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 #4674 Bench: 1444646
official-stockfish · Jul 11, 2023 · af110e0 · af110e0 · PaulJeFi · Jul 12, 2023
1 parent 6a8767a
commit af110e0
Show file tree

Hide file tree

Showing 16 changed files with 37 additions and 2,745 deletions.
diff --git a/src/Makefile b/src/Makefile
@@ -56,8 +56,8 @@ else
 endif
 
 ### Source and object files
-SRCS = benchmark.cpp bitbase.cpp bitboard.cpp endgame.cpp evaluate.cpp main.cpp \
-	material.cpp misc.cpp movegen.cpp movepick.cpp pawns.cpp position.cpp psqt.cpp \
+SRCS = benchmark.cpp bitboard.cpp evaluate.cpp main.cpp \
+	misc.cpp movegen.cpp movepick.cpp position.cpp psqt.cpp \
 	search.cpp thread.cpp timeman.cpp tt.cpp uci.cpp ucioption.cpp tune.cpp syzygy/tbprobe.cpp \
 	nnue/evaluate_nnue.cpp nnue/features/half_ka_v2_hm.cpp
 

diff --git a/src/benchmark.cpp b/src/benchmark.cpp
@@ -153,24 +153,15 @@ vector<string> setup_bench(const Position& current, istream& is) {
   list.emplace_back("setoption name Hash value " + ttSize);
   list.emplace_back("ucinewgame");
 
-  size_t posCounter = 0;
-
   for (const string& fen : fens)
       if (fen.find("setoption") != string::npos)
           list.emplace_back(fen);
       else
       {
-          if (evalType == "classical" || (evalType == "mixed" && posCounter % 2 == 0))
-              list.emplace_back("setoption name Use NNUE value false");
-          else if (evalType == "NNUE" || (evalType == "mixed" && posCounter % 2 != 0))
-              list.emplace_back("setoption name Use NNUE value true");
           list.emplace_back("position fen " + fen);
           list.emplace_back(go);
-          ++posCounter;
       }
 
-  list.emplace_back("setoption name Use NNUE value true");
-
   return list;
 }
 

diff --git a/src/bitbase.cpp b/src/bitbase.cpp
diff --git a/src/bitboard.h b/src/bitboard.h
@@ -25,13 +25,6 @@
 
 namespace Stockfish {
 
-namespace Bitbases {
-
-void init();
-bool probe(Square wksq, Square wpsq, Square bksq, Color us);
-
-} // namespace Stockfish::Bitbases
-
 namespace Bitboards {
 
 void init();