Real-time tasks for command and control systems are too large or too complex for one processor to handle.  Simply adding more CPUs does not result in a linear increase in performance. Current comparative analysis of parallel algorithms does not accurately reflect the increased  cost of scheduling when more processors are added.   A case is made that associative processors effectively handle real-time command and control type problems and avoid most of the difficulties introduced by multiprocessors. These results suggest that when comparing different architectures, comparative analysis should consider the ALU and control unit {CU} separately.