The FPGA-based SPCU architecture was compared with a software implementation running on a powerful workstation. The Bellman–Ford algorithm was coded in C and executed on an Intel Pentium-4, single-core 3400 MHz processor with 4 GB physical memory. For the sake of fair comparison, the C program was also made to terminate upon algorithm convergence. Also, the time required to load the graph topology into the memory was excluded. It can be seen from the results in Table 4 that despite running at a clock about 20 times slower compared to the CPU, the FPGA-based architecture for shortest-path computation is more than twice as fast as the CPU.