045, 26 | non-functional refactoring: extract accumulators, enforce consistent naming, remove useless alignment |
| World | Reckless | static-eval-history-3 | diff | 8.0+0.08 | LLR: 2.95 (-2.25, 2.89) [0.00, 4.00] Games: 18126 W: 4339 L: 4149 D: 9638 Ptnml(0-2): 67, 2136, 4482, 2296, 82 | more restrictive version in both delta and clamp |
| World | Reckless | nmp-iir | diff | 8.0+0.08 | LLR: 2.99 (-2.25, 2.89) [0.00, 4.00] Games: 50170 W: 11957 L: 11668 D: 26545 Ptnml(0-2): 211, 5950, 12500, 6187, 237 | |
| Peregr | Reckless | basic_pcm4 | diff | 8.0+0.08 | LLR: 2.92 (-2.25, 2.89) [0.00, 4.00] Games: 16414 W: 3957 L: 3774 D: 8683 Ptnml(0-2): 68, 1888, 4134, 2027, 90 | |