FuryBench Testing Framework

home toIntegralPlentyChessObsidianCaissaQuanticadeSerendipitySpaghetSchoenemannClarityIlluminaPawnocchioVineAnura
No logs for event exist
Active : 17 Machines / 635 Threads / 398.21 MNPS
Priority 0
Caissa Witek
tm-cross-thread-instability
TimeManager: Cross-thread best move instability Each search thread counts how often its own root move changes between iterations. The main thread sums those counters, normalizes by thread count and folds the result into the soft time limit as one more multiplicative factor, so time allocation sees the helper threads disagreeing instead of only the main thread's own stability streak.
smp diff5.0+0.05
ELO    2.85 +- 17.08 (95%)
LLR    0.04 (-2.94, 2.94) [0.00, 3.00]
GAMES  N: 366 W: 82 L: 79 D: 205
PENTA  [0, 40, 100, 43, 0]
Integral Fury
spsa
please ascend me!
smp diff20.0+0.20
TUNE   106 parameters
ITER   4,941 / 20,000
GAMES  19,766 / 80,000
Quanticade DarkNeutrino
master
25K node datagen.
diffN=25000
ELO    -0.07 +- 0.39 (95%)
GAMES  N: 2138634/30000000 W: 750211 L: 750623 D: 637800
Caissa Witek
pv-pruning-margins
Search: PV-node margins for history, futility and SEE pruning
diff10.0+0.10
ELO    -0.62 +- 8.80 (95%)
LLR    -0.06 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 1678 W: 381 L: 384 D: 913
PENTA  [9, 206, 406, 215, 3]
Caissa Witek
qs-node-delta-prune
QSearch: Node-level delta pruning Bail out of a quiescence node before move generation when even winning the most valuable piece on the board (plus a queen promotion when a pawn stands on the relative 7th) cannot reach alpha.
diff10.0+0.10
ELO    -3.26 +- 3.46 (95%)
LLR    -1.21 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 9712 W: 2241 L: 2332 D: 5139
PENTA  [24, 1169, 2561, 1078, 24]
Priority -1
Caissa Witek
rfp-qsearch-verify
diff10.0+0.10
ELO    0.16 +- 1.01 (95%)
LLR    -1.38 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 120220 W: 28278 L: 28223 D: 63719
PENTA  [365, 14410, 30510, 14455, 370]
Caissa Witek
singular-beta-history
diff10.0+0.10
ELO    -0.07 +- 1.21 (95%)
LLR    -1.58 (-2.94, 2.94) [0.00, 2.00]
GAMES  N: 83510 W: 19673 L: 19691 D: 44146
PENTA  [257, 10045, 21177, 10011, 265]
Priority -2
Illumina Mergener
neg-extensions
Negative extensions
diff40.0+0.40
ELO    -0.75 +- 11.07 (95%)
LLR    -0.15 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 932 W: 182 L: 184 D: 566
PENTA  [3, 104, 253, 104, 2]
Illumina Mergener
neg-extensions
Negative extensions
diff8.0+0.08
ELO    -7.47 +- 9.30 (95%)
LLR    -1.04 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 1536 W: 320 L: 353 D: 863
PENTA  [7, 205, 380, 166, 10]
Illumina Mergener
fix-non-pawn-corrhist
Fix non pawn corrhist
diff8.0+0.08
ELO    -3.95 +- 5.40 (95%)
LLR    -1.51 (-2.25, 2.89) [0.00, 5.00]
GAMES  N: 3254 W: 683 L: 720 D: 1851
PENTA  [7, 321, 1010, 280, 9]
Finished
Integral Fury
spsa_4500
diff10.0+0.10
ELO    -2.28 +- 3.56 (95%)
LLR    -1.41 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 9440 W: 2249 L: 2311 D: 4880
PENTA  [27, 1140, 2450, 1074, 29]
Quanticade DarkNeutrino
D4D2F8C3BDC4446D
2 speedups both doing the same thing tho
diff4.0+0.04
ELO    2.56 +- 2.67 (95%)
LLR    1.50 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 17914 W: 4417 L: 4285 D: 9212
PENTA  [101, 1990, 4655, 2098, 113]
Quanticade DarkNeutrino
ttpv-reduction
search.c: Reduce more for tt_pv ahead of pruning
diff60.0+0.60
ELO    -0.70 +- 3.99 (95%)
LLR    -0.48 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 6426 W: 1490 L: 1503 D: 3433
PENTA  [1, 710, 1803, 699, 0]
Quanticade DarkNeutrino
lmr-cutnode-ttmove
search.c: Reduce more if this node is cutnode and we dont have TT move
diff10.0+0.10
ELO    -2.64 +- 2.91 (95%)
LLR    -2.26 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 13306 W: 3064 L: 3165 D: 7077
PENTA  [20, 1592, 3529, 1493, 19]
Quanticade DarkNeutrino
multicut-corr
plenty stuff (search is depressing man)
diff10.0+0.10
ELO    0.18 +- 1.20 (95%)
LLR    -2.27 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 79832 W: 19016 L: 18975 D: 41841
PENTA  [123, 9357, 20951, 9326, 159]
Quanticade DarkNeutrino
tune
Tuned 4700 iters
smp diff20.0+0.20
ELO    1.07 +- 2.69 (95%)
LLR    0.28 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 13630 W: 3211 L: 3169 D: 7250
PENTA  [0, 1424, 3928, 1460, 3]
Quanticade DarkNeutrino
master
Source: Add and make use of removing lowest bit (#430)
diff60.0+0.60
ELO    90.78 +- 7.70 (95%)
GAMES  N: 1816/10000 W: 698 L: 234 D: 884
PENTA  [0, 50, 362, 478, 18]
Illumina Mergener
null-move-prefetch
Prefetching TT entries on NMP
diff8.0+0.08
ELO    2.06 +- 1.53 (95%)
LLR    2.92 (-2.25, 2.89) [0.00, 2.50]
GAMES  N: 48142 W: 10686 L: 10400 D: 27056
PENTA  [226, 4818, 13702, 5094, 231]
Quanticade DarkNeutrino
simp-cutnode-lmr-ext
search.c: Simplify LMR extensions for cutnode
diff10.0+0.10
ELO    2.05 +- 2.58 (95%)
LLR    2.94 (-2.94, 2.94) [-3.00, 1.00]
GAMES  N: 17444 W: 4162 L: 4059 D: 9223
PENTA  [30, 2007, 4557, 2086, 42]
Illumina Mergener
triangular-pv
diff8.0+0.08
ELO    1.60 +- 2.07 (95%)
LLR    2.90 (-2.25, 2.89) [-3.00, 0.00]
GAMES  N: 23682 W: 5253 L: 5144 D: 13285
PENTA  [97, 2137, 7272, 2230, 105]
Quanticade Anematode
reduce-copies
goose
diff4.0+0.04
ELO    3.06 +- 2.17 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 26460 W: 6657 L: 6424 D: 13379
PENTA  [118, 2939, 6905, 3128, 140]
Illumina Mergener
no-eg-module
Remove endgame module
diff8.0+0.08
ELO    0.76 +- 1.67 (95%)
LLR    2.99 (-2.25, 2.89) [-3.00, 0.00]
GAMES  N: 39156 W: 8534 L: 8448 D: 22174
PENTA  [153, 3941, 11322, 3991, 171]
Illumina Mergener
history-aging
Refactor history
diff8.0+0.08
ELO    3.27 +- 2.31 (95%)
LLR    2.90 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 25926 W: 5883 L: 5639 D: 14404
PENTA  [169, 3046, 6296, 3276, 176]
Quanticade DarkNeutrino
net58
net58 1024l1 otherwise same as net59 (yes weird to have earlier net)
diffN=25000
ELO    10.06 +- 4.65 (95%)
LLR    3.03 (-2.25, 2.89) [0.00, 3.00]
GAMES  N: 8356 W: 2484 L: 2242 D: 3630
PENTA  [128, 956, 1812, 1110, 172]
Caissa Witek
singular-exact-margin
diff60.0+0.60
ELO    0.85 +- 1.47 (95%)
LLR    0.94 (-2.94, 2.94) [-0.50, 2.50]
GAMES  N: 50790 W: 11600 L: 11476 D: 27714
PENTA  [39, 5818, 13547, 5962, 29]