merge: SIMD popcount fallback

pm2d/_jit_kernels.py

@@ -517,10 +517,22 @@ def top_max_per_variant(
     )
 
 
+_HAS_NP_BITCOUNT = hasattr(np, "bitwise_count")
+
+
 def popcount_density(spread: np.ndarray) -> np.ndarray:
+    """Conta bit set per pixel.
+
+    Order:
+    1) Numba JIT parallel (preferito: piu veloce su 1080p, 0.5ms vs 1.6ms)
+    2) numpy.bitwise_count (NumPy 2.0+, SIMD ma single-thread)
+    3) Fallback numpy bit-shift puro
+    """
+    spread_c = np.ascontiguousarray(spread, dtype=np.uint8)
     if HAS_NUMBA:
-        return _jit_popcount_density(np.ascontiguousarray(spread, dtype=np.uint8))
-    # Fallback
+        return _jit_popcount_density(spread_c)
+    if _HAS_NP_BITCOUNT:
+        return np.bitwise_count(spread_c).astype(np.float32, copy=False)
     H, W = spread.shape
     out = np.zeros((H, W), dtype=np.float32)
     for b in range(8):