| Active : 1 Machines / 32 Threads / 22.0 MNPS | ||||||
|---|---|---|---|---|---|---|
| Priority 0 | ||||||
| Terje | Weiss | SingExtPvNodeDouble | diff | 10.0+0.10 | LLR: -0.66 (-2.94, 2.94) [0.00, 3.00] Games: 149284 W: 41755 L: 41405 D: 66124 Ptnml(0-2): 2617, 17703, 33674, 18009, 2639 | |
| Vshche | Igel | draw_fix | diff | 60.0+0.60 | LLR: -0.89 (-2.94, 2.94) [-3.00, 1.00] Games: 13396 W: 2446 L: 2483 D: 8467 Ptnml(0-2): 0, 699, 5338, 660, 1 | 3.6.39: fix draw detection |
| Rosent | Winter | net347_d24f64 * | diff | 40.0+0.40 | LLR: -2.31 (-2.94, 2.94) [0.00, 5.00] Games: 4416 W: 844 L: 916 D: 2656 Ptnml(0-2): 53, 525, 1116, 469, 45 | Another day another net. |
| Priority -5 | ||||||
| Kieren | Halogen | spsa_tune_21_50k | diff | 20.0+0.20 | LLR: 0.09 (-2.94, 2.94) [0.00, 3.00] Games: 1536 W: 399 L: 391 D: 746 Ptnml(0-2): 2, 164, 426, 176, 0 | |
| Terje | Weiss | Connectivity2 | diff | 60.0+0.60 | LLR: -2.17 (-2.94, 2.94) [0.00, 3.00] Games: 19396 W: 4960 L: 5051 D: 9385 Ptnml(0-2): 150, 2348, 4767, 2309, 124 | |
| Finished | ||||||
| Vshche | Igel | draw_fix | diff | 10.0+0.10 | LLR: 0.41 (-2.94, 2.94) [0.00, 2.00] Games: 43792 W: 8355 L: 8280 D: 27157 Ptnml(0-2): 15, 3046, 15703, 3113, 19 | 3.6.39: fix draw detection |
| Jhonno | Berserk | refactor/remove-setjmp-search | diff | 10.0+0.10 | LLR: 2.94 (-2.25, 2.89) [-2.00, 0.00] Games: 31618 W: 7773 L: 7571 D: 16274 Ptnml(0-2): 76, 3287, 8860, 3531, 55 | refactor: remove setjmp from search |
| Jhonno | Berserk | speedups | diff | 10.0+0.10 | LLR: 2.94 (-2.25, 2.89) [0.00, 2.00] Games: 11046 W: 2816 L: 2549 D: 5681 Ptnml(0-2): 28, 1086, 3028, 1353, 28 | perf: drop the pext slider path and the -pext binaries Since AVX2 builds compute slider attacks by hyperbola quintessence, the pext lookup only ever applied to targets that have BMI2 but not AVX2, which is not a combination worth carrying a second slider implementation for. Stockfish reached the same point and removed its pext path outright. That also collapses the release matrix. avx2-pext differed from avx2 only by -mbmi2, and avx512-pext existed because every AVX-512 part has BMI2, so both names now describe nothing. The Windows build script ships four binaries instead of five: x86-64, sse41, avx2, avx512. No functional change on any AVX2 host: the emitted code for a native build is byte identical before and after. Co-authored-by: Claude Agent <claude@home.arpa> |
| Vshche | Igel | draw_fix | diff | 10.0+0.10 | LLR: 2.97 (-2.94, 2.94) [-3.00, 1.00] Games: 11210 W: 2172 L: 2087 D: 6951 Ptnml(0-2): 2, 742, 4035, 821, 5 | 3.6.39: fix draw detection |
| Vshche | Igel | history-follow-decay-operand | diff | 10.0+0.10 | LLR: 1.05 (-2.94, 2.94) [-3.00, 1.00] Games: 29756 W: 7333 L: 7330 D: 15093 Ptnml(0-2): 181, 3552, 7419, 3535, 191 | 3.6.38: fix history overflow |
| Vshche | Igel | history-follow-decay-operand | diff | 60.0+0.60 | LLR: 3.06 (-2.94, 2.94) [-3.00, 1.00] Games: 18668 W: 4402 L: 4297 D: 9969 Ptnml(0-2): 38, 2099, 4947, 2220, 30 | 3.6.38: fix history overflow |
| Rosent | Winter | net347_d24f64 * | diff | N=40000 | Elo: 25.02 +- 7.56 (95%) [N=4000] Games: 4020 W: 1277 L: 988 D: 1755 Ptnml(0-2): 95, 414, 767, 575, 159 | Preliminary fixed node test with a potential larger net. |
| Vshche | Igel | singular-ttscore-mate-coherence | diff | 10.0+0.10 | LLR: -2.23 (-2.94, 2.94) [0.00, 2.00] Games: 134664 W: 33282 L: 33282 D: 68100 Ptnml(0-2): 842, 15893, 33860, 15897, 840 | 3.6.38: fix mate score for sext |
| Rosent | Winter | net347_W50 * | diff | 40.0+0.40 | LLR: 2.96 (-2.94, 2.94) [0.00, 5.00] Games: 4838 W: 986 L: 852 D: 3000 Ptnml(0-2): 44, 487, 1244, 579, 65 | Trained with more data. |
| Vshche | Igel | probcut-ttscore-mate-coherence-b | diff | 10.0+0.10 | LLR: 2.96 (-2.94, 2.94) [-3.00, 1.00] Games: 25730 W: 6470 L: 6371 D: 12889 Ptnml(0-2): 197, 2958, 6431, 3107, 172 | 3.6.37: fix mate score fo probcut - after rebase |
| Vshche | Igel | qsearch-tt-fifty-guard | diff | 10.0+0.10 | LLR: 3.05 (-2.94, 2.94) [-3.00, 1.00] Games: 72032 W: 13107 L: 13086 D: 45839 Ptnml(0-2): 23, 4686, 26579, 4703, 25 | 3.6.36: use fifty move guard on tt in qsearch |
| Vshche | Igel | probcut-ttscore-mate-coherence | diff | 10.0+0.10 | LLR: -0.17 (-2.94, 2.94) [-3.00, 1.00] Games: 55286 W: 13556 L: 13649 D: 28081 Ptnml(0-2): 349, 6538, 13951, 6467, 338 | 3.6.36: fix mate score fo probcut |
| Rosent | Winter | net347_W50 * | diff | 8.0+0.08 | LLR: 3.03 (-2.94, 2.94) [0.00, 5.00] Games: 2440 W: 644 L: 499 D: 1297 Ptnml(0-2): 38, 241, 541, 338, 62 | Trained with more data. |
| Vshche | Igel | qsearch-killer-scope | diff | 10.0+0.10 | LLR: -2.97 (-2.94, 2.94) [0.00, 2.00] Games: 230498 W: 57178 L: 57097 D: 116223 Ptnml(0-2): 1583, 28174, 55668, 28227, 1597 | 3.6.36: clear killer moves before qsearch |
| Vshche | Igel | qss | diff | 10.0+0.10 | LLR: -2.97 (-2.94, 2.94) [0.00, 2.00] Games: 164828 W: 40756 L: 40779 D: 83293 Ptnml(0-2): 1116, 19867, 40428, 19930, 1073 | 3.6.36: store piece stack for qsearch |
| Vshche | Igel | singular-killer-preserve | diff | 10.0+0.10 | LLR: -2.99 (-2.94, 2.94) [0.00, 2.00] Games: 224430 W: 55806 L: 55737 D: 112887 Ptnml(0-2): 1534, 27455, 54234, 27392, 1600 | 3.6.36: preserve killer moves for singular search |
| Vshche | Igel | nullmove-killer-preserve | diff | 10.0+0.10 | LLR: -2.95 (-2.94, 2.94) [0.00, 2.00] Games: 104294 W: 25954 L: 26071 D: 52269 Ptnml(0-2): 769, 12771, 25150, 12722, 735 | 3.6.36: preserve killer moves in nmp |
| Vshche | Igel | nullmove-history-suppression | diff | 10.0+0.10 | LLR: -3.02 (-2.94, 2.94) [0.00, 2.00] Games: 118416 W: 29426 L: 29527 D: 59463 Ptnml(0-2): 837, 14598, 28459, 14457, 857 | 3.6.36: supress history for null moves |
| Vshche | Igel | probcut_take2 | diff | 10.0+0.10 | LLR: -2.96 (-2.94, 2.94) [0.00, 2.00] Games: 88128 W: 21970 L: 22113 D: 44045 Ptnml(0-2): 657, 10751, 21331, 10728, 597 | 3.6.36: store piece stack for probcut |
| Vshche | Igel | singular-killer-suppression | diff | 60.0+0.60 | LLR: -0.45 (-2.94, 2.94) [0.00, 2.00] Games: 26070 W: 6092 L: 6094 D: 13884 Ptnml(0-2): 56, 3116, 6699, 3102, 62 | 3.6.36: skip killer moves for skipmoves |
| Vshche | Igel | singular-killer-suppression | diff | 10.0+0.10 | LLR: 2.98 (-2.94, 2.94) [0.00, 2.00] Games: 87476 W: 21987 L: 21564 D: 43925 Ptnml(0-2): 618, 10518, 21048, 10931, 623 | 3.6.36: skip killer moves for skipmoves |
| Kieren | Halogen | spsa_tune_21_50k | diff | 5.0+0.05 | LLR: 2.95 (-2.94, 2.94) [0.00, 3.00] Games: 23702 W: 6083 L: 5860 D: 11759 Ptnml(0-2): 58, 2638, 6236, 2861, 58 | |
| Kieren | Halogen | spsa_tune_21_50k | diff | 40.0+0.40 | LLR: 2.96 (-2.94, 2.94) [0.00, 3.00] Games: 18562 W: 4662 L: 4454 D: 9446 Ptnml(0-2): 27, 2034, 4945, 2254, 21 | |
| Rosent | Winter | master * | diff | 40.0+0.40 | Elo: 26.89 +- 6.25 (95%) [N=4000] Games: 4000 W: 1002 L: 693 D: 2305 Ptnml(0-2): 33, 354, 963, 571, 79 | Regression Test vs v5.0 |
| Vshche | Igel | singular-killer-preserve | diff | 60.0+0.60 | LLR: 0.00 (-2.94, 2.94) [0.00, 2.00] Games: 0 W: 0 L: 0 D: 0 Ptnml(0-2): 0, 0, 0, 0, 0 | 3.6.36: preserve killer moves for singular search |