Retire cPawns/cNonPawns piece-location lists in favor of bbPawns/bbPieces/cKingSq, and hoist two redundant TotalNonPawnCount POPCNT calls out of per-node hot loops.

POSITION no longer stores cPawns[2][8], cNonPawns[2][16], uPawnCount[2],
uNonPawnCount[2][8], or uWhiteSqBishopCount[2] -- every reader now goes
through PawnMaterial/TotalNonPawnCount/WhiteSqBishopCount/KingPosition
(chess.h), computed from the already-incrementally-maintained bbPawns/
bbPieces/cKingSq bitboards via a single -mpopcnt POPCNT instead of a
stored counter. move.c's make/unmake loses the list-swap-on-removal
bookkeeping entirely. GNUmakefile now passes -mpopcnt so the popcount
builtins actually compile to one instruction instead of clang's ~15-op
SWAR fallback.

Measured a small but real nps regression from the naive swap (search.c's
QSearch move-filter and eval.c's _EvalKing were each recomputing the same
TotalNonPawnCount sum on every candidate move / twice per node); hoisted
both to a single call per node instead. Net result across a same-code
self-play match: ~1541.5 knps candidate vs ~1505.7 knps head_reference.

A third hoist (FindEnprisePiece out of SelectBestWithHistory) was tried
and reverted -- its cache isn't actually loop-invariant within a node
(populated from inside Eval(), which doesn't run before every selection
call), caught by a DEBUG-build ASSERT before it landed.

Co-Authored-By: Claude Sonnet 5 <[email protected]>

1 files changed, 16 insertions, 15 deletions

diff --git a/src/root.c b/src/root.c
index f5fe4c1..314395a 100644
--- a/src/root.c
+++ b/src/root.c
@@ -1033,19 +1033,22 @@ _DetectPreMoveTerminalStates(SEARCHER_THREAD_CONTEXT *ctx,
     
     // Look for insufficient material.
     FOREACH_COLOR(u) {
-        uMajors[u] = (pos->uNonPawnCount[u][ROOK] +
-                      pos->uNonPawnCount[u][QUEEN]);
-        uMinors[u] = (pos->uNonPawnCount[u][KNIGHT] +
-                      pos->uNonPawnCount[u][BISHOP]);
-        uWhiteBishops[u] = pos->uWhiteSqBishopCount[u];
-        uBlackBishops[u] = pos->uNonPawnCount[u][BISHOP] - uWhiteBishops[u];
+        uMajors[u] = (FastCountBits(pos->bbPieces[u][ROOK]) +
+                      FastCountBits(pos->bbPieces[u][QUEEN]));
+        uMinors[u] = (FastCountBits(pos->bbPieces[u][KNIGHT]) +
+                      FastCountBits(pos->bbPieces[u][BISHOP]));
+        uWhiteBishops[u] = WhiteSqBishopCount(pos, u);
+        uBlackBishops[u] = FastCountBits(pos->bbPieces[u][BISHOP]) - uWhiteBishops[u];
     }
     FOREACH_COLOR(u) {
-        if ((pos->uPawnCount[u] != 0) || 
-            (pos->uPawnCount[FLIP(u)] != 0)) {
+        ULONG uNonKing = FastCountBits(NON_KING_PIECES_BB(pos, u));
+        ULONG uNonKingFlip = FastCountBits(NON_KING_PIECES_BB(pos, FLIP(u)));
+
+        if ((pos->bbPawns[u] != 0) ||
+            (pos->bbPawns[FLIP(u)] != 0)) {
               continue;
         }
-        if (pos->uNonPawnCount[u][0] == 1) {
+        if (uNonKing == 0) {
             if (uMajors[FLIP(u)] == 0 &&
                 uMinors[FLIP(u)] == 1) {
                 ret.eResult = RESULT_DRAW;
@@ -1058,12 +1061,10 @@ _DetectPreMoveTerminalStates(SEARCHER_THREAD_CONTEXT *ctx,
                 strcpy(ret.szDescription, "insufficient material");
                 return ret;
             }
-        } else if ((pos->uNonPawnCount[u][0] == 1 + uWhiteBishops[u] &&
-                   pos->uNonPawnCount[FLIP(u)][0] == 
-                   1 + uWhiteBishops[FLIP(u)]) ||
-                   (pos->uNonPawnCount[u][0] == 1 + uBlackBishops[u] &&
-                    pos->uNonPawnCount[FLIP(u)][0] ==
-                    1 + uBlackBishops[FLIP(u)])) {
+        } else if ((uNonKing == uWhiteBishops[u] &&
+                   uNonKingFlip == uWhiteBishops[FLIP(u)]) ||
+                   (uNonKing == uBlackBishops[u] &&
+                    uNonKingFlip == uBlackBishops[FLIP(u)])) {
             ret.eResult = RESULT_DRAW;
             strcpy(ret.szDescription, "insufficient material");
             return ret;