3322349c1a
Simplify pieceValue to one phase.
...
Simplifies the usage of pieceValues to mg values with the exception of pawnValues, After the removal of PSQT.
passed STC:
https://tests.stockfishchess.org/tests/view/64d147845b17f7c21c0dd86c
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 197248 W: 50168 L: 50125 D: 96955
Ptnml(0-2): 651, 23029, 51222, 23070, 652
passed LTC:
https://tests.stockfishchess.org/tests/view/64d212de5b17f7c21c0debbb
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 181170 W: 45949 L: 45893 D: 89328
Ptnml(0-2): 84, 19656, 51052, 19706, 87
closes https://github.com/official-stockfish/Stockfish/pull/4734
Bench: 1494401
2023-08-13 11:58:08 +02:00
495852fecd
Simplify SEE pruning for captures
...
It seems that the current search is smart enough to allow us to remove
(again) the block of code that checks for discovered attacks after the
first pruning condition for captures.
STC:
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 278848 W: 70856 L: 70903 D: 137089
Ptnml(0-2): 960, 32829, 71894, 32780, 961
https://tests.stockfishchess.org/tests/view/64d0af095b17f7c21c0dc440
LTC:
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 100704 W: 25564 L: 25425 D: 49715
Ptnml(0-2): 56, 10858, 28381, 11005, 52
https://tests.stockfishchess.org/tests/view/64d293e85b17f7c21c0df844
closes https://github.com/official-stockfish/Stockfish/pull/4736
Bench: 1470572
2023-08-13 11:52:47 +02:00
c02ee70927
Simplify prior countermove bonus
...
Swapping a multiplication operation between two terms with a simple constant
Passed STC:
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 60512 W: 15424 L: 15231 D: 29857
Ptnml(0-2): 200, 6985, 15712, 7140, 219
https://tests.stockfishchess.org/tests/view/64d2addf5b17f7c21c0dfae6
Passed LTC:
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 108456 W: 27545 L: 27414 D: 53497
Ptnml(0-2): 63, 11629, 30698, 11790, 48
https://tests.stockfishchess.org/tests/view/64d3ab6e5b17f7c21c0e1188
closes https://github.com/official-stockfish/Stockfish/pull/4738
Bench: 1636213
2023-08-13 11:48:32 +02:00
84e97a38a3
Remove the unused enum ScaleFactor
...
closes https://github.com/official-stockfish/Stockfish/pull/4740
No functional change
2023-08-13 11:46:48 +02:00
b7b7a3f3fa
Detect repetitions before they happen in qsearch
...
Passed STC:
https://tests.stockfishchess.org/tests/view/64d495995b17f7c21c0e29ed
LLR: 2.95 (-2.94,2.94) <0.00,2.00>
Total: 340288 W: 86664 L: 85910 D: 167714
Ptnml(0-2): 1030, 38855, 89697, 39455, 1107
Passed LTC:
https://tests.stockfishchess.org/tests/view/64d5e1085b17f7c21c0e4ab5
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 193230 W: 49235 L: 48606 D: 95389
Ptnml(0-2): 98, 20432, 54921, 21071, 93
closes https://github.com/official-stockfish/Stockfish/pull/4742
Bench: 1579576
2023-08-13 11:44:17 +02:00
222f3ea55b
Simplify a depth condition
...
As the negative extension term has sensitive scaling, it would make more sense to allow more negative extension also at lower depth, and not just a region between low and high depth.
Passed STC:
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 124096 W: 31611 L: 31485 D: 61000
Ptnml(0-2): 422, 14437, 32205, 14561, 423
https://tests.stockfishchess.org/tests/view/64d205d75b17f7c21c0dea82
Passed LTC:
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 387882 W: 97840 L: 97993 D: 192049
Ptnml(0-2): 198, 42004, 109668, 41895, 176
https://tests.stockfishchess.org/tests/view/64d333f85b17f7c21c0e06c6
closes https://github.com/official-stockfish/Stockfish/pull/4743
Bench: 1542357
2023-08-13 11:40:35 +02:00
d97a02ea2b
Give extra bonus to main history for moves that caused a fail low. #4744
...
Current master gives this type of bonuses to continuation history, this patch also gives them to main history.
Passed STC:
https://tests.stockfishchess.org/tests/view/64d4802a5b17f7c21c0e27b3
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 480768 W: 122767 L: 121798 D: 236203
Ptnml(0-2): 1563, 56190, 123834, 57309, 1488
Passed LTC:
https://tests.stockfishchess.org/tests/view/64d7e4c05b17f7c21c0e7456
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 32052 W: 8329 L: 8022 D: 15701
Ptnml(0-2): 19, 3335, 9015, 3634, 23
closes https://github.com/official-stockfish/Stockfish/pull/4744
Bench: 1711793
2023-08-13 11:38:24 +02:00
8192945870
Improve testing coverage, remove unused code
...
a) Add further tests to CI to cover most features. This uncovered a potential race
in case setoption was sent between two searches. As the UCI protocol requires
this sent to be went the engine is not searching, setoption now ensures that
this is the case.
b) Remove some unused code
closes https://github.com/official-stockfish/Stockfish/pull/4730
No functional change
2023-08-11 19:27:46 +02:00
0d2ddb81ef
Fix Makefile for incorrect nnue file
...
If an incorrect network file is present at the start of the compilation stage, the
Makefile script now correctly removes it before trying to download a clean version.
closes https://github.com/official-stockfish/Stockfish/pull/4726
No functional change
2023-08-11 19:20:29 +02:00
e64b817e0a
Remove all references to Score type
...
Score is obsolete with the removal of psqt.
No functional change.
Signed-off-by: Cody Ho <codyho@stanford.edu >
closes https://github.com/official-stockfish/Stockfish/pull/4724
2023-08-09 18:27:16 +02:00
5c2111cc30
Adjust futility pruning base in qsearch
...
Current master used value from transposition table there if it existed,
this patch uses minimum between this tt value and the static eval instead
(this thus is closer to the main search function, which uses the static eval).
Passed STC:
https://tests.stockfishchess.org/tests/view/64cd57285b17f7c21c0d6a8c
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 252544 W: 64671 L: 64039 D: 123834
Ptnml(0-2): 839, 29207, 65575, 29785, 866
Passed LTC:
https://tests.stockfishchess.org/tests/view/64cf6c915b17f7c21c0d9fcb
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 60150 W: 15374 L: 15012 D: 29764
Ptnml(0-2): 24, 6321, 17024, 6681, 25
closes https://github.com/official-stockfish/Stockfish/pull/4725
Bench: 1573024
2023-08-07 07:24:11 +02:00
a26f8d37e1
Tweak formula for pruning moves losing material
...
Simplify the "Prune moves with negative SEE" formula,
by removing one multiplication and subtraction operation.
Passed STC:
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 214272 W: 54596 L: 54572 D: 105104
Ptnml(0-2): 741, 25160, 55320, 25164, 751
https://tests.stockfishchess.org/tests/view/64c430d1dc56e1650abbdbf6
Passed LTC:
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 238380 W: 60600 L: 60601 D: 117179
Ptnml(0-2): 132, 26069, 66791, 26064, 134
https://tests.stockfishchess.org/tests/view/64c81f155b17f7c21c0cee2b
closes https://github.com/official-stockfish/Stockfish/pull/4721
bench: 1655337
2023-08-06 22:25:58 +02:00
0ad9b51dea
Remove classical psqt
...
Based on vondele's deletepsqt branch:
https://github.com/vondele/Stockfish/commit/369f5b051
This huge simplification uses a weighted material differences instead of
the positional piece square tables (psqt) in the semi-classical complexity
calculation. Tuned weights using spsa at 45+0.45 with:
int pawnMult = 100;
int knightMult = 325;
int bishopMult = 350;
int rookMult = 500;
int queenMult = 900;
TUNE(SetRange(0, 200), pawnMult);
TUNE(SetRange(0, 650), knightMult);
TUNE(SetRange(0, 700), bishopMult);
TUNE(SetRange(200, 800), rookMult);
TUNE(SetRange(600, 1200), queenMult);
The values obtained via this tuning session were for a model where
the psqt replacement formula was always from the point of view of White,
even if the side to move was Black. We re-used the same values for an
implementation with a psqt replacement from the point of view of the side
to move, testing the result both on our standard book on positions with
a strong White bias, and an alternate book with positions with a strong
Black bias.
We note that with the patch the last use of the venerable "Score" type
disappears in Stockfish codebase (the Score type was used in classical
evaluation to get a tampered eval interpolating values smoothly from the
early midgame stage to the endgame stage). We leave it to another commit
to clean all occurrences of Score in the code and the comments.
-------
Passed non-regression LTC:
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 142542 W: 36264 L: 36168 D: 70110
Ptnml(0-2): 76, 15578, 39856, 15696, 65
https://tests.stockfishchess.org/tests/view/64c8cb495b17f7c21c0cf9f8
Passed non-regression LTC (with a book with Black bias):
https://tests.stockfishchess.org/tests/view/64c8f9295b17f7c21c0cfdaf
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 494814 W: 125565 L: 125827 D: 243422
Ptnml(0-2): 244, 53926, 139346, 53630, 261
------
closes https://github.com/official-stockfish/Stockfish/pull/4713
Bench: 1655985
2023-08-06 22:16:52 +02:00
a6d9a302b8
Implement AffineTransformSparseInput for armv8
...
Implements AffineTransformSparseInput layer for the NNUE evaluation
for the armv8 and armv8-dotprod architectures. We measured some nice
speed improvements via 10 runs of our benchmark:
armv8, Cortex-X1 : 18.5% speed-up
armv8, Cortex-A76 : 13.2% speed-up
armv8-dotprod, Cortex-X1 : 27.1% speed-up
armv8-dotprod, Cortex-A76 : 12.1% speed-up
armv8, Cortex-A72, Raspberry Pi 4 : 8.2% speed-up (thanks Torom!)
closes https://github.com/official-stockfish/Stockfish/pull/4719
No functional change
2023-08-06 21:22:37 +02:00
002a50457c
Identify NEON_DOTPROD in compiler_info()
...
closes https://github.com/official-stockfish/Stockfish/pull/4712
No functional change
2023-08-06 21:14:39 +02:00
65ece7d985
Malus during move ordering for putting pieces en prise
...
The original idea is the reverse of a previous patch [1] which added bonuses
in our move picker to moves escaping threats. In this patch, in addition to
bonuses for evading threats, we apply penalties to moves moving to threatened
squares.
Further tweaks of that basic idea resulted in this specific version which
further increases the penalty of moves moving to squares threatend depending
on the piece threatening it. So for example a queen moving to a square attacked
by a pawn would receive a larger penalty than a queen moving to square attacked
by a rook.
[1]: https://github.com/official-stockfish/Stockfish/commit/08e0f52b77edb929989c68c49e954b9bc5d7d67e
--------
Passed STC:
https://tests.stockfishchess.org/tests/live_elo/64c11269dc56e1650abb935d
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 95552 W: 24654 L: 24250 D: 46648
Ptnml(0-2): 322, 11098, 24562, 11442, 352
Passed LTC:
https://tests.stockfishchess.org/tests/live_elo/64c2004ddc56e1650abba8b3
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 190230 W: 48806 L: 48178 D: 93246
Ptnml(0-2): 90, 20439, 53453, 21019, 114
-------
closes https://github.com/official-stockfish/Stockfish/pull/4711
Bench: 1350831
2023-07-29 00:56:26 +02:00
f84eb1f3ef
Improve some comments
...
- clarify the examples for the bench command
- typo in search.cpp
closes https://github.com/official-stockfish/Stockfish/pull/4710
No functional change
2023-07-28 23:38:49 +02:00
cb22520a9c
Remove unused return type from propagate()
...
Also make two get_weight_index() static methods constexpr, for
consistency with the other static get_hash_value() method right above.
Tested for speed by user Torom (thanks).
closes https://github.com/official-stockfish/Stockfish/pull/4708
No functional change
2023-07-28 23:24:42 +02:00
2667316ffc
Simplify one multicut extension
...
Simplify away the ttValue <= alpha extension in the multicut block.
Passed STC:
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 318336 W: 81307 L: 81398 D: 155631
Ptnml(0-2): 1088, 37291, 82469, 37264, 1056
https://tests.stockfishchess.org/tests/view/64b8589fdc56e1650abad61d
Passed LTC:
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 89388 W: 22925 L: 22775 D: 43688
Ptnml(0-2): 34, 9635, 25210, 9777, 38
https://tests.stockfishchess.org/tests/view/64bc41d0dc56e1650abb29cb
closes https://github.com/official-stockfish/Stockfish/pull/4709
bench: 1604592
2023-07-25 16:43:35 +02:00
027713c4b4
Remove Zobrist::noPawns
...
Zobrist::noPawns is no longer used.
closes https://github.com/official-stockfish/Stockfish/pull/4344
no functional change
2023-07-25 00:13:38 +02:00
76e1e8fd39
Simplify TT cutoff
...
Remove the exact bound condition from TT depth check.
STC:
https://tests.stockfishchess.org/tests/view/64b30b320cdec37b957359e9
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 332928 W: 84895 L: 85003 D: 163030
Ptnml(0-2): 1242, 39200, 85604, 39260, 1158
LTC:
https://tests.stockfishchess.org/tests/view/64b74e2adc56e1650abac0b6
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 92946 W: 23628 L: 23482 D: 45836
Ptnml(0-2): 38, 10033, 26192, 10165, 45
closes https://github.com/official-stockfish/Stockfish/pull/4702
Bench: 1601764
2023-07-24 02:23:43 +02:00
78e3d2ad78
Simplify some qsearch conditions
...
Use the assert which ensures that beta == alpha+1 at PVNodes
to simplify a little bit the conditions further down in the code.
passed STC:
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 56160 W: 14370 L: 14173 D: 27617
Ptnml(0-2): 210, 6192, 15076, 6395, 207
https://tests.stockfishchess.org/tests/view/64bc769cdc56e1650abb2e26
closes https://tests.stockfishchess.org/tests/view/64bc769cdc56e1650abb2e26
No functional change
2023-07-24 02:09:44 +02:00
4b2979760f
Check clock more often
...
This patch changes the frequency with which the time is checked, changing
frequency from every 1024 counted nodes to every 512 counted nodes. The
master value was tuned for the old classical eval, the patch takes the
roughly 2x slowdown in nps with SFNNUEv7 into account. This could reduce
a bit the losses on time on fishtest, but they are probably unrelated.
passed STC:
https://tests.stockfishchess.org/tests/view/64bb8ae5dc56e1650abb1b11
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 76576 W: 19677 L: 19501 D: 37398
Ptnml(0-2): 274, 8592, 20396, 8736, 290
closes https://github.com/official-stockfish/Stockfish/pull/4704
No functional change
2023-07-24 01:56:20 +02:00
5ea1cbc778
Do more futility pruning for cutNodes that are not in TT
...
This is somewhat similar to IIR for cutnodes but instead of reducing
depth for cutnodes that don't have tt move we reduce margin multiplier
in futility pruning for cutnodes that are not in TT.
Passed STC:
https://tests.stockfishchess.org/tests/view/64b244b90cdec37b95734c5b
LLR: 2.95 (-2.94,2.94) <0.00,2.00>
Total: 75552 W: 19404 L: 19029 D: 37119
Ptnml(0-2): 233, 8806, 19378, 9071, 288
Passed LTC:
https://tests.stockfishchess.org/tests/view/64b3ae5a0cdec37b95736516
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 104988 W: 27152 L: 26697 D: 51139
Ptnml(0-2): 41, 11259, 29446, 11700, 48
closes https://github.com/official-stockfish/Stockfish/pull/4700
bench 1727577
2023-07-19 21:40:38 +02:00
1444837887
Remove inline assembly
...
closes https://github.com/official-stockfish/Stockfish/pull/4698
No functional change
2023-07-19 21:39:51 +02:00
3fe0d5c533
Unused code cleanup
...
closes https://github.com/official-stockfish/Stockfish/pull/4696
No functional change
2023-07-19 21:38:39 +02:00
42d28424bc
Removes a few Bitboards and functions
...
No longer used
closes https://github.com/official-stockfish/Stockfish/pull/4695
No functional change
2023-07-18 08:10:11 +02:00
6a31f54d3c
remove evalType from bench
...
no longer used
closes https://github.com/official-stockfish/Stockfish/pull/4694
No functional change
2023-07-18 08:09:52 +02:00
d70a905ce3
Deprecate the x86-64-modern arch
...
Explicitly describe the architecture as deprecated,
it remains available as its current alias x86-64-sse41-popcnt
CPUs that support just this instruction set are now years old,
any few years old Intel or AMD CPU supports x86-64-avx2. However,
naming things 'modern' doesn't age well, so instead use explicit names.
Adjust CI accordingly. Wiki, fishtest, downloader done as well.
closes https://github.com/official-stockfish/Stockfish/pull/4691
No functional change.
2023-07-16 17:47:25 +02:00
913574f421
Remove improvement variable
...
No longer used in a meaningful way.
Improve comments.
Closes https://github.com/official-stockfish/Stockfish/pull/4688
No functional change
2023-07-16 15:18:41 +02:00
18fdc2df3c
Remove pawnKey from StateInfo
...
Remove pawnKey since it is not used anymore.
Passed Non-regression STC:
https://tests.stockfishchess.org/tests/view/64b023110cdec37b9573265c
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 334848 W: 85440 L: 85545 D: 163863
Ptnml(0-2): 1134, 38101, 89075, 37964, 1150
closes https://github.com/official-stockfish/Stockfish/pull/4687
No functional change
2023-07-16 15:16:14 +02:00
e8a5c64988
Consolidate to centipawns conversion
...
avoid doing this calculations in multiple places.
closes https://github.com/official-stockfish/Stockfish/pull/4686
No functional change
2023-07-16 15:14:50 +02:00
a42ab95e1f
remove large input specialization
...
Removes unused large input specialization for dense affine transform. It has been obsolete since #4612 was merged.
closes https://github.com/official-stockfish/Stockfish/pull/4684
No functional change
2023-07-16 15:12:21 +02:00
ee53f8ed2f
Reintroduce nnue eval pawn count multipliers again
...
With separate multipliers for nnue eval and optimism scaling.
This patch used 4 out of 7 params tuned with spsa at 30+0.3
using this tuning config:
Value LazyThreshold1 = Value(3622);
Value LazyThreshold2 = Value(1962);
int psqThresh = 2048;
int nnueNpmBase = 945;
int nnuePcMult = 0;
int optNpmBase = 150;
int optPcMult = 0;
TUNE(SetRange(3322, 3922), LazyThreshold1);
TUNE(SetRange(1662, 2262), LazyThreshold2);
TUNE(SetRange(1748, 2348), psqThresh);
TUNE(SetRange(745, 1145), nnueNpmBase);
TUNE(SetRange(-16, 16), nnuePcMult);
TUNE(SetRange(0, 300), optNpmBase);
TUNE(SetRange(-16, 16), optPcMult);
Passed STC:
https://tests.stockfishchess.org/tests/view/64a5a9b402cd07745c60ed07
LLR: 2.95 (-2.94,2.94) <0.00,2.00>
Total: 173632 W: 44417 L: 43903 D: 85312
Ptnml(0-2): 547, 20025, 45068, 20719, 457
Passed LTC:
https://tests.stockfishchess.org/tests/view/64a972a302cd07745c6136af
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 277644 W: 70955 L: 70147 D: 136542
Ptnml(0-2): 193, 29902, 77787, 30784, 156
closes https://github.com/official-stockfish/Stockfish/pull/4681
bench 1556301
2023-07-15 09:16:09 +02:00
a3a91f3f9f
Build and test more binaries in CI
...
use a fixed compiler on Linux and Windows (right now gcc 11).
build avxvnni on Windows (Linux needs updated core utils)
build x86-32 on Linux (Windows needs other mingw)
fix a Makefile issue where a failed PGOBENCH would not stop the build
reuse the WINE_PATH for SDE as we do for QEMU
use WINE_PATH variable also for the signature
verify the bench for each of the binaries
do not build x86-64-avx2 on macos
closes https://github.com/official-stockfish/Stockfish/pull/4682
No functional change
2023-07-15 09:15:16 +02:00
acdbf45171
Use more expressive names for bonus1 and bonus2
...
closes https://github.com/official-stockfish/Stockfish/pull/4683
No functional change
2023-07-15 09:13:02 +02:00
529d3be8e2
More simplifications and cleanup in affine_transform_sparse_input.h
...
closes https://github.com/official-stockfish/Stockfish/pull/4677
No functional change
2023-07-13 08:20:33 +02:00
f972947492
Cleanup code after removal of classical evaluation
...
This includes the following changes:
- Remove declaration of removed global variable
- Adapt string that mentions removed UCI option
closes https://github.com/official-stockfish/Stockfish/pull/4675
No functional change
2023-07-13 08:19:37 +02:00
af110e02ec
Remove classical evaluation
...
since the introduction of NNUE (first released with Stockfish 12), we
have maintained the classical evaluation as part of SF in frozen form.
The idea that this code could lead to further inputs to the NN or
search did not materialize. Now, after five releases, this PR removes
the classical evaluation from SF. Even though this evaluation is
probably the best of its class, it has become unimportant for the
engine's strength, and there is little need to maintain this
code (roughly 25% of SF) going forward, or to expend resources on
trying to improve its integration in the NNUE eval.
Indeed, it had still a very limited use in the current SF, namely
for the evaluation of positions that are nearly decided based on
material difference, where the speed of the classical evaluation
outweights its inaccuracies. This impact on strength is small,
roughly 2Elo, and probably decreasing in importance as the TC grows.
Potentially, removal of this code could lead to the development of
techniques to have faster, but less accurate NN evaluation,
for certain positions.
STC
https://tests.stockfishchess.org/tests/view/64a320173ee09aa549c52157
Elo: -2.35 ± 1.1 (95%) LOS: 0.0%
Total: 100000 W: 24916 L: 25592 D: 49492
Ptnml(0-2): 287, 12123, 25841, 11477, 272
nElo: -4.62 ± 2.2 (95%) PairsRatio: 0.95
LTC
https://tests.stockfishchess.org/tests/view/64a320293ee09aa549c5215b
Elo: -1.74 ± 1.0 (95%) LOS: 0.0%
Total: 100000 W: 25010 L: 25512 D: 49478
Ptnml(0-2): 44, 11069, 28270, 10579, 38
nElo: -3.72 ± 2.2 (95%) PairsRatio: 0.96
VLTC SMP
https://tests.stockfishchess.org/tests/view/64a3207c3ee09aa549c52168
Elo: -1.70 ± 0.9 (95%) LOS: 0.0%
Total: 100000 W: 25673 L: 26162 D: 48165
Ptnml(0-2): 8, 9455, 31569, 8954, 14
nElo: -3.95 ± 2.2 (95%) PairsRatio: 0.95
closes https://github.com/official-stockfish/Stockfish/pull/4674
Bench: 1444646
2023-07-11 22:56:49 +02:00
6a8767a0d5
Simplify PvNode reduction
...
Simplification STC: https://tests.stockfishchess.org/tests/view/64a415803ee09aa549c539c3
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 37856 W: 9719 L: 9504 D: 18633
Ptnml(0-2): 98, 4277, 9977, 4464, 112
Simplification LTC: https://tests.stockfishchess.org/tests/view/64a5ffe202cd07745c60f360
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 55878 W: 14323 L: 14138 D: 27417
Ptnml(0-2): 21, 5993, 15732, 6166, 27
closes https://github.com/official-stockfish/Stockfish/pull/4673
Bench: 2604965
2023-07-11 22:55:00 +02:00
e699fee513
Update default net to nn-c38c3d8d3920.nnue
...
This was a later epoch from the same experiment that led to the
previous master net. After training, it was prepared the same way:
1. greedy permuting L1 weights with https://github.com/official-stockfish/Stockfish/pull/4620
2. leb128 compression with https://github.com/glinscott/nnue-pytorch/pull/251
3. greedy 2- and 3- cycle permuting with https://github.com/official-stockfish/Stockfish/pull/4640
Local elo at 25k nodes per move (vs. L1-1536 nn-fdc1d0fe6455.nnue):
nn-epoch739.nnue : 20.2 +/- 1.7
Passed STC:
https://tests.stockfishchess.org/tests/view/64a050b33ee09aa549c4e4c8
LLR: 2.95 (-2.94,2.94) <0.00,2.00>
Total: 195552 W: 49977 L: 49430 D: 96145
Ptnml(0-2): 556, 22775, 50607, 23242, 596
Passed LTC:
https://tests.stockfishchess.org/tests/view/64a127bd3ee09aa549c4f60c
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 235452 W: 60327 L: 59609 D: 115516
Ptnml(0-2): 119, 25173, 66426, 25887, 121
closes https://github.com/official-stockfish/Stockfish/pull/4666
bench 2427629
2023-07-06 23:03:58 +02:00
f8e65d82eb
Simplify away lookup_count.
...
https://tests.stockfishchess.org/tests/view/64a3c1a93ee09aa549c53167
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 32832 W: 8497 L: 8280 D: 16055
Ptnml(0-2): 80, 3544, 8967, 3729, 96
closes https://github.com/official-stockfish/Stockfish/pull/4662
No functional change
2023-07-06 23:02:11 +02:00
95ce443aaa
simplified gives check castling
...
tested verifying perft and bench is unchanged
on a larger set of epds for both standard and FRC chess.
Passed non-regression STC:
https://tests.stockfishchess.org/tests/live_elo/648587be65ffe077ca123d78
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 153632 W: 41015 L: 40928 D: 71689
Ptnml(0-2): 377, 16077, 43816, 16174, 372
closes https://github.com/official-stockfish/Stockfish/pull/4628
No functional change
2023-07-03 18:54:22 +02:00
9cd563cb54
Improving grammar and readability of comments
...
closes https://github.com/official-stockfish/Stockfish/pull/4643
No functional change
2023-07-03 18:38:41 +02:00
5f8480a730
Simplify score improvement reduction
...
Reduce depth by 2 based on score improvement, only for depths 3 to 11.
Simplification STC: https://tests.stockfishchess.org/tests/view/64929a53dc7002ce609c7807
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 238912 W: 63466 L: 63468 D: 111978
Ptnml(0-2): 564, 26262, 65805, 26262, 563
Simplification LTC: https://tests.stockfishchess.org/tests/view/64942e47dc7002ce609c9e07
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 64452 W: 17485 L: 17320 D: 29647
Ptnml(0-2): 19, 6161, 19706, 6316, 24
closes https://github.com/official-stockfish/Stockfish/pull/4637
Bench: 2740142
2023-07-03 18:33:27 +02:00
eb9aaf9489
Simplify away improvement term in null move search
...
passed STC:
https://tests.stockfishchess.org/tests/view/649c0d2edc7002ce609d33b5
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 271104 W: 72181 L: 72217 D: 126706
Ptnml(0-2): 691, 30042, 74129, 29992, 698
passed LTC:
https://tests.stockfishchess.org/tests/view/649d0dd7dc7002ce609d4efa
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 183120 W: 49469 L: 49418 D: 84233
Ptnml(0-2): 84, 17636, 56063, 17699, 78
closes https://github.com/official-stockfish/Stockfish/pull/4650
Bench: 2642851
2023-07-03 18:27:33 +02:00
fa143922ae
Fix pruning to (in TB loss) in Null move pruning.
...
Current logic can apply Null move pruning
on a dead-lost position returning an unproven loss
(i.e. in TB loss score or mated in losing score) on nonPv nodes.
on a default bench, this can be observed by adding this debugging line:
```
if (nullValue >= beta)
{
// Do not return unproven mate or TB scores
nullValue = std::min(nullValue, VALUE_TB_WIN_IN_MAX_PLY-1);
dbg_hit_on(nullValue <= VALUE_TB_LOSS_IN_MAX_PLY); // Hit #0 : Total 73983 Hits 1 Hit Rate (%) 0.00135166
if (thisThread->nmpMinPly || depth < 14)
return nullValue;
```
This fixes this very rare issue (happens at ~0.00135166% of the time) by
eliminating the need to try Null Move Pruning with dead-lost positions
and leaving it to be determined by a normal searching flow.
The previous try to fix was not as safe enough because it was capping
the returned value to (out of TB range) thus reviving the dead-lost position
based on an artificial clamp (i.e. the in TB score/mate score can be lost on that nonPv node):
https://tests.stockfishchess.org/tests/view/649756d5dc7002ce609cd794
Final fix:
Passed STC:
https://tests.stockfishchess.org/tests/view/649a5446dc7002ce609d1049
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 577280 W: 153613 L: 153965 D: 269702
Ptnml(0-2): 1320, 60594, 165190, 60190, 1346
Passed LTC:
https://tests.stockfishchess.org/tests/view/649cd048dc7002ce609d4801
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 246432 W: 66769 L: 66778 D: 112885
Ptnml(0-2): 83, 22105, 78847, 22100, 81
closes https://github.com/official-stockfish/Stockfish/pull/4649
Bench: 2425978
2023-07-03 18:24:41 +02:00
80564bcfcd
Simplify lookup_count and clean up pieces().
...
https://github.com/official-stockfish/Stockfish/pull/4656
No functional change
2023-07-03 18:20:10 +02:00
915532181f
Update NNUE architecture to SFNNv7 with larger L1 size of 2048
...
Creating this net involved:
- a 5-step training process from scratch
- greedy permuting L1 weights with https://github.com/official-stockfish/Stockfish/pull/4620
- leb128 compression with https://github.com/glinscott/nnue-pytorch/pull/251
- greedy 2- and 3- cycle permuting with https://github.com/official-stockfish/Stockfish/pull/4640
The 5 training steps were:
1. 400 epochs, lambda 1.0, lr 9.75e-4
UHOx2-wIsRight-multinet-dfrc-n5000-largeGensfen-d9.binpack (178G)
nodes5000pv2_UHO.binpack
data_pv-2_diff-100_nodes-5000.binpack
wrongIsRight_nodes5000pv2.binpack
multinet_pv-2_diff-100_nodes-5000.binpack
dfrc_n5000.binpack
large_gensfen_multipvdiff_100_d9.binpack
ep399 chosen as start model for step2
2. 800 epochs, end-lambda 0.75, skip 16
LeelaFarseer-T78juntoaugT79marT80dec.binpack (141G)
T60T70wIsRightFarseerT60T74T75T76.binpack
test78-junjulaug2022-16tb7p.no-db.min.binpack
test79-mar2022-16tb7p.no-db.min.binpack
test80-dec2022-16tb7p.no-db.min.binpack
ep559 chosen as start model for step3
3. 800 epochs, end-lambda 0.725, skip 20
leela96-dfrc99-v2-T80dectofeb-sk20-mar-v6-T77decT78janfebT79apr.binpack (223G)
leela96-filt-v2.min.binpack
dfrc99-16tb7p-eval-filt-v2.min.binpack
test80-dec2022-16tb7p-filter-v6-sk20.min-mar2023.binpack
test80-jan2023-16tb7p-filter-v6-sk20.min-mar2023.binpack
test80-feb2023-16tb7p-filter-v6-sk20.min-mar2023.binpack
test80-mar2023-2tb7p-filter-v6.min.binpack
test77-dec2021-16tb7p.no-db.min.binpack
test78-janfeb2022-16tb7p.no-db.min.binpack
test79-apr2022-16tb7p.no-db.min.binpack
ep499 chosen as start model for step4
4. 800 epochs, end-lambda 0.7, skip 24
0dd1cebea57 dataset https://github.com/official-stockfish/Stockfish/pull/4606
ep599 chosen as start model for step5
5. 800 epochs, end-lambda 0.7, skip 28
same dataset as step4
ep619 became nn-1b951f8b449d.nnue
For the final step5 training:
python3 easy_train.py \
--experiment-name L1-2048-S5-sameData-sk28-S4-0dd1cebea57-shuffled-S3-leela96-dfrc99-v2-T80dectofeb-sk20-mar-v6-T77decT78janfebT79apr-sk20-S2-LeelaFarseerT78T79T80-ep399-S1-UHOx2-wIsRight-multinet-dfrc-n5000-largeGensfen-d9 \
--training-dataset /data/leela96-dfrc99-T60novdec-v2-T80juntonovjanfebT79aprmayT78jantosepT77dec-v6dd-T80apr.binpack \
--early-fen-skipping 28 \
--nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes-L1-2048 \
--engine-test-branch linrock/Stockfish/L1-2048 \
--start-from-engine-test-net False \
--start-from-model /data/experiments/experiment_L1-2048-S4-0dd1cebea57-shuffled-S3-leela96-dfrc99-v2-T80dectofeb-sk20-mar-v6-T77decT78janfebT79apr-sk20-S2-LeelaFarseerT78T79T80-ep399-S1-UHOx2-wIsRight-multinet-dfrc-n5000-largeGensfen-d9/training/run_0/nn-epoch599.nnue
--max_epoch 800 \
--lr 4.375e-4 \
--gamma 0.995 \
--start-lambda 1.0 \
--end-lambda 0.7 \
--tui False \
--seed $RANDOM \
--gpus 0
SF training data components for the step1 dataset:
https://drive.google.com/drive/folders/1yLCEmioC3Xx9KQr4T7uB6GnLm5icAYGU
Leela training data for steps 2-5 can be found at:
https://robotmoon.com/nnue-training-data/
Due to larger L1 size and slower inference, the speed penalty loses elo
at STC. Measurements from 100 bench runs at depth 13 with x86-64-modern
on Intel Core i5-1038NG7 2.00GHz:
sf_base = 1240730 +/- 3443 (95%)
sf_test = 1153341 +/- 2832 (95%)
diff = -87388 +/- 1616 (95%)
speedup = -7.04330% +/- 0.130% (95%)
Local elo at 25k nodes per move (vs. L1-1536 nn-fdc1d0fe6455.nnue):
nn-epoch619.nnue : 21.1 +/- 3.2
Failed STC:
https://tests.stockfishchess.org/tests/view/6498ee93dc7002ce609cf979
LLR: -2.95 (-2.94,2.94) <0.00,2.00>
Total: 11680 W: 3058 L: 3299 D: 5323
Ptnml(0-2): 44, 1422, 3149, 1181, 44
LTC:
https://tests.stockfishchess.org/tests/view/649b32f5dc7002ce609d20cf
Elo: 0.68 ± 1.5 (95%) LOS: 80.5%
Total: 40000 W: 10887 L: 10809 D: 18304
Ptnml(0-2): 36, 3938, 11958, 4048, 20
nElo: 1.50 ± 3.4 (95%) PairsRatio: 1.02
Passed VLTC 180+1.8:
https://tests.stockfishchess.org/tests/view/64992b43dc7002ce609cfd20
LLR: 3.06 (-2.94,2.94) <0.00,2.00>
Total: 38086 W: 10612 L: 10338 D: 17136
Ptnml(0-2): 9, 3316, 12115, 3598, 5
Passed VLTC SMP 60+0.6 th 8:
https://tests.stockfishchess.org/tests/view/649a21fedc7002ce609d0c7d
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 38936 W: 11091 L: 10820 D: 17025
Ptnml(0-2): 1, 2948, 13305, 3207, 7
closes https://github.com/official-stockfish/Stockfish/pull/4646
Bench: 2505168
2023-07-01 13:34:30 +02:00
e551964ef6
Negative extension on cutNodes based on depth
...
This patch was inspired by candirufish original attempt at negative extensions
here that failed yellow: https://tests.stockfishchess.org/tests/view/6486529065ffe077ca124f32
I tested some variations of the idea and tuned a depth condition for
a modified version of it here https://tests.stockfishchess.org/tests/view/648db80a91c58631ce31fe00
after noticing abnormal scaling (ie many passed STC but not LTC)
After some small tweaks I got the final version here
Passed STC:
LLR: 2.98 (-2.94,2.94) <0.00,2.00>
Total: 122208 W: 32776 L: 32350 D: 57082
Ptnml(0-2): 310, 13250, 33553, 13686, 305
https://tests.stockfishchess.org/tests/view/64997934dc7002ce609d01e3
Passed LTC:
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 145092 W: 39617 L: 39115 D: 66360
Ptnml(0-2): 54, 13691, 44552, 14197, 52
https://tests.stockfishchess.org/tests/view/649a1c5ddc7002ce609d0bff
closes https://github.com/official-stockfish/Stockfish/pull/4644
Bench: 2637784
2023-07-01 13:06:49 +02:00
Shahin M. Shahin