Design Of An Elliptic Curve Cryptographic SoC Over GF(p)

With the continuous development of computer and electronic commerce, information security becomes increasingly important. Public key cryptography is an important branch of information security. As the security per-bit of elliptic curve cryptosystem is known as the highest in the public key cryptography, elliptic curve cryptosystem is widely used.This thesis presented the research of elliptic curve cryptographic SoC design and proposed a suitable SoC architecture for the elliptic curve cryptographic algorithms. Firstly the background of the SoC and hardware/software co-design methodology of SoC were introduced, followed by the basic theory of elliptic curve cryptographic algorithm and SM2algorithm. Secondly the software efficiency of Elliptic Curve Cryptography (ECC) algorithm over GF(p) was analyzed. Against the disadvantages of the software implementation, the partition between software and hardware was given. A hardware accelerator suitable for Sytem-on-Chip (SoC) was proposed.Hardware acceleration for both filed multiplication and Miller-Rabin primality test was implemented, of which the bit width is multiples of64, from192to2048. The acceleration was equipped with a tightly coupled memory. Based on the HJTC O.llum eFlash standard cell-library, the maximum working frequency of the accelerator is up to160MHZ and the area of the accelerator is about0.6mm2. The accelerator can execute167operations per second for192-bit unknown-point multiplication and94operations per second for256-bit at50MHz. Experimental results show that the performance per unit area of the accelerator is higher than other approaches. The SM2public key cryptographic algorithm was implemented on chip, area of the whole chip is about4mm2. The chip can execute64.1times digital signature per second,25.6times signature verification per second,35.7times public key encryption per second,60.2times public key decryption per second,72.7times key generation per second and11.8times key exchange per second. Experimental results show that the performance per unit area of the accelerator is higher than other approaches.