Dev Builds » 20251117-1224

Use this dev build

NCM plays each Stockfish dev build 20,000 times against Stockfish 15. This yields an approximate Elo difference and establishes confidence in the strength of the dev builds.

Summary

Host Duration Avg Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo
ncm-dbt-01 06:45:36 580541 4000 1695 409 1896 +115.81 ± 4.7 1 42 659 1266 32 +256.16 ± 13.23
ncm-dbt-02 06:46:03 586527 4000 1713 435 1852 +115.03 ± 4.6 0 46 648 1288 18 +257.59 ± 13.35
ncm-dbt-03 06:44:35 585461 4000 1703 417 1880 +115.81 ± 4.6 1 36 664 1274 25 +258.17 ± 13.16
ncm-dbt-04 06:44:45 566837 4000 1705 398 1897 +117.85 ± 4.6 1 35 647 1290 27 +263.71 ± 13.34
ncm-dbt-05 06:45:22 583869 4000 1694 413 1893 +115.32 ± 4.62 0 43 656 1278 23 +257.02 ± 13.26
20000 8510 2072 9418 +115.96 ± 2.07 3 202 3274 6396 125 +258.52 ± 5.93

Test Detail

ID Host Base NPS Games WLD Standard Elo Ptnml(0-2) Gamepair Elo CLI PGN
441562 ncm-dbt-01 580696 500 196 44 260 +109.07 ± 12.53 0 4 91 154 1 +243.0 ± 35.57
441561 ncm-dbt-04 566138 500 210 45 245 +119.11 ± 12.99 0 3 84 158 5 +263.42 ± 37.11
441560 ncm-dbt-05 584495 500 206 57 237 +106.77 ± 13.56 0 9 85 154 2 +234.38 ± 37.19
441559 ncm-dbt-02 584874 500 204 58 238 +104.49 ± 13.05 0 6 94 148 2 +228.08 ± 35.08
441558 ncm-dbt-03 582903 500 213 60 227 +109.83 ± 13.4 0 6 89 151 4 +238.66 ± 36.16
441557 ncm-dbt-04 564997 500 207 44 249 +117.55 ± 12.46 0 2 86 159 3 +263.42 ± 36.51
441556 ncm-dbt-01 580945 500 214 48 238 +119.89 ± 13.51 0 7 74 165 4 +268.17 ± 39.97
441555 ncm-dbt-03 585169 500 219 52 229 +120.67 ± 12.97 0 3 82 160 5 +268.17 ± 37.61
441554 ncm-dbt-05 585843 500 216 34 250 +132.54 ± 12.71 0 4 64 178 4 +309.64 ± 43.08
441553 ncm-dbt-02 585674 500 216 56 228 +115.22 ± 13.2 0 4 87 154 5 +251.89 ± 36.48
441552 ncm-dbt-04 565508 500 222 52 226 +123.02 ± 12.17 0 2 78 168 2 +282.94 ± 38.55
441551 ncm-dbt-03 587494 500 209 48 243 +116.0 ± 13.02 1 3 82 162 2 +263.42 ± 37.69
441550 ncm-dbt-01 581070 500 201 57 242 +102.97 ± 14.18 0 10 91 144 5 +217.85 ± 35.89
441549 ncm-dbt-02 585337 500 217 53 230 +118.33 ± 14.2 0 12 65 170 3 +265.78 ± 42.44
441548 ncm-dbt-05 581402 500 211 47 242 +118.33 ± 13.0 0 4 82 160 4 +263.42 ± 37.69
441547 ncm-dbt-04 565508 500 206 46 248 +115.22 ± 12.3 0 3 85 161 1 +261.07 ± 36.86
441546 ncm-dbt-03 584411 500 215 48 237 +120.67 ± 12.78 0 5 75 168 2 +275.45 ± 39.63
441545 ncm-dbt-01 582694 500 226 55 219 +123.81 ± 12.92 0 3 78 164 5 +277.93 ± 38.66
441544 ncm-dbt-02 588728 500 214 51 235 +117.55 ± 13.18 0 6 78 163 3 +263.42 ± 38.85
441543 ncm-dbt-05 578177 500 213 61 226 +109.07 ± 12.53 0 4 91 154 1 +243.0 ± 35.57
441542 ncm-dbt-04 568554 500 211 52 237 +114.45 ± 12.49 0 5 81 164 0 +261.07 ± 38.02
441541 ncm-dbt-01 583154 500 206 49 245 +112.91 ± 13.72 1 6 81 159 3 +251.89 ± 38.11
441540 ncm-dbt-02 586012 500 225 54 221 +123.81 ± 12.16 0 2 77 169 2 +285.49 ± 38.83
441539 ncm-dbt-03 585801 500 205 35 260 +123.02 ± 13.11 0 7 68 173 2 +282.94 ± 41.76
441538 ncm-dbt-05 577971 500 214 57 229 +112.91 ± 13.04 0 5 86 156 3 +249.64 ± 36.79
441537 ncm-dbt-04 568236 500 216 54 230 +116.77 ± 13.54 0 7 78 161 4 +258.75 ± 38.88
441536 ncm-dbt-01 579785 500 223 57 220 +119.89 ± 12.42 0 1 86 159 4 +268.17 ± 36.37
441535 ncm-dbt-05 586816 500 207 53 240 +110.6 ± 12.7 0 4 90 154 2 +245.2 ± 35.79
441534 ncm-dbt-03 586435 500 205 58 237 +105.25 ± 12.17 0 2 100 147 1 +232.26 ± 33.47
441533 ncm-dbt-02 586393 500 206 52 242 +110.6 ± 12.7 0 4 90 154 2 +245.2 ± 35.79
441532 ncm-dbt-04 567047 500 220 44 236 +127.76 ± 12.65 0 3 72 171 4 +293.29 ± 40.39
441531 ncm-dbt-01 578712 500 218 50 232 +121.45 ± 13.49 0 6 75 164 5 +270.57 ± 39.67
441530 ncm-dbt-03 585717 500 216 57 227 +114.45 ± 13.21 0 6 82 159 3 +254.16 ± 37.82
441529 ncm-dbt-05 578959 500 212 53 235 +114.45 ± 13.38 0 6 83 157 4 +251.89 ± 37.57
441528 ncm-dbt-02 587792 500 225 57 218 +121.45 ± 12.58 0 5 73 171 1 +280.42 ± 40.21
441527 ncm-dbt-04 568713 500 213 61 226 +109.07 ± 15.14 1 10 83 148 8 +230.16 ± 37.67
441526 ncm-dbt-01 577274 500 211 49 240 +116.77 ± 13.36 0 5 83 157 5 +256.44 ± 37.51
441525 ncm-dbt-03 585759 500 221 59 220 +116.77 ± 13.36 0 4 86 154 6 +254.16 ± 36.71
441524 ncm-dbt-05 597292 500 215 51 234 +118.33 ± 13.35 0 7 75 165 3 +265.78 ± 39.69
441523 ncm-dbt-02 587409 500 206 54 240 +109.07 ± 12.88 0 7 84 159 0 +245.2 ± 37.37

Commit

Commit ID b083049fe0c3671d20d195aa8dea72687cd6e44c
Author Timothy Herchen
Date 2025-11-17 12:24:32 UTC
Use non-locking operations for nodes count and tbHits fetch_add and friends must produce a locking instruction because they guarantee consistency in the presence of multiple writers. Because only one thread ever writes to nodes and tbHits, we may use relaxed load and store to emit regular loads and stores (on both x86-64 and arm64), while avoiding undefined behavior and miscounting nodes. Credit must go to Arseniy Surkov of Reckless (codedeliveryservice) for uncovering this performance gotcha. failed yellow as a gainer on fishtest: LLR: -2.95 (-2.94,2.94) <0.00,2.00> Total: 219616 W: 57165 L: 57105 D: 105346 Ptnml(0-2): 732, 24277, 59720, 24357, 722 https://tests.stockfishchess.org/tests/view/69086abfea4b268f1fac2809 potential small speedup on large core system: ``` ==== master ==== 1 Nodes/second : 294269736 2 Nodes/second : 295217629 Average (over 2): 294743682 ==== patch ==== 1 Nodes/second : 299003603 2 Nodes/second : 298111320 Average (over 2): 298557461 ``` closes https://github.com/official-stockfish/Stockfish/pull/6392 No functional change
Copyright 2011–2025 Next Chess Move LLC