Research of high performance architecture for elliptic curve scalar multiplication over GF(2m)

A efficient hardware architecture accelerators to speed up the scalar multiplications on elliptic curves over GF(2m) in polynomial basis representation was proposed. The performance and area trade-off is considered reasonably. The point addition module and point doubling module can operation in parallel. They are optimized and implemented by the method of combining parallel and serial. Initialization and the final coordinates conversion module are decomposed into a series of multiplication and addition operations, which can be merged into one module finally. The implementation results based on Xilinx VirtexE XCV2600 FPGA show that our proposed design is able to compute general GF(2163) elliptic curve scalar multiplication operations in 36.5 μs, which indicates this architecture is suitable for high-performance application.