Stockfish-NNUE

Scorpio · Post by **Scorpio** » 03/05/2020, 7:58

A new delivery from the SF team:

Author: Marco Costalba
Date: Sat May 2 17:32:11 2020 +0200
Timestamp: 1588433531

Fishtest Tuning Framework

The purpose of the code is to allow developers to easily and flexibly
setup SF for a tuning session. Mainly you have just to remove 'const'
qualifiers from the variables you want to tune and flag them for
tuning, so if you have:

int myKing = 10;
Score myBonus = S(5, 15);
Value myValue[][2] = { { V(100), V(20) }, { V(7), V(78) } };

and at the end of the update you may want to call
a post update function:

void my_post_update();

If instead of default Option's min-max values,
you prefer your custom ones, returned by:

std::pair<int, int> my_range(int value)

Or you jus want to set the range directly, you can
simply add below:

TUNE(SetRange(my_range), myKing, SetRange(-200, 200), myBonus, myValue, my_post_update);

And all the magic happens :-)

At startup all the parameters are printed in a
format suitable to be copy-pasted in fishtest.

In case the post update function is slow and you have many
parameters to tune, you can add:

UPDATE_ON_LAST();

And the values update, including post update function call, will
be done only once, after the engine receives the last UCI option.
The last option is the one defined and created as the last one, so
this assumes that the GUI sends the options in the same order in
which have been defined.

closes https://github.com/official-stockfish/Stockfish/pull/2654

No functional change.

Scorpio · Post by **Scorpio** » 06/05/2020, 16:09

https://abrok.eu/stockfish/

Author: xoto10
Date: Wed May 6 16:20:01 2020 +0200
Timestamp: 1588774801

Penalty for all enemy pawns xrayed by our bishop.

STC:
LLR: 2.93 (-2.94,2.94) {-0.50,1.50}
Total: 159760 W: 30229 L: 29813 D: 99718 Elo +0.90
Ptnml(0-2): 2659, 18309, 37534, 18713, 2665
https://tests.stockfishchess.org/tests/view/5eb1d5032326444a3b6d33ce

LTC:
LLR: 2.93 (-2.94,2.94) {0.25,1.75}
Total: 26496 W: 3908 L: 3656 D: 18932 Elo +3.30
Ptnml(0-2): 192, 2512, 7610, 2720, 214
https://tests.stockfishchess.org/tests/view/5eb1e2dd2326444a3b6d33f9

closes https://github.com/official-stockfish/Stockfish/pull/2662

Bench 5185517

Scorpio · Post by **Scorpio** » 09/05/2020, 10:08

https://abrok.eu/stockfish/

Author: xoto10
Date: Sat May 9 09:39:52 2020 +0200
Timestamp: 1589009992

Fix syzygy dependencies issue

fixes https://github.com/official-stockfish/Stockfish/issues/2660

The problem was caused by .depend being created with a rule for tbprobe.o not for syzygy/tbprobe.o.
This patch keeps an explicit list of sources (SRCS), generates OBJS,
and compiles all object files to the src/ directory, consistent with .depend.
VPATH is used to search the syzygy directory as needed.

joint work with @gvreuls

closes https://github.com/official-stockfish/Stockfish/pull/2664

No functional change

kramnik · Post by **kramnik** » 12/05/2020, 19:05

Is there someone wanting to make a compile if I make a new version source?

INNA · Post by **INNA** » 13/05/2020, 1:04

kramnik wrote:Is there someone wanting to make a compile if I make a new version source?

Yes

mocha1961 · Post by **mocha1961** » 13/05/2020, 2:42

it would be nice to have some tutorial on how to use this sf polyglot on a polyglot setting. how to load the 4 binbooks. I would like to try and use it in FlyorDie site using Horvig

kramnik · Post by **kramnik** » 13/05/2020, 3:13

[youtube]https://youtu.be/nJH0p09oWe0[/youtube]

minute 8:40

mocha1961 wrote:it would be nice to have some tutorial on how to use this sf polyglot on a polyglot setting. how to load the 4 binbooks. I would like to try and use it in FlyorDie site using Horvig

mocha1961 · Post by **mocha1961** » 13/05/2020, 10:56

can't play this video

Post by **timetraveller** » 13/05/2020, 10:58

Author: Moez Jellouli
Date: Mon May 11 20:46:39 2020 +0200
Timestamp: 1589222799

Tune pawn value

Small tune of PawnValue parameters -4 / -7 with "closedpos.epd" opening book.

STC:
LLR: 2.96 (-2.94,2.94) {-0.50,1.50}
Total: 58776 W: 11787 L: 11511 D: 35478 Elo +1.63
Ptnml(0-2): 975, 6876, 13443, 7086, 1008
https://tests.stockfishchess.org/tests/view/5eb5aa712326444a3b6d3e33

LTC:
LLR: 2.98 (-2.94,2.94) {0.25,1.75}
Total: 137544 W: 19687 L: 19115 D: 98742 Elo +1.44
Ptnml(0-2): 988, 13219, 39901, 13561, 1103
https://tests.stockfishchess.org/tests/view/5eb67a392326444a3b6d3e9a

Non regression STC with "noob_3moves.epd" opening book
LLR: 2.94 (-2.94,2.94) {-1.50,0.50}
Total: 98168 W: 18545 L: 18499 D: 61124 Elo +0.16
Ptnml(0-2): 1647, 11396, 22951, 11444, 1646
https://tests.stockfishchess.org/tests/view/5eb7e489e0300e8e8c896203

closes https://github.com/official-stockfish/Stockfish/pull/2670

Bench 4696646
source
-----------------------------------------------------------------------------------------------------------------------------
Author: Joost VandeVondele
Date: Mon May 11 20:41:49 2020 +0200
Timestamp: 1589222509

Use posix_memalign instead of aligned_alloc

should be a little more portable to older linux systems (before glibc-2.16).

fixes https://github.com/official-stockfish/Stockfish/issues/2665

closes https://github.com/official-stockfish/Stockfish/pull/2668

kramnik · Post by **kramnik** » 13/05/2020, 13:36

https://youtu.be/nJH0p09oWe0 minute 8:40

mocha1961 wrote:can't play this video

JairoSawka · Post by **JairoSawka** » 13/05/2020, 14:23

mocha1961 wrote:it would be nice to have some tutorial on how to use this sf polyglot on a polyglot setting. how to load the 4 binbooks. I would like to try and use it in FlyorDie site using Horvig

what program do you use?

if you use chess bots, don't waste your time, this Kramnik version works very bad.

i can show you how to run the 4 books and you can try it,

I tried it and the engine doesn't read the books properly and besides, it moves very slow.

kramnik · Post by **kramnik** » 13/05/2020, 14:33

That bug has been fixed:

Changelog:
-Fixed the OwnBook checkbox bug
-Matching Stockfish beta having timestamp 1586274421 - continuation histories when in check.

Download it again and try.

JairoSawka wrote:
mocha1961 wrote:it would be nice to have some tutorial on how to use this sf polyglot on a polyglot setting. how to load the 4 binbooks. I would like to try and use it in FlyorDie site using Horvig

what program do you use?

if you use chess bots, don't waste your time, this Kramnik version works very bad.

i can show you how to run the 4 books and you can try it,

I tried it and the engine doesn't read the books properly and besides, it moves very slow.

mocha1961 · Post by **mocha1961** » 14/05/2020, 7:31

Author: Tomasz Sobczyk
Date: Wed May 13 19:50:30 2020 +0200
Timestamp: 1589392230

Use a trivially copyable struct for TBTables::Entry instead of a tuple.

fixes https://github.com/official-stockfish/Stockfish/issues/2673
which is a warning issued by recent gcc (10.1)

closes https://github.com/official-stockfish/Stockfish/pull/2674

No functional change

------------------------------------------------------------------------------------------------------------------

Author: Sami Kiminki
Date: Wed May 13 20:57:47 2020 +0200
Timestamp: 1589396267

Add support for Windows large pages

for users that set the needed privilige "Lock Pages in Memory"
large pages will be automatically enabled (see Readme.md).

This expert setting might improve speed, 5% - 30%, depending
on the hardware, the number of threads and hash size. More for
large hashes, large number of threads and NUMA. If the operating
system can not allocate large pages (easier after a reboot), default
allocation is used automatically. The engine log provides details.

closes https://github.com/official-stockfish/Stockfish/pull/2656

fixes https://github.com/official-stockfish/Stockfish/issues/2619

No functional change

Download: https://abrok.eu/stockfish/

Post by **timetraveller** » 14/05/2020, 20:50

Author: protonspring
Date: Thu May 14 20:47:59 2020 +0200
Timestamp: 1589482079

Simplify Time Management

This is a functional simplification of the time management system.

With this patch, there is a simple equation for each of two distinct
time controls: basetime + increment, and x moves in y seconds (+increment).
These equations are easy to plot and understand making future modifications
or adding additional time controls much easier.

SlowMover is reset to 100 so that is has no effect unless a user changes it.

There are two scaling variables:
* Opt_scale is a scale factor (or percentage) of time to use for this current move.
* Max_scale is a scale factor to apply to the resulting optimumTime.

There seems to be some elo gain in most scenarios.
Better performance is attributable to one of two things:
* minThinkingTime was not allowing reasonable time calculations for very short games like 10+0 or 10+0.01. This is because adding almost no increment and substracting move overhead for 50 moves quickly results in almost 0 time very early in the game. Master depended on minThinkingTime to handle these short games instead of good time management. This patch addresses this issue by lowering minThinkingTime to 0 and adjusting moverOverhead if there are very low increments.
* Notice that the time distribution curves tail downward for the first 10 moves or so. This causes less time to attribute for very early moves leaving more time available for middle moves where more important decisions happen.

Here is a summary of tests for this version at different time controls:

SMP 5+0.05
LLR: 2.97 (-2.94,2.94) {-1.50,0.50}
Total: 46544 W: 7175 L: 7089 D: 32280 Elo +0.64
Ptnml(0-2): 508, 4826, 12517, 4914, 507
https://tests.stockfishchess.org/tests/user/protonspring

STC
LLR: 2.94 (-2.94,2.94) {-1.50,0.50}
Total: 20480 W: 3872 L: 3718 D: 12890 Elo +2.61
Ptnml(0-2): 295, 2364, 4824, 2406, 351
https://tests.stockfishchess.org/tests/view/5ebc343e7dd5693aad4e6873

STC, sudden death
LLR: 2.93 (-2.94,2.94) {-1.50,0.50}
Total: 7024 W: 1706 L: 1489 D: 3829 Elo +10.74
Ptnml(0-2): 149, 813, 1417, 938, 195
https://tests.stockfishchess.org/tests/view/5ebc346f7dd5693aad4e6875

STC, TCEC style
LLR: 2.95 (-2.94,2.94) {-1.50,0.50}
Total: 4192 W: 1014 L: 811 D: 2367 Elo +16.84
Ptnml(0-2): 66, 446, 912, 563, 109
https://tests.stockfishchess.org/tests/view/5ebc34857dd5693aad4e6877

40/10
LLR: 2.93 (-2.94,2.94) {-1.50,0.50}
Total: 54032 W: 10592 L: 10480 D: 32960 Elo +0.72
Ptnml(0-2): 967, 6148, 12677, 6254, 970
https://tests.stockfishchess.org/tests/view/5ebc50597dd5693aad4e688d

LTC, sudden death
LLR: 2.95 (-2.94,2.94) {-1.50,0.50}
Total: 9152 W: 1391 L: 1263 D: 6498 Elo +4.86
Ptnml(0-2): 75, 888, 2526, 1008, 79
https://tests.stockfishchess.org/tests/view/5ebc6f5c7dd5693aad4e689b

LTC
LLR: 2.98 (-2.94,2.94) {-1.50,0.50}
Total: 12344 W: 1563 L: 1459 D: 9322 Elo +2.93
Ptnml(0-2): 70, 1103, 3740, 1171, 88
https://tests.stockfishchess.org/tests/view/5ebc6f4c7dd5693aad4e6899

closes https://github.com/official-stockfish/Stockfish/pull/2678

Bench: 4395562
source

kramnik · Post by **kramnik** » 15/05/2020, 14:47

tacos40 wrote:- I remember in old MZ forum this problem happened to several engines: Raubfisch, MZfish, Sugar or S_XPrO, Brainlearn and the like
- In fact, I referred to it as BBMI : "Best Book Move Issue"
- I have found a backup of Brainlearn with SRC where BBMI was fixed, in case it can help; link below
- https://www.dropbox.com/s/z2yax07d5jwbixh/MZ2019_09oct_BBMI_BIN_book_FIXED_BrainFish%20X%201.4.1.zip?dl=1

Hope it helps

Tacos, I'm checking the source you gave me, I guess you are wrong: the function PolyBook::probe is perfectly equal in both the sources.

In particular:

if (use_best_book_move)
idx1 = index_best;
else
idx1 = index_rand;

m1 = pg_move_to_sf_move(pos, polyhash[idx1].move);

m1 is the move returned by the function.

you can see in the else statement that a random variable is used, therefore there isn't any issue about BestBookMove set to OFF.

Outskirts CheSS ForuM

Outskirts CheSS ForuM

Stockfish-NNUE

Stockfish

Stockfish

Stockfish

Stockfish Polyglot

Stockfish Polyglot

Stockfish Polyglot

Stockfish Polyglot

Stockfish Polyglot

Stockfish

Stockfish Polyglot

Stockfish Polyglot

Stockfish Polyglot

Stockfish

Stockfish

Stockfish Polyglot