MCPT-Solver: An Monte Carlo Algorithm Solver Using MTJ Devices for Particle Transport Problems

2026-03-30

AI Summary

This work addresses the efficiency bottleneck of von Neumann architectures in Monte Carlo particle transport simulations, which arises from irregular memory access patterns and stochastic branching. To overcome this limitation, the authors propose a spin-based true random number generator leveraging magnetic tunnel junctions (MTJs), integrated with a hardware Bayesian inference network to enable tunable output probabilities. This design is the first to simultaneously achieve process–voltage–temperature tolerance and probabilistic programmability, specifically optimized for hardware acceleration of stochastic algorithms. System-level simulations demonstrate exceptional performance in particle transport problems, achieving a mean squared error as low as 7.6×10⁻⁶, a throughput of 185 Mb/s, an area efficiency of 27.8 μm²/bit, and an energy consumption of only 8.6 pJ/bit—significantly outperforming general-purpose processors.

Abstract

Monte Carlo particle transport problems play a vital role in scientific computing, but solving them on exiting von Neumann architectures suffers from random branching and irregular memory access, causing computing inefficiency due to a fundamental mismatch between stochastic algorithms and deterministic hardware. To bridge this gap, we propose MCPT-Solver, a spin-based hardware true random number generator (TRNG) with tunable output probability enabled by a Bayesian inference network architecture. It is dedicated for efficiently solving stochastic applications including Monte Carlo particle transport problems. First, we leverage the stochastic switching property of spin devices to provide a high-quality entropy source for the TRNG and achieve high generating throughput and process-voltage-temperature tolerance through optimized control logic and write mechanism designs. Next, we propose a hardware Bayesian inference network to enable probability-tunable random number outputs. Finally, we present a system-level simulation framework to evaluate MCPT-Solver. Experimental results show that MCPT-Solver achieves a mean squared error of 7.6e-6 for solving transport problems while demonstrating a dramatic acceleration effect over general-purpose processors. Additionally, the MCPT-Solver's throughput reaches 185 Mb/s with an area of 27.8 um2/bit and energy consumption of 8.6 pJ/bit, making it the first spin-based TRNG that offers both process-voltage-temperature tolerance and adjustable probability.

Problem

• Monte Carlo particle transport
• von Neumann architecture
• random branching
• irregular memory access
• stochastic algorithms

Innovation

• MTJ-based TRNG
• Monte Carlo particle transport
• Bayesian inference hardware
• spintronic computing
• probability-tunable random number generation