Algorithmically-Enhanced Design of Spintronic-Based Tunable True Random Number Generator for Dependable Stochastic Computing

This paper proposes a tunable true random number generator (TTRNG) based on stochastic magnetic tunnel junction (MTJ) switching in the subcritical current regime. The proposed design consists of three parts. The first part is a write/read circuit featuring a static write circuit and an energy-efficient circuit optimized for read operations. The second finds the Probability Generation Array (PGA) similar to the Longest Common Subsequence (LCS) problem. However, the algorithms presented so far for the LCS have not been responsive to finding the Desired-PGA as it must look for the common subsequence among one million sequences, each sequence being 259 long. Hence, the convergence of those algorithms is impossible in this problem. Accordingly, we propose an algorithm to find a common subsequence of length 24, each defining a logic function. We also propose a controller to generate arbitrary probabilities with a zero steady-state error. These parts, especially PGA, make the design highly robust to the process variations. Notably, the proposed design passes the NIST test. The proposed design also reduces energy dissipation compared to previous designs. Also, as it does not require precise sizing, the FinFET technology is appropriately used to design the proposed approach.