Reordered weights in such a way that accumulated sum fits to output.
Weights are grouped in blocks of four elements because four
int8 (weight type) corresponds to one int32 (output type).
No horizontal additions.
Grouped AVX512, AVX2 and SSSE3 implementations.
Repeated code was removed.
An earlier version passed STC:
LLR: 2.97 (-2.94,2.94) {-0.25,1.25}
Total: 15336 W: 1495 L: 1355 D: 12486
Ptnml(0-2): 44, 1054, 5350, 1158, 62
https://tests.stockfishchess.org/tests/view/5ff60e106019e097de3eefd5
Speedup depends on the architecture, up to 4% measured on a NNUE only bench.
closes https://github.com/official-stockfish/Stockfish/pull/3287
No functional change
Improves throughput by summing 2 intermediate dot products using 16 bit addition before upconverting to 32 bit.
Potential saturation is detected and the code-path is avoided in this case.
The saturation can't happen with the current nets,
but nets can be constructed that trigger this check.
STC https://tests.stockfishchess.org/tests/view/5fd40a861ac1691201888479
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 25544 W: 2451 L: 2296 D: 20797
Ptnml(0-2): 92, 1761, 8925, 1888, 106
about 5% speedup
closes https://github.com/official-stockfish/Stockfish/pull/3261
No functional change
This appears to be slightly faster than using a comparison against zero
to compute the high bits, on both old (like Pentium III) and new (like
Zen 2) hardware.
closes https://github.com/official-stockfish/Stockfish/pull/3254
No functional change.
in affine transform for AVX512/AVX2/SSSE3
The idea is to initialize sum with the first element instead of zero.
Reduce one add_epi32 and one set_zero SIMD instructions for each output dimension.
sum = 0; for i = 1 to n sum += a[i] ->
sum = a[1]; for i = 2 to n sum += a[i]
STC:
LLR: 2.95 (-2.94,2.94) {-0.25,1.25}
Total: 69048 W: 7024 L: 6799 D: 55225
Ptnml(0-2): 260, 5175, 23458, 5342, 289
https://tests.stockfishchess.org/tests/view/5faf2cf467cbf42301d6aa06
closes https://github.com/official-stockfish/Stockfish/pull/3227
No functional change.
For the feature transformer the code is analogical to AVX2 since there was room for easy adaptation of wider simd registers.
For the smaller affine transforms that have 32 byte stride we keep 2 columns in one zmm register. We also unroll more aggressively so that in the end we have to do 16 parallel horizontal additions on ymm slices each consisting of 4 32-bit integers. The slices are embedded in 8 zmm registers.
These changes provide about 1.5% speedup for AVX-512 builds.
Closes https://github.com/official-stockfish/Stockfish/pull/3218
No functional change.
A non-functional speedup. Unroll the loops going over
the output dimensions in the affine transform layers by
a factor of 4 and perform 4 horizontal additions at a time.
Instead of doing naive horizontal additions on each vector
separately use hadd and shuffling between vectors to reduce
the number of instructions by using all lanes for all stages
of the horizontal adds.
passed STC of the initial version:
LLR: 2.95 (-2.94,2.94) {-0.25,1.25}
Total: 17808 W: 1914 L: 1756 D: 14138
Ptnml(0-2): 76, 1330, 5948, 1460, 90
https://tests.stockfishchess.org/tests/view/5f9d516f6a2c112b60691da3
passed STC of the final version after cleanup:
LLR: 2.95 (-2.94,2.94) {-0.25,1.25}
Total: 16296 W: 1750 L: 1595 D: 12951
Ptnml(0-2): 72, 1192, 5479, 1319, 86
https://tests.stockfishchess.org/tests/view/5f9df5776a2c112b60691de3
closes https://github.com/official-stockfish/Stockfish/pull/3203
No functional change
This patch was inspired by c065abd which updates the accumulator,
if possible, based on the accumulator of two plies back if
the accumulator of the preceding ply is not available.
With this patch we look back even further in the position history
in an attempt to reduce the number of complete recomputations.
When we find a usable accumulator for the position N plies back,
we also update the accumulator of the position N-1 plies back
because that accumulator is most likely to be helpful later
when evaluating positions in sibling branches.
By not updating all intermediate accumulators immediately,
we avoid doing too much work that is not certain to be useful.
Overall, roughly 2-3% speedup.
This patch makes the code more specific to the net architecture,
changing input features of the net will require additional changes
to the incremental update code as discussed in the PR #3193 and #3191.
Passed STC:
https://tests.stockfishchess.org/tests/view/5f9056712c92c7fe3a8c60d0
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 10040 W: 1116 L: 968 D: 7956
Ptnml(0-2): 42, 722, 3365, 828, 63
closes https://github.com/official-stockfish/Stockfish/pull/3193
No functional change.
- Clean signature of functions in namespace NNUE
- Add comment for countermove based pruning
- Remove bestMoveCount variable
- Add const qualifier to kpp_board_index array
- Fix spaces in get_best_thread()
- Fix indention in capture LMR code in search.cpp
- Rename TtmemDeleter to LargePageDeleter
Closes https://github.com/official-stockfish/Stockfish/pull/3063
No functional change
Use TT memory functions to allocate memory for the NNUE weights. This
should provide a small speed-up on systems where large pages are not
automatically used, including Windows and some Linux distributions.
Further, since we now have a wrapper for std::aligned_alloc(), we can
simplify the TT memory management a bit:
- We no longer need to store separate pointers to the hash table and
its underlying memory allocation.
- We also get to merge the Linux-specific and default implementations
of aligned_ttmem_alloc().
Finally, we'll enable the VirtualAlloc code path with large page
support also for Win32.
STC: https://tests.stockfishchess.org/tests/view/5f66595823a84a47b9036fba
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 14896 W: 1854 L: 1686 D: 11356
Ptnml(0-2): 65, 1224, 4742, 1312, 105
closes https://github.com/official-stockfish/Stockfish/pull/3081
No functional change.
This fixes#3108 and removes some NNUE code that is currently not used.
At the moment, do_null_move() copies the accumulator from the previous
state into the new state, which is correct. It then clears the "computed_score"
flag because the side to move has changed, and with the other side to move
NNUE will return a completely different evaluation (normally with changed
sign but also with different NNUE-internal tempo bonus).
The problem is that do_null_move() clears the wrong flag. It clears the
computed_score flag of the old state, not of the new state. It turns out
that this almost never affects the search. For example, fixing it does not
change the current bench (but it does change the previous bench). This is
because the search code usually avoids calling evaluate() after a null move.
This PR corrects do_null_move() by removing the computed_score flag altogether.
The flag is not needed because nnue_evaluate() is never called twice on a position.
This PR also removes some unnecessary {}s and inserts a few blank lines
in the modified NNUE files in line with SF coding style.
Resulf ot STC non-regression test:
LLR: 2.95 (-2.94,2.94) {-1.25,0.25}
Total: 26328 W: 3118 L: 3012 D: 20198
Ptnml(0-2): 126, 2208, 8397, 2300, 133
https://tests.stockfishchess.org/tests/view/5f553ccc2d02727c56b36db1
closes https://github.com/official-stockfish/Stockfish/pull/3109
bench: 4109324
covers the most important cases from the user perspective:
It embeds the default net in the binary, so a download of that binary will result
in a working engine with the default net. The engine will be functional in the default mode
without any additional user action.
It allows non-default nets to be used, which will be looked for in up to
three directories (working directory, location of the binary, and optionally a specific default directory).
This mechanism is also kept for those developers that use MSVC,
the one compiler that doesn't have an easy mechanism for embedding data.
It is possible to disable embedding, and instead specify a specific directory, e.g. linux distros might want to use
CXXFLAGS="-DNNUE_EMBEDDING_OFF -DDEFAULT_NNUE_DIRECTORY=/usr/share/games/stockfish/" make -j ARCH=x86-64 profile-build
passed STC non-regression:
https://tests.stockfishchess.org/tests/view/5f4a581c150f0aef5f8ae03a
LLR: 2.95 (-2.94,2.94) {-1.25,-0.25}
Total: 66928 W: 7202 L: 7147 D: 52579
Ptnml(0-2): 291, 5309, 22211, 5360, 293
closes https://github.com/official-stockfish/Stockfish/pull/3070
fixes https://github.com/official-stockfish/Stockfish/issues/3030
No functional change.
This patch removes the EvalList structure from the Position object and generally simplifies the interface between do_move() and the NNUE code.
The NNUE evaluation function first calculates the "accumulator". The accumulator consists of two halves: one for white's perspective, one for black's perspective.
If the "friendly king" has moved or the accumulator for the parent position is not available, the accumulator for this half has to be calculated from scratch. To do this, the NNUE node needs to know the positions and types of all non-king pieces and the position of the friendly king. This information can easily be obtained from the Position object.
If the "friendly king" has not moved, its half of the accumulator can be calculated by incrementally updating the accumulator for the previous position. For this, the NNUE code needs to know which pieces have been added to which squares and which pieces have been removed from which squares. In principle this information can be derived from the Position object and StateInfo struct (in the same way as undo_move() does this). However, it is probably a bit faster to prepare this information in do_move(), so I have kept the DirtyPiece struct. Since the DirtyPiece struct now stores the squares rather than "PieceSquare" indices, there are now at most three "dirty pieces" (previously two). A promotion move that captures a piece removes the capturing pawn and the captured piece from the board (to SQ_NONE) and moves the promoted piece to the promotion square (from SQ_NONE).
An STC test has confirmed a small speedup:
https://tests.stockfishchess.org/tests/view/5f43f06b5089a564a10d850a
LLR: 2.94 (-2.94,2.94) {-0.25,1.25}
Total: 87704 W: 9763 L: 9500 D: 68441
Ptnml(0-2): 426, 6950, 28845, 7197, 434
closes https://github.com/official-stockfish/Stockfish/pull/3068
No functional change
due to downclocking on current chips (tested up to cascade lake)
supporting avx512 and vnni512, it is better to use avx2 or vnni256
in multithreaded (in particular hyperthreaded) engine use.
In single threaded use, the picture is different.
gcc compilation for vnni256 requires a toolchain for gcc >= 9.
closes https://github.com/official-stockfish/Stockfish/pull/3038
No functional change
Clang-10.0.0 poses as gcc-4.2:
$ clang++ -E -dM - </dev/null | grep GNUC
This means that Clang is using the workaround for the alignment bug of gcc-8
even though it does not have the bug (as far as I know).
This patch should speed up AVX2 and AVX512 compiles on Windows (when using Clang),
because it disables (for Clang) the gcc workaround we had introduced in this commit:
875183b310
closes https://github.com/official-stockfish/Stockfish/pull/3050
No functional change.
This patch fixes the byte order when reading 16- and 32-bit values from the network file on a big-endian machine.
Bytes are ordered in read_le() using unsigned arithmetic, which doesn't need tricks to determine the endianness of the machine. Unfortunately the compiler doesn't seem to be able to optimise the ordering operation, but reading in the weights is not a time-critical operation and the extra time it takes should not be noticeable.
Big endian systems are still untested with NNUE.
fixes#3007
closes https://github.com/official-stockfish/Stockfish/pull/3009
No functional change.
Adds support for Vector Neural Network Instructions (avx512), as available on Intel Cascade Lake
The _mm512_dpbusd_epi32() intrinsic (vpdpbusd instruction) is taylor made for NNUE.
on a cascade lake CPU (AWS C5.24x.large, gcc 10) NNUE eval is at roughly 78% nps of classical
(single core test)
bench 1024 1 24 default depth:
target classical NNUE ratio
vnni 2207232 1725987 78.20
avx512 2216789 1671734 75.41
avx2 2194006 1611263 73.44
modern 2185001 1352469 61.90
closes https://github.com/official-stockfish/Stockfish/pull/2987
No functional change
this workaround is possibly rather a windows & gcc specific problem. See e.g.
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=54412#c25
on Linux with gcc 8 this patch brings roughly a 8% speedup.
However, probably needs some testing in the wild.
includes a workaround for an old msys make (3.81) installation (fixes#2984)
No functional change
This patch allows old x86 CPUs, from AMD K8 (which the x86-64 baseline
targets) all the way down to the Pentium MMX, to benefit from NNUE with
comparable performance hit versus hand-written eval as on more modern
processors.
NPS of the bench with NNUE enabled on a Pentium III 1.13 GHz (using the
MMX code):
master: 38951
this patch: 80586
NPS of the bench with NNUE enabled using baseline x86-64 arch, which is
how linux distros are likely to package stockfish, on a modern CPU
(using the SSE2 code):
master: 882584
this patch: 1203945
closes https://github.com/official-stockfish/Stockfish/pull/2956
No functional change.
despite usage of alignas, the generated (avx2/avx512) code with older compilers needs to use
unaligned loads with older gcc (e.g. confirmed crash with gcc 7.3/mingw on abrok).
Better performance thus requires gcc >= 9 on hardware supporting avx2/avx512
closes https://github.com/official-stockfish/Stockfish/pull/2969
No functional change
This patch ports the efficiently updatable neural network (NNUE) evaluation to Stockfish.
Both the NNUE and the classical evaluations are available, and can be used to
assign a value to a position that is later used in alpha-beta (PVS) search to find the
best move. The classical evaluation computes this value as a function of various chess
concepts, handcrafted by experts, tested and tuned using fishtest. The NNUE evaluation
computes this value with a neural network based on basic inputs. The network is optimized
and trained on the evalutions of millions of positions at moderate search depth.
The NNUE evaluation was first introduced in shogi, and ported to Stockfish afterward.
It can be evaluated efficiently on CPUs, and exploits the fact that only parts
of the neural network need to be updated after a typical chess move.
[The nodchip repository](https://github.com/nodchip/Stockfish) provides additional
tools to train and develop the NNUE networks.
This patch is the result of contributions of various authors, from various communities,
including: nodchip, ynasu87, yaneurao (initial port and NNUE authors), domschl, FireFather,
rqs, xXH4CKST3RXx, tttak, zz4032, joergoster, mstembera, nguyenpham, erbsenzaehler,
dorzechowski, and vondele.
This new evaluation needed various changes to fishtest and the corresponding infrastructure,
for which tomtor, ppigazzini, noobpwnftw, daylen, and vondele are gratefully acknowledged.
The first networks have been provided by gekkehenker and sergiovieri, with the latter
net (nn-97f742aaefcd.nnue) being the current default.
The evaluation function can be selected at run time with the `Use NNUE` (true/false) UCI option,
provided the `EvalFile` option points the the network file (depending on the GUI, with full path).
The performance of the NNUE evaluation relative to the classical evaluation depends somewhat on
the hardware, and is expected to improve quickly, but is currently on > 80 Elo on fishtest:
60000 @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f28fe6ea5abc164f05e4c4c
ELO: 92.77 +-2.1 (95%) LOS: 100.0%
Total: 60000 W: 24193 L: 8543 D: 27264
Ptnml(0-2): 609, 3850, 9708, 10948, 4885
40000 @ 20+0.2 th 8
https://tests.stockfishchess.org/tests/view/5f290229a5abc164f05e4c58
ELO: 89.47 +-2.0 (95%) LOS: 100.0%
Total: 40000 W: 12756 L: 2677 D: 24567
Ptnml(0-2): 74, 1583, 8550, 7776, 2017
At the same time, the impact on the classical evaluation remains minimal, causing no significant
regression:
sprt @ 10+0.1 th 1
https://tests.stockfishchess.org/tests/view/5f2906a2a5abc164f05e4c5b
LLR: 2.94 (-2.94,2.94) {-6.00,-4.00}
Total: 34936 W: 6502 L: 6825 D: 21609
Ptnml(0-2): 571, 4082, 8434, 3861, 520
sprt @ 60+0.6 th 1
https://tests.stockfishchess.org/tests/view/5f2906cfa5abc164f05e4c5d
LLR: 2.93 (-2.94,2.94) {-6.00,-4.00}
Total: 10088 W: 1232 L: 1265 D: 7591
Ptnml(0-2): 49, 914, 3170, 843, 68
The needed networks can be found at https://tests.stockfishchess.org/nns
It is recommended to use the default one as indicated by the `EvalFile` UCI option.
Guidelines for testing new nets can be found at
https://github.com/glinscott/fishtest/wiki/Creating-my-first-test#nnue-net-tests
Integration has been discussed in various issues:
https://github.com/official-stockfish/Stockfish/issues/2823https://github.com/official-stockfish/Stockfish/issues/2728
The integration branch will be closed after the merge:
https://github.com/official-stockfish/Stockfish/pull/2825https://github.com/official-stockfish/Stockfish/tree/nnue-player-wip
closes https://github.com/official-stockfish/Stockfish/pull/2912
This will be an exciting time for computer chess, looking forward to seeing the evolution of
this approach.
Bench: 4746616
