Dev Builds » 20220911-1219

You are viewing an old NCM Stockfish dev build test. You may find the most recent dev build tests using Stockfish 15 as the baseline here.

Use this dev build

NCM plays each Stockfish dev build 20,000 times against Stockfish 7. This yields an approximate Elo difference and establishes confidence in the strength of the dev builds.

Summary

Host Duration Avg Base NPS Games Wins Losses Draws Elo
ncm-et-3 13:03:38 1959364 3859 3379 8 472 +468.29 ± 15.7
ncm-et-4 13:02:05 1032849 677 583 19 75 +416.28 ± 38.26
ncm-et-9 13:03:36 1962335 3872 3301 9 562 +436.69 ± 14.37
ncm-et-10 13:03:30 1955719 3859 3332 6 521 +451.88 ± 14.93
ncm-et-13 13:03:33 1958640 3875 3348 11 516 +450.91 ± 15.01
ncm-et-15 13:03:34 1959989 3858 3298 8 552 +439.93 ± 14.5
20000 17241 61 2698 +448.02 ± 6.55

Test Detail

ID Host Started (UTC) Duration Base NPS Games Wins Losses Draws Elo CLI PGN
160420 ncm-et-15 2022-09-13 21:52 01:11:50 1966460 358 314 1 43 +469.4 ± 53.25
160419 ncm-et-10 2022-09-13 21:51 01:12:53 1951923 359 315 0 44 +474.07 ± 52.51
160418 ncm-et-3 2022-09-13 21:51 01:13:00 1960156 359 322 0 37 +505.97 ± 57.64
160417 ncm-et-9 2022-09-13 21:49 01:14:39 1960315 372 301 1 70 +388.01 ± 41.14
160416 ncm-et-13 2022-09-13 21:46 01:17:11 1948732 375 329 0 46 +473.92 ± 51.3
160415 ncm-et-3 2022-09-13 20:10 01:40:16 1960001 500 436 2 62 +460.32 ± 43.99
160414 ncm-et-9 2022-09-13 20:09 01:39:52 1968157 500 417 1 82 +415.05 ± 37.98
160413 ncm-et-15 2022-09-13 20:08 01:43:26 1956024 500 421 0 79 +426.65 ± 38.66
160412 ncm-et-10 2022-09-13 20:08 01:42:27 1956788 500 446 0 54 +497.39 ± 47.22
160411 ncm-et-13 2022-09-13 20:02 01:43:40 1948574 500 429 2 69 +441.5 ± 41.61
160410 ncm-et-3 2022-09-13 18:28 01:40:50 1959428 500 446 0 54 +497.39 ± 47.22
160409 ncm-et-9 2022-09-13 18:27 01:41:11 1966618 500 429 3 68 +438.95 ± 41.92
160408 ncm-et-10 2022-09-13 18:25 01:42:14 1948737 500 436 1 63 +463.16 ± 43.6
160407 ncm-et-15 2022-09-13 18:24 01:42:47 1951543 500 439 2 59 +468.96 ± 45.15
160406 ncm-et-13 2022-09-13 18:23 01:38:58 1962630 500 437 3 60 +460.32 ± 44.73
160405 ncm-et-3 2022-09-13 16:47 01:40:15 1961385 500 443 0 57 +487.45 ± 45.89
160404 ncm-et-9 2022-09-13 16:45 01:41:18 1959265 500 426 0 74 +438.95 ± 40.01
160403 ncm-et-10 2022-09-13 16:45 01:39:29 1963391 500 434 0 66 +460.32 ± 42.48
160402 ncm-et-15 2022-09-13 16:42 01:42:06 1959541 500 419 1 80 +419.61 ± 38.47
160401 ncm-et-13 2022-09-13 16:41 01:40:37 1961103 500 423 0 77 +431.48 ± 39.18
160400 ncm-et-9 2022-09-13 15:04 01:40:18 1965226 500 435 0 65 +463.15 ± 42.83
160399 ncm-et-3 2022-09-13 15:04 01:43:11 1949836 500 429 1 70 +444.09 ± 41.26
160398 ncm-et-10 2022-09-13 15:02 01:42:05 1949637 500 417 2 81 +412.8 ± 38.27
160397 ncm-et-15 2022-09-13 15:02 01:39:10 1965706 500 430 1 69 +446.7 ± 41.57
160396 ncm-et-13 2022-09-13 15:00 01:40:13 1962161 500 431 1 68 +449.35 ± 41.89
160395 ncm-et-3 2022-09-13 13:21 01:42:25 1957558 500 445 1 54 +490.71 ± 47.28
160394 ncm-et-9 2022-09-13 13:20 01:42:52 1958165 500 428 2 70 +438.95 ± 41.29
160393 ncm-et-10 2022-09-13 13:20 01:41:14 1962613 500 434 0 66 +460.32 ± 42.48
160392 ncm-et-13 2022-09-13 13:19 01:40:45 1965534 500 441 1 58 +477.99 ± 45.54
160391 ncm-et-15 2022-09-13 13:18 01:42:50 1956025 500 430 1 69 +446.7 ± 41.57
160390 ncm-et-4 2022-09-13 11:46 11:19:22 103241 177 152 1 24 +440.36 ± 72.72
160389 ncm-et-13 2022-09-13 11:38 01:40:15 1966179 500 425 3 72 +429.05 ± 40.7
160388 ncm-et-9 2022-09-13 11:38 01:41:49 1959850 500 443 1 56 +484.25 ± 46.39
160387 ncm-et-10 2022-09-13 11:37 01:42:16 1956335 500 423 2 75 +426.65 ± 39.83
160386 ncm-et-15 2022-09-13 11:37 01:40:37 1960769 500 425 0 75 +436.43 ± 39.73
160385 ncm-et-3 2022-09-13 11:37 01:42:57 1950166 500 427 0 73 +441.5 ± 40.29
160384 ncm-et-10 2022-09-13 09:56 01:40:52 1956330 500 427 1 72 +438.95 ± 40.66
160383 ncm-et-9 2022-09-13 09:56 01:41:37 1961089 500 422 1 77 +426.65 ± 39.25
160382 ncm-et-4 2022-09-13 09:56 01:42:43 1962457 500 431 18 51 +408.38 ± 45.29
160381 ncm-et-15 2022-09-13 09:56 01:40:48 1963849 500 420 2 78 +419.61 ± 39.03
160380 ncm-et-13 2022-09-13 09:56 01:41:54 1954212 500 433 1 66 +454.76 ± 42.55
160379 ncm-et-3 2022-09-13 09:56 01:40:44 1976385 500 431 4 65 +441.5 ± 42.88

Commit

Commit ID 82bb21dc7a198609589ef0cc78d185f00f619a90
Author mstembera
Date 2022-09-11 12:19:57 UTC
Optimize AVX2 path in NNUE evaluation always selecting AffineTransform specialization for small inputs. A related patch was tested as Initially tested as a simplification STC https://tests.stockfishchess.org/tests/view/6317c3f437f41b13973d6dff LLR: 2.95 (-2.94,2.94) <-1.75,0.25> Total: 58072 W: 15619 L: 15425 D: 27028 Ptnml(0-2): 241, 6191, 15992, 6357, 255 Elo gain speedup test STC https://tests.stockfishchess.org/tests/view/63181c1b37f41b13973d79dc LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 184496 W: 49922 L: 49401 D: 85173 Ptnml(0-2): 851, 19397, 51208, 19964, 828 and this patch gained in testing speedup = +0.0071 P(speedup > 0) = 1.0000 on CPU: 16 x AMD Ryzen 9 3950X closes https://github.com/official-stockfish/Stockfish/pull/4158 No functional change
Copyright 2011–2024 Next Chess Move LLC