Wire NNUE eval into real search path; fix critical perf regression

Load-and-call infra: export_nnue_weights.py-produced weight files can
now be loaded at runtime (nnueeval.c's NnueLoadWeights, "nnue load"
command, --nnueweights CLI flag for scripted match-play), and the FC
head (NnueForward) runs the real forward pass against the live
accumulator.

Real integration: Eval() now short-circuits to NnueForward when
g_fUseNnueEval && g_fNnueWeightsLoaded, so ./typhoon can actually play
on the NNUE eval -- ./eval_tune/test_vs_head.sh works unmodified to
compare it against the old HCE. ReInitializeSearcherContext (root.c)
gained a defensive accumulator recompute hook covering setboard's
downstream effect on the next go/ponder; it only fires when both
kings are validly placed, since testrecogn.c's synthetic positions
don't always have one at the moment this is called.

Critical fix: the NNUE accumulator maintenance added to move.c's 8
primitives (and MakeMove/UnmakeMove's king-move backup/restore) was
running unconditionally, on the mistaken assumption this was cheap.
It cost ~50% of engine throughput even with NNUE off (673k nps
measured vs the expected 1.4-1.5M baseline). Gated all of it behind
g_fUseNnueEval; classic HCE is back to ~1.52M nps, NNUE eval runs at
a fair ~409k nps (expected for an unquantized float32 forward pass).

This gating also exposed that testnnue.c's TestNnueAccumulator never
set g_fUseNnueEval, so its own direct NnueAccumRecompute calls raced
ahead of now-gated-off incremental maintenance; fixed by having the
test set/restore the flag around its run.

board.c: added en passant legality check to IsBoardLegal (rank vs
side-to-move, origin-square occupancy) -- a real, previously-latent
bug surfaced while building the NNUE test fixtures, unrelated to
NNUE itself.

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

1 files changed, 25 insertions, 1 deletions

diff --git a/src/main.c b/src/main.c
index ac2ebf6..90301af 100644
--- a/src/main.c
+++ b/src/main.c
@@ -50,7 +50,6 @@ Return value:
 
     Trace("Typhoon %s (built on %s %s, commit %s):\n", VERSION, __DATE__, __TIME__, GIT_COMMIT);
     Trace("    Copyright (C) 2000-2026, Scott Gasch ([email protected])\n");
-    Trace("    " REVISION);
     Trace("    " COMPILER_STRING);
     Trace("    Make profile used: %s\n", PROFILE);
 #ifdef MP
@@ -400,6 +399,31 @@ Return value:
         {
             g_Options.fNoInputThread = TRUE;
         }
+        else if ((!STRCMPI(pszArg, "--nnueweights")) && fHaveVal)
+        {
+            // Loads and enables NNUE eval at startup -- for scripted
+            // match-play (eval_tune/match_play.py et al) spawning a
+            // fresh engine process per game, where there's no
+            // reliable way to send an interactive "nnue load"/"nnue
+            // on" command pair before the first "go". Interactive use
+            // can still do the same thing via the 'nnue' command.
+            if (!NnueLoadWeights(pszVal))
+            {
+                UtilPanic(INITIALIZATION_FAILURE,
+                          (void *)"Bad NNUE weights file",
+                          (void *)&(pszVal),
+                          (void *)"load",
+                          NULL,
+                          __FILE__, __LINE__);
+            }
+            else
+            {
+                g_fUseNnueEval = TRUE;
+                Trace("Loaded NNUE weights \"%s\", NNUE eval enabled.\n",
+                      pszVal);
+            }
+            if (fConsumedNextArg) i++;
+        }
         else if ((!STRCMPI(pszArg, "--dnafile")) && fHaveVal)
         {
             if (!ReadEvalDNA(pszVal))