A high performance implementation of the IDEA presented by Leong [8] uses a novel bit-serial architecture to perform multiplication modulo 216 + 1; the implementation occupies a minimal amount of hardware. The bit-serial architecture enabled the algorithm to be deeply pipelined to achieve a system clock rate of 125MHz. An implementation on a Xilinx Virtex X CV300-4 was successfully tested, delivering a throughput of 500Mb/sec. With a X CV1000-6 device, the estimated performance is 2.35Gb/sec, three orders of magnitude faster than a software implementation on a 450MHz Intel Pentium II. This design is suitable for applications in online encryption for high-speed networks. The results of Leong’s experiment are summarized in Table 3.