Optimising simulation data structures for the Xeon Phi

In this paper, we propose a lock-free architecture to accelerate logic gate circuit simulation using SIMD multi-core machines. We evaluate its performance on different test circuits simulated on the Intel Xeon Phi and 2 other machines. Comparisons are presented of this software/hardware combination with reported performances of GPU and other multi-core simulation platforms. Comparisons are also given between the lock free architecture and a leading commercial simulator running on the same Intel hardware.