fix sim model for PO that also drive further logic

src/kyupy/sim.py

@@ -272,10 +272,10 @@ class SimOps:
 
         # allocate and keep memory for PI/PPI, keep memory for PO/PPO (allocated later)
         for i, n in enumerate(circuit.s_nodes):
-            if len(n.outs) > 0:
+            if 'dff' in n.kind.lower() or len(n.ins) == 0:  # PPI or PI
                 self.c_locs[self.ppi_offset + i], self.c_caps[self.ppi_offset + i] = h.alloc(c_caps_min), c_caps_min
                 ref_count[self.ppi_offset + i] += 1
-            if len(n.ins) > 0:
+            if len(n.ins) > 0:  # PO
                 i0_idx = stems[n.ins[0]] if stems[n.ins[0]] >= 0 else n.ins[0]
                 ref_count[i0_idx] += 1