Sparse Spiking Neural-like Membrane Systems on Graphics Processing Units

TL;DR

This paper introduces GPU-accelerated, sparse matrix representations for simulating Spiking Neural P systems, significantly improving efficiency for sparse neural graphs compared to dense matrix methods.

Contribution

It implements and parallelizes two sparse matrix compression methods on GPUs, enhancing simulation performance of Spiking Neural P systems with delays.

Findings

Sparse matrix methods outperform dense matrix approaches on GPUs.

GPU implementation achieves higher efficiency on high-end GPUs.

Simulation speed is significantly improved with sparse representations.

Abstract

The parallel simulation of Spiking Neural P systems is mainly based on a matrix representation, where the graph inherent to the neural model is encoded in an adjacency matrix. The simulation algorithm is based on a matrix-vector multiplication, which is an operation efficiently implemented on parallel devices. However, when the graph of a Spiking Neural P system is not fully connected, the adjacency matrix is sparse and hence, lots of computing resources are wasted in both time and memory domains. For this reason, two compression methods for the matrix representation were proposed in a previous work, but they were not implemented nor parallelized on a simulator. In this paper, they are implemented and parallelized on GPUs as part of a new Spiking Neural P system with delays simulator. Extensive experiments are conducted on high-end GPUs (RTX2080 and A100 80GB), and it is concluded that they outperform other solutions based on state-of-the-art GPU libraries when simulating Spiking Neural P systems.