Scalable Node Level Computation Kernels for Parallel Exact Inference

In this paper, the authors investigate data parallelism in exact inference with respect to arbitrary junction trees. Exact inference is a key problem in exploring probabilistic graphical models, where the computation complexity increases dramatically with clique width and the number of states of random variables. They study potential table representation and scalable algorithms for node level primitives. Based on such node level primitives, they propose computation kernels for evidence collection and evidence distribution. A data parallel algorithm for exact inference is presented using the proposed computation kernels.