Schönhage-Strassen algorithm (SSA) based on the number-theoretic transform is one of the faster large integer multiplication algorithms widely used in the practical applications at present. Firstly in this paper, the principle of the SSA algorithm is introduced in detail. Then, parallel optimization is applied to SSA algorithm from a fine-grained perspective in the multi-core platform. The parallel SSA algorithm is implemented based on the open source library of large integer arithmetic algorithm GMP, and its correctness and performance is validated in the Intel X86 platform. The maximum speedup can reach 6.59 and the average speedup is 6.41 by 8 threads. The scalability of the parallel SSA algorithm is tested on the Inspur TS850, and experimental results show that it has good scalability and the maximum speedup can reach 21.42.