jirayu_sri/stockfish
1
0
Fork 0
mirror of https://github.com/official-stockfish/Stockfish.git synced 2026-07-23 05:07:14 +00:00
Code Issues Packages Projects Releases Wiki Activity
6,866 Commits 6 Branches 60 Tags
93f2d14d95ca72ec2ec96c6e3de0b9a6121fe118
Commit Graph
241 Commits
Author SHA1 Message Date
Shawn XuandDisservin 93f2d14d95 Simplify Incremental Updates 
Passed Non-regression STC:
LLR: 3.03 (-2.94,2.94) <-1.75,0.25>
Total: 277856 W: 71575 L: 71611 D: 134670
Ptnml(0-2): 842, 30719, 75836, 30695, 836
https://tests.stockfishchess.org/tests/view/69169dc17ca8781852331d76

Supersedes #6430

closes https://github.com/official-stockfish/Stockfish/pull/6434

No functional change
 2025-11-30 21:43:54 +01:00
Shawn XuandDisservin 1132d893e0 Simplify Accumulator Updates 
Passed Non-regression STC:
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 146848 W: 37915 L: 37820 D: 71113
Ptnml(0-2): 415, 16159, 40186, 16244, 420
https://tests.stockfishchess.org/tests/view/691772217ca878185233202b

closes https://github.com/official-stockfish/Stockfish/pull/6421

No functional change
 2025-11-30 21:41:51 +01:00
Joost VandeVondele a27fcd6274 Fix format 
No functional change
 2025-11-17 13:57:53 +01:00
Carlos EsparzaandJoost VandeVondele 2084d94266 inline make_index() and avoid templating perspective 
combination of two patches.

pass perspective as argument
passed STC:
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 52832 W: 13725 L: 13528 D: 25579
Ptnml(0-2): 154, 5756, 14412, 5927, 167
https://tests.stockfishchess.org/tests/view/69162e307ca8781852331c6a

inline make_index
passed STC:
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 68768 W: 17786 L: 17607 D: 33375
Ptnml(0-2): 187, 7591, 18694, 7680, 232
https://tests.stockfishchess.org/tests/view/6916859e7ca8781852331d36

closes https://github.com/official-stockfish/Stockfish/pull/6429

No functional change
 2025-11-17 13:34:45 +01:00
Shawn XuandJoost VandeVondele 1d504b927f Fix undefined behavior 
C++ standard does not define `uint8_t` as an allowed pointer alias type. Despite
`uint8_t` being `unsigned char` on most platforms, this is not enforced by the standard.

https://eel.is/c++draft/basic.lval#11
https://stackoverflow.com/a/16138470

closes https://github.com/official-stockfish/Stockfish/pull/6420

No functional change
 2025-11-14 17:43:44 +01:00
Shawn XuandJoost VandeVondele db824e26be Pass accumulator caches by reference 
closes https://github.com/official-stockfish/Stockfish/pull/6416

No functional change
 2025-11-14 17:32:17 +01:00
Shawn XuandJoost VandeVondele bd82b9e01f Cleanup, fix style issues 
use naming convention for variables, functions, constants

closes https://github.com/official-stockfish/Stockfish/pull/6416

no functional change
 2025-11-14 17:29:01 +01:00
Timothy HerchenandJoost VandeVondele fa4f05d3ef Don't copy around DirtyThreats 
The contents of DirtyThreats gets memcpyed twice for each call to do_move.
(Return value optimization doesn't apply to the do_move function itself because
it constructs a std::pair, so it gets copied; and the calls to reset also
require a copy.) This patch inserts the dirty info in place.

Sometimes the caller of do_move ignores the DirtyThreats info, so we pass in
scratch objects. I found that stack-allocating these scratch objects was bad on
Fishtest, so I begrudgingly put them in the Position struct. Both templating
the do_move function on whether dirty threats are needed and putting a
null-check branch for each use of dirty threats were slowdowns locally. Of
course, nothing prevents a future attempt at cleaning this up.

passed STC
LLR: 2.96 (-2.94,2.94) <0.00,2.00>
Total: 68448 W: 17770 L: 17418 D: 33260
Ptnml(0-2): 198, 7425, 18630, 7769, 202
https://tests.stockfishchess.org/tests/view/6914c01a7ca87818523318ba

closes https://github.com/official-stockfish/Stockfish/pull/6414

No functional change
 2025-11-13 22:17:03 +01:00
Viren6andJoost VandeVondele 3ae7684714 Improve Threats Speed 
Passed STC:
LLR: 2.95 (-2.94,2.94) <0.00,2.00>
Total: 23168 W: 6132 L: 5845 D: 11191
Ptnml(0-2): 77, 2405, 6325, 2708, 69
https://tests.stockfishchess.org/tests/view/69148c3c7ca8781852331831

```
Result of  50 runs
==================
base (./stockfish.master       ) =     985641  +/- 4249
test (./stockfish.patch        ) =    1038567  +/- 5679
diff                             =     +52926  +/- 4473

speedup        = +0.0537
P(speedup > 0) =  1.0000

CPU: 16 x AMD Ryzen 9 3950X 16-Core Processor
Hyperthreading: on
```

closes https://github.com/official-stockfish/Stockfish/pull/6415

No functional change
 2025-11-13 22:13:47 +01:00
+1
sscg13Joost VandeVondeleShawn XuTimothy HerchenViren6Yoshie2000rn5f107s2cj5716AliceRoseliaLinmiao XuDisservin
 		8e5392d79a Update NNUE architecture to SFNNv10 with Threat Inputs and net nn-49c1193b131c.nnue 
This commit introduces Full Threat Input features, which are a subset of Piece(Square)-Piece(Square) pairs. In any given position, the active features consist of pairs where the second piece’s square lies in the attack set of the first piece. This is an extremely simplified explanation that leaves out many details. The already-used HalfKAv2_hm feature set completes the input features.
Minor quantization changes have also been made.

The net nn-49c1193b131c.nnue was trained by vondele using the following setup: https://github.com/vondele/nettest/blob/7de71238e9b295e3f88ed7c9c5936af632c9b981/threats.yaml

A graphical version of an earlier scheme (with less refinement) that illustrates the core concepts can be found attached.
[NewInputs.pdf](https://github.com/user-attachments/files/23478441/NewInputs.pdf)

Further information, as well as a brief description of the history of development, can be found attached.
[Stockfish threat inputs PR summary.pdf](https://github.com/user-attachments/files/23478634/Stockfish.threat.inputs.PR.summary.pdf)

This has been a huge effort spanning over half a year, with the original [discussion thread](https://discord.com/channels/435943710472011776/1336647760388034610) reaching over 11k messages. Thanks to everyone who has contributed.

Monty PRs:
https://github.com/official-monty/Monty/pull/87 (Initial threat input PR)
https://github.com/official-monty/Monty/pull/114 (Fixed threat indexing to take into account colour correctly)
https://github.com/official-monty/Monty/pull/116 (i8 quantisation of weights whilst keeping calculations in i16)

Yukari commit:
https://github.com/yukarichess/yukari/commit/2d482c64a79cec03cf4987d5289334b9cdc737bc (Threat inputs merged)

Plentychess PRs:
https://github.com/Yoshie2000/PlentyChess/pull/400 (Threat inputs merged)
https://github.com/Yoshie2000/PlentyChess/pull/411 (Threat input weights quantised to i8)

Passed STC:
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 63424 W: 16956 L: 16591 D: 29877
Ptnml(0-2): 276, 7522, 15797, 7795, 322
https://tests.stockfishchess.org/tests/view/69105b3dec1d00d2c195c569

Passed LTC:
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 27876 W: 7417 L: 7110 D: 13349
Ptnml(0-2): 23, 3033, 7530, 3318, 34
https://tests.stockfishchess.org/tests/view/6910d817ec1d00d2c195c66e

Passed VVLTC (Hash accidentally set to 1/2 normal value for both sides):
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 12458 W: 3353 L: 3102 D: 6003
Ptnml(0-2): 0, 1106, 3767, 1355, 1
https://tests.stockfishchess.org/tests/view/69115a26ec1d00d2c195c7cd

This version has also passed non-regression LTC against the originally passed version:
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 51144 W: 13086 L: 12903 D: 25155
Ptnml(0-2): 22, 5167, 15018, 5336, 29
https://tests.stockfishchess.org/tests/view/69138a317ca87818523314bf

LTC elo estimate on ARM:
1 patch     :    13.9    1.9  38296.5   73728    52
2 master    :     0.0   ----  35431.5   73728    48

closes https://github.com/official-stockfish/Stockfish/pull/6411

bench: 2626086

Co-authored-by: Shawn Xu <xu107288696@gmail.com>
Co-authored-by: Timothy Herchen <timothy.herchen@gmail.com>
Co-authored-by: Viren6 <94880762+Viren6@users.noreply.github.com>
Co-authored-by: Yoshie2000 <patrick.leonhardt@gmx.net>
Co-authored-by: Joost Vandevondele <Joost.VandeVondele@gmail.com>
Co-authored-by: rn5f107s2 <clemens.lerchl@gmail.com>
Co-authored-by: cj5716 <125858804+cj5716@users.noreply.github.com>
Co-authored-by: AliceRoselia <63040919+AliceRoselia@users.noreply.github.com>
Co-authored-by: Linmiao Xu <linmiao.xu@gmail.com>
Co-authored-by: Disservin <disservin.social@gmail.com>
 2025-11-12 10:49:39 +01:00
Tomasz SobczykJoost VandeVondeledisservin
 		69a01b88f3 Use shared memory for network weights 
This enables different Stockfish processes that use the same weights to use the
same memory. The approach establishes equivalence by memory content, and is
compatible with NUMA replication.  The benefit of sharing is reduced memory usage
and a speedup thanks to improved (inter-process) caching of the network in the
CPUs cache, and thus reduced bandwidth usage to main memory. Even though this
change doesn't benefit a user running a single process, this helps on fishtest
or e.g.  for Lichess, when multiple games run concurrently, or multiple
positions are analyzed in parallel.

This concept was probably first introduced in the Monty engine
(https://github.com/official-monty/Monty/pull/62), after a discussion in
https://github.com/official-stockfish/fishtest/issues/2077 on the issue of
memory pressure. Measurements based on Torch
(https://github.com/user-attachments/files/21386224/verbatim.pdf) further
suggested that large gains were possible. Multiple other engines have
adopted this 'verbatim' format as well.

The implementation here adds the flexibility needed for SF, for example, retains
the ability to bundle compressed networks with the binary, to load nets by uci
option, and to distribute the shared nets to the proper NUMA region. This
flexibility comes with a fair amount of complexity in the implementation, such
as OS specific code, and fallback code.

For most users this should be transparent. However, for example, those running
docker containers should ensure the `--ipc` flag is set correctly, and
`--shm-size` is sufficiently large.

The benefits of this patch significantly depend on hardware, with systems with
many cores and a large (O(150MB), the net size) L3 cache benefitting typically
most.  On such systems SF speedups (as measured via nps playing games with
large concurrency but just 1 thread) can be 38%, which results in master vs.
patch Elo which gains about 25 Elo.

```
   # PLAYER             :  RATING  ERROR   POINTS  PLAYED   (%)
   1 shared_memoryPR    :    24.8    1.9  39432.0   73728    53
   2 master             :     0.0   ----  34296.0   73728    47
```

In a multithreaded setup, where weights are already shared, that benefit is smaller,
for example on the same HW as above, but with 8t for each side.
```
   # PLAYER             :  RATING  ERROR  POINTS  PLAYED   (%)
   1 shared_memoryPR    :     5.2    3.5  9351.0   18432    51
   2 master             :     0.0   ----  9081.0   18432    49
```

On fishtest with a typical hardware mix of our contributors, the following was measured:

STC, 60k games
https://tests.stockfishchess.org/tests/view/69074a49ea4b268f1fac236c
Elo: 4.69 ± 1.4 (95%) LOS: 100.0%
Total: 60000 W: 16085 L: 15275 D: 28640
Ptnml(0-2): 154, 6440, 16053, 7148, 205
nElo: 9.38 ± 2.8 (95%) PairsRatio: 1.12

To verify correctness with a single process on a NUMA architecture,
speedtest was used, confirming near equivalence:
```
master:        Average (over 10):  296236186
shared_memory: Average (over 10):  295769332
```
Currently, using large pages for the shared network weights is not always possible,
which can lead to a small slowdown (1-2%), in case a single process is run.

closes https://github.com/official-stockfish/Stockfish/pull/6173

No functional change

Co-authored-by: disservin <disservin.social@gmail.com>
Co-authored-by: Joost VandeVondele <Joost.VandeVondele@gmail.com>
 2025-11-02 16:04:09 +01:00
Carlos EsparzaandJoost VandeVondele e9674a7888 simplify make_index() 
passed non-regression STC: https://tests.stockfishchess.org/tests/view/68fdb409637acd2a11e72f11
LLR: 3.08 (-2.94,2.94) <-1.75,0.25>
Total: 95008 W: 24837 L: 24677 D: 45494
Ptnml(0-2): 268, 10024, 26775, 10154, 283

closes https://github.com/official-stockfish/Stockfish/pull/6384

no functional change
 2025-11-01 11:34:54 +01:00
Carlos EsparzaandJoost VandeVondele 11ab4cde07 Avoid unnecessary allocations in AccumulatorStack 
replacing the vector with an array resulted in a .45+-.10 % speedup.

closes https://github.com/official-stockfish/Stockfish/pull/6352

no functional change
 2025-11-01 11:12:03 +01:00
Timothy HerchenandJoost VandeVondele 6764561916 Improve index generation 
The speedup seems to vary by machine.  The indexing function can be changed w/o needing to understand intrinsics.

Result of 100 runs
==================
base (...ish_baseline) =    1719637  +/- 3233
test (./stockfish    ) =    1734245  +/- 3534
diff                   =     +14608  +/- 4868

speedup        = +0.0085
P(speedup > 0) =  1.0000

closes https://github.com/official-stockfish/Stockfish/pull/6366

No functional change
 2025-11-01 10:42:42 +01:00
Shawn XuandJoost VandeVondele f434cc2918 Allow AccumulatorStack::size to point to one past the end 
this is guaranteed to be correct since we access the last element with `size - 1`

closes https://github.com/official-stockfish/Stockfish/pull/6368

fixes https://github.com/official-stockfish/Stockfish/issues/6367

no functional change
 2025-11-01 10:34:44 +01:00
mstemberaandJoost VandeVondele c956df4cbb Split accumulator 3-way for avxvnni 
This does the same thing for x86-64-avxvnni as #6336, #6339.

closes https://github.com/official-stockfish/Stockfish/pull/6347

No functional change
 2025-10-14 17:25:48 +02:00
Timothy HerchenJoost VandeVondeleM Stembera
 		b09339a420 Split accumulator 3-Way 
Squeeze a tiny bit more juice from the original idea in #6336 which this is on top of.

https://tests.stockfishchess.org/tests/view/68dddd85fa806e2e8393c0b9
LLR: 2.95 (-2.94,2.94) <0.00,2.00>
Total: 156320 W: 40925 L: 40447 D: 74948
Ptnml(0-2): 427, 17330, 42172, 17800, 431

4-way doesn't look to be better than this.
https://tests.stockfishchess.org/tests/view/68dde19efa806e2e8393c0c1

closes https://github.com/official-stockfish/Stockfish/pull/6339

No functional change

Co-authored-by: M Stembera <m_stembera@yahoo.com>
 2025-10-05 09:33:23 +02:00
Timothy HerchenandJoost VandeVondele 9b164d9520 Shave some instructions off a hot loop in affine transform 
On x86, GCC generates highly suboptimal code for this loop in its old form,
about 2x as many instructions as necessary. This decreases throughput
especially in an SMT setting. Clang does a better job but this change still has
some improvement. Note that the std::ptrdiff_t type is not optional; using an
unsigned type brings back the bad assembly. (Not sure why, but it seems
reliable on all the GCC versions I tested.)

passed STC:
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 44672 W: 11841 L: 11527 D: 21304
Ptnml(0-2): 165, 4625, 12415, 4993, 138
https://tests.stockfishchess.org/tests/view/68d8111efa806e2e8393b10e

closes https://github.com/official-stockfish/Stockfish/pull/6331

No functional change
 2025-09-28 21:04:29 +02:00
mstemberaandJoost VandeVondele 0383670cd5 Avoid using _mm512_storeu_epi16() 
gcc 9 & 10 do not provide this function, instead use the generic _mm512_storeu_si512

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=95483

https://tests.stockfishchess.org/actions?max_actions=1&action=&user=&text=&before=1755266300.455175&run_id=

closes https://github.com/official-stockfish/Stockfish/pull/6231

No functional change
 2025-08-16 11:46:39 +02:00
mstemberaandJoost VandeVondele 5464f7b114 Remove an instruction from find_nnz() 
closes https://github.com/official-stockfish/Stockfish/pull/6212

No functional change
 2025-08-09 08:54:47 +02:00
mstemberaandJoost VandeVondele 83071917e9 Optimize find_nnz() using VBMI2 
about a 0.7% speedup for the x86-64-avx512icl ARCH

closes https://github.com/official-stockfish/Stockfish/pull/6186

No functional change
 2025-08-02 15:49:35 +02:00
mstemberaandDisservin ce7254b5ea Optimize find_nnz() using AVX512 
About a 1% speedup for ARCH x86-64-avx512 and x86-64-vnni512.

Note:  This could be optimized further if we wanted to add an ARCH
supporting VBMI2 which is even more modern than VNNI.

https://en.wikichip.org/wiki/x86/avx512_vbmi2

closes https://github.com/official-stockfish/Stockfish/pull/6139

No functional change
 2025-07-02 18:41:45 +02:00
mstemberaandJoost VandeVondele d27298d7dc Remove unused threatenedPieces 
threatenedPieces is no longer used since #6023

Also can_move_king_or_pawn() can be const.
Also remove a couple of redundant declarations.

closes https://github.com/official-stockfish/Stockfish/pull/6101

No functional change
 2025-06-02 21:24:38 +02:00
Shawn XuandJoost VandeVondele dc85c5a4c9 Remove nnz lookup table load optimization 
Passed Non-regression STC:
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 63296 W: 16491 L: 16311 D: 30494
Ptnml(0-2): 129, 6624, 17972, 6784, 139
https://tests.stockfishchess.org/tests/view/6833ce486ec7634154f9cb22

Passed 2nd Non-regression STC:
LLR: 2.97 (-2.94,2.94) <-1.75,0.25>
Total: 369568 W: 95314 L: 95451 D: 178803
Ptnml(0-2): 897, 40231, 102601, 40222, 833
https://tests.stockfishchess.org/tests/view/68355c956ec7634154f9ce07

closes https://github.com/official-stockfish/Stockfish/pull/6100

no functional change
 2025-06-02 21:21:54 +02:00
Shawn XuandJoost VandeVondele 472cc764be Move SIMD code to a separate header 
Passed Non-regression STC:
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 115328 W: 29903 L: 29777 D: 55648
Ptnml(0-2): 265, 12293, 32444, 12375, 287
https://tests.stockfishchess.org/tests/view/68300e086ec7634154f9b1d1

closes https://github.com/official-stockfish/Stockfish/pull/6086

no functional change
 2025-05-25 20:52:57 +02:00
DisservinandJoost VandeVondele 2662d6bf35 Update clang-format to v20 
closes https://github.com/official-stockfish/Stockfish/pull/6085

No functional change
 2025-05-23 08:54:06 +02:00
DisservinandJoost VandeVondele c13c1d2c30 Silence "may be used uninitialized" GCC 15 warning 
closes https://github.com/official-stockfish/Stockfish/pull/6083

No functional change
 2025-05-23 08:53:00 +02:00
Carlos EsparzaandDisservin 63c6f22627 Simplify DirtyPiece 
Simplifies the DirtyPiece struct.

passed STC: https://tests.stockfishchess.org/tests/view/68054c9798cd372e3aea05d7
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 36608 W: 9641 L: 9437 D: 17530
Ptnml(0-2): 89, 3630, 10668, 3822, 95

passed LTC: https://tests.stockfishchess.org/tests/view/6805514598cd372e3aea0783
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 127620 W: 31993 L: 31894 D: 63733
Ptnml(0-2): 42, 10983, 41665, 11074, 46

closes https://github.com/official-stockfish/Stockfish/pull/6016

No functional change
 2025-05-13 20:30:22 +02:00
Carlos EsparzaandDisservin fda269a299 Introduce double incremental accumulator updates 
when we need to update an accumulator by two moves and the second move
captures the piece moved in the first move, we can skip computing the
middle accumulator and cancel a feature add with a feature remove to
save work.

Passed STC
https://tests.stockfishchess.org/tests/view/67f70b1c31d7cf8afdc45f51
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 72800 W: 18878 L: 18529 D: 35393
Ptnml(0-2): 160, 7711, 20374, 7930, 225

closes https://github.com/official-stockfish/Stockfish/pull/5988

No functional change
 2025-04-27 19:27:18 +02:00
FauziAkramandJoost VandeVondele 8b85290313 Remove manual stack alignment workaround for GCC < 9.3 
consequently using these old compilers will now error out.

closes https://github.com/official-stockfish/Stockfish/pull/6008

No functional change.
 2025-04-26 22:15:08 +02:00
Shawn XuandJoost VandeVondele f273eea71f Remove non-functional accumulator reset 
Passed Non-regression STC:
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 219360 W: 56600 L: 56583 D: 106177
Ptnml(0-2): 582, 23419, 61620, 23518, 541
https://tests.stockfishchess.org/tests/view/67fad20dcd501869c669780f

closes https://github.com/official-stockfish/Stockfish/pull/5986

no functional change
 2025-04-26 21:30:01 +02:00
FauziAkramandDisservin 5f8e67a544 Remove combineLast3 optimization 
Passed non-reg STC 1st:
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 67328 W: 17296 L: 17118 D: 32914
Ptnml(0-2): 158, 7095, 19011, 7211, 189
https://tests.stockfishchess.org/tests/view/67e6c2796682f97da2178ebe

Passed non-reg STC 2nd:
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 92288 W: 23885 L: 23734 D: 44669
Ptnml(0-2): 213, 10039, 25518, 10132, 242
https://tests.stockfishchess.org/tests/view/67ed6a2d31d7cf8afdc45190

closes https://github.com/official-stockfish/Stockfish/pull/5975

Bench: 1875196
 2025-04-18 14:32:26 +02:00
mstemberaandDisservin 8d2eef2b1e Fix fused() all controll paths should return a value. 
closes https://github.com/official-stockfish/Stockfish/pull/5973

No functional change
 2025-04-18 14:32:26 +02:00
mstemberaandDisservin 1577fa0470 Simplify Forward and Backward 
Forward and Backward are not independent so simplify to a bool.

Cleanup some MSVC warnings like "warning C4267: 'argument': conversion
from 'size_t' to 'int', possible loss of data" Other minor formatting
stuff.

This is a rebase of https://github.com/official-stockfish/Stockfish/pull/5912

closes https://github.com/official-stockfish/Stockfish/pull/5967

No functional change
 2025-04-18 14:32:19 +02:00
Disservin 7beff18ef0 Retire Acc Pointer 
Since @xu-shawn's refactor the acc pointer has become a bit unnecessary,
we can achieve the same behavior by using the dimension size to get the
right accumulator from the `AccumulatorState`. I think the acc pointer
has become a bit of a burden required to be passed through multiple
different functions together with the necessary templating required.

Passed Non-Regression STC:
https://tests.stockfishchess.org/tests/view/67ed600f31d7cf8afdc45183
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 279744 W: 72037 L: 72082 D: 135625
Ptnml(0-2): 673, 29918, 78767, 29809, 705

closes https://github.com/official-stockfish/Stockfish/pull/5942

No functional change
 2025-04-18 13:54:09 +02:00
mstemberaandDisservin ed89817f62 Various cleanups 
Various simplifications, cleanups, consistancy improvements, and warning
mitigations.

Passed Non-Regression STC:
https://tests.stockfishchess.org/tests/view/67e7dd2d6682f97da2178fd8
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 386848 W: 99593 L: 99751 D: 187504
Ptnml(0-2): 1024, 41822, 107973, 41498, 1107

closes https://github.com/official-stockfish/Stockfish/pull/5948

No functional change
 2025-04-02 17:43:14 +02:00
Shawn XuandDisservin c2ff7a95c3 Cleanup fused updates 
Passed Non-regression STC:
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 70656 W: 18257 L: 18077 D: 34322
Ptnml(0-2): 217, 7912, 18879, 8114, 206
https://tests.stockfishchess.org/tests/view/67e23ae78888403457d876d4

closes https://github.com/official-stockfish/Stockfish/pull/5941

No functional change
 2025-04-02 17:34:31 +02:00
Disservin aafc732bcb Silence "may be used uninitialized" GCC warning 
Helps gcc silence the warning about

```
warning: 'added' may be used uninitialized [-Wmaybe-uninitialized]
const IndexType offsetA0 = TransformedFeatureDimensions * added[0];
```

closes https://github.com/official-stockfish/Stockfish/pull/5950

No functional change
 2025-03-29 11:55:55 +01:00
Shawn XuandDisservin fc0e0a44d4 Refactor accumulator storage/updates 
Passed Non-regression STC:
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 115840 W: 29983 L: 29854 D: 56003
Ptnml(0-2): 338, 12990, 31149, 13091, 352
https://tests.stockfishchess.org/tests/view/67d0a044166a3e8781d84223

closes https://github.com/official-stockfish/Stockfish/pull/5927

No functional change
 2025-03-21 11:12:47 +01:00
mstemberaandDisservin e4d7136042 Combine last 3 add/remove operations 
https://tests.stockfishchess.org/tests/view/67ad587052879dfd14d7e8a5
LLR: 2.95 (-2.94,2.94) <0.00,2.00>
Total: 45856 W: 12177 L: 11855 D: 21824
Ptnml(0-2): 176, 4845, 12588, 5119, 200

The two most common cases are when added and removed counts are equal
and when they are off by 1.  When they are off by 1 we currently do a
pass combining 2 and then an extra pass for the last 1.  This patch does
a single combined pass on the final 3 instead. Tested on top of the
simplification in
https://github.com/official-stockfish/Stockfish/pull/5901

closes https://github.com/official-stockfish/Stockfish/pull/5902

No functional change
 2025-02-27 20:30:44 +01:00
mstemberaandDisservin d330b48e21 Handle updating the small accumulator the same way as the big one 
https://tests.stockfishchess.org/tests/view/67abfe1ca04df5eb8dbebf0b
LLR: 2.97 (-2.94,2.94) <-1.75,0.25>
Total: 153088 W: 40072 L: 39979 D: 73037
Ptnml(0-2): 619, 16728, 41764, 16807, 626

closes https://github.com/official-stockfish/Stockfish/pull/5901

No functional change
 2025-02-27 20:30:10 +01:00
Disservin 291a429cdd Remove duplicated info string printing 
Currently "info string" is being printed twice for the network arch

```
info string info string NNUE evaluation using nn-1c0000000000.nnue (133MiB, (22528, 3072, 15, 32, 1))
info string info string NNUE evaluation using nn-37f18f62d772.nnue (6MiB, (22528, 128, 15, 32, 1))
```

closes https://github.com/official-stockfish/Stockfish/pull/5889

No functional change
 2025-02-24 19:10:38 +01:00
FauziAkramandDisservin 095d19afea Use neon_m128_reduce_add_epi32 for NEON vector reduction 
Accomplishing the entire horizontal addition in a single NEON instruction

closes https://github.com/official-stockfish/Stockfish/pull/5885

No functional change
 2025-02-24 19:07:29 +01:00
Carlos EsparzaandDisservin e9997afb1c Replace hint_common_parent_position() by backwards accumulator updates 
Only calls to `evaluate()` now trigger NNUE accumulator updates. To make
sure that we are likely to find parent positions from which to update
the accumulators we perform a backwards NNUE update whenever we compute
the accumulator from scratch for some position.

passed STC
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 39680 W: 10474 L: 10164 D: 19042
Ptnml(0-2): 171, 4068, 11042, 4398, 161
https://tests.stockfishchess.org/tests/view/67a27f26eb183d11c65945be

passed LTC
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 337308 W: 86408 L: 85550 D: 165350
Ptnml(0-2): 276, 30551, 106126, 31441, 260
https://tests.stockfishchess.org/tests/view/67a287efeb183d11c65945ee

then simplified:
STC
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 28608 W: 7641 L: 7413 D: 13554
Ptnml(0-2): 132, 3036, 7744, 3256, 136
https://tests.stockfishchess.org/tests/view/67a4703719f522d3866d3345

LTC
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 200226 W: 51026 L: 50990 D: 98210
Ptnml(0-2): 170, 18468, 62799, 18508, 168
https://tests.stockfishchess.org/tests/view/67a4f255229c1a170cc08964

The version in this PR is a bit different from the simplified version,
but it's compile-time changes only.

closes https://github.com/official-stockfish/Stockfish/pull/5870

No functional change
 2025-02-24 19:01:23 +01:00
Shawn XuandJoost VandeVondele e7367cef0f Clean up pack reordering 
closes https://github.com/official-stockfish/Stockfish/pull/5802

no functional change
 2025-01-25 20:17:39 +01:00
mstemberaandJoost VandeVondele 18b3465a86 Generate lookup indices at compile time. 
Credit to @Disservin: the constexpr lsb is just the De Bruijn bitscan with the xor from the cpw https://www.chessprogramming.org/BitScan

closes https://github.com/official-stockfish/Stockfish/pull/5801

No functional change
 2025-01-25 20:12:38 +01:00
Shawn XuandJoost VandeVondele 62ecdfe82c simplify accumulator updates 
After #5759 accumulator updates are strictly on a per-move basis. Therefore, the generic code for updating multiple moves at once is no longer needed.

Passed Non-regression STC:
LLR: 3.00 (-2.94,2.94) <-1.75,0.25>
Total: 81696 W: 21204 L: 21039 D: 39453
Ptnml(0-2): 210, 8431, 23416, 8566, 225
https://tests.stockfishchess.org/tests/view/67823a24a31c4c13e83518a8

closes https://github.com/official-stockfish/Stockfish/pull/5760

no functional change
 2025-01-25 20:09:09 +01:00
mstemberaandJoost VandeVondele 329c267e25 Optimize find_nnz() by reducing the size of lookup_indices 
https://tests.stockfishchess.org/tests/view/67896b688082388fa0cbfdee
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 452800 W: 118213 L: 117300 D: 217287
Ptnml(0-2): 1638, 50255, 121864, 50842, 1801

It's faster to shrink lookup_indices[] to 8 bit and zero extend to 16 bit using _mm_cvtepu8_epi16() than to read the larger 16 bit version. I suspect that having the constants available at compile time isn't too valuable and can be simplified back to generating at initialization time since this version also almost passed. https://tests.stockfishchess.org/tests/view/67863057460e2910c51de7e0 I will try that as a follow up.

closes https://github.com/official-stockfish/Stockfish/pull/5793

No functional change
 2025-01-18 21:13:12 +01:00
pb00067andJoost VandeVondele 56000827af Simplify common hint for parent position 
Removes function hint_common_access_for_perspective together with it's comments,
which weren't accurate anymore since merge of #5576

https://tests.stockfishchess.org/tests/view/6784c9cd460e2910c51dde39
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 295104 W: 76702 L: 76765 D: 141637
Ptnml(0-2): 1031, 32135, 81249, 32140, 997

closes https://github.com/official-stockfish/Stockfish/pull/5780

No functional change
 2025-01-18 20:35:46 +01:00
Shawn XuandDisservin 8d517bddff Simplify accumulator updates 
AMD Ryzen 5 7600X
```
sf_base =  1902646 +/-   2114 (95%)
sf_test =  1920873 +/-   2515 (95%)
diff    =    18227 +/-   3067 (95%)
speedup = 0.95800% +/- 0.161% (95%)
```

Ryzen 9 5950X
```
sf_base =  1413387 +/-   3592 (95%)
sf_test =  1437893 +/-   3355 (95%)
diff    =    24505 +/-   4669 (95%)
speedup = 1.73380% +/- 0.330% (95%)
```

Intel Core i7-6700K
```
sf_base =   912476 +/-   1863 (95%)
sf_test =   921864 +/-   2042 (95%)
diff    =     9388 +/-   3333 (95%)
speedup = 1.02893% +/- 0.365% (95%)
```

Raspberry Pi 5
```
sf_base =   260993 +/-   1508 (95%)
sf_test =   262912 +/-   1746 (95%)
diff    =     1918 +/-   1221 (95%)
speedup = 0.73504% +/- 0.468% (95%)
```

Passed Non-regression STC:
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 23072 W: 6041 L: 5813 D: 11218
Ptnml(0-2): 61, 2435, 6319, 2657, 64
https://tests.stockfishchess.org/tests/view/6780a0ca9168c8bf30927757

closes https://github.com/official-stockfish/Stockfish/pull/5759

No functional change
 2025-01-12 21:21:53 +01:00