Institute of Electrical & Electronic Engineers
Markov Chain Monte Carlo (MCMC) is a method used to draw samples from probability distributions in order to estimate - otherwise intractable - integrals. When the distribution is complex, simple MCMC becomes inefficient and advanced, computationally intensive MCMC methods are employed to make sampling possible. This paper proposes a novel streaming FPGA architecture to accelerate Parallel Tempering, a widely adopted MCMC method designed to sample from multimodal distributions. The proposed architecture demonstrates how custom precision can be intelligently employed without introducing sampling errors, in order to save resources and increase the sampling throughput.