Throughput/Area-efficient ECC Processor Using Montgomery Point Multiplication on FPGA

Abstract

High throughput while maintaining low resource is a key issue for elliptic curve cryptography (ECC) hardware implementations in many applications. In this brief, an ECC processor architecture over Galois fields is presented, which achieves the best reported throughput/area performance on field-programmable gate array (FPGA) to date. A novel segmented pipelining digit serial multiplier is developed to speed up ECC point multiplication. To achieve low latency, a new combined algorithm is developed for point addition and point doubling with careful scheduling. A compact and flexible distributed-RAM-based memory unit design is developed to increase speed while keeping area low. Further optimizations were made via timing constraints and logic level modifications at the implementation level. The proposed architecture is implemented on Virtex4 (V4), Virtex5 (V5), and Virtex7 (V7) FPGA technologies and, respectively, achieved throughout/slice figures of 19.65, 65.30, and 64.48 (10 ⁶ /(Seconds × Slices)).