Graph Generation on GPUs using Dynamic Memory Allocation

Complex networks are often studied using statistical measurements over many independently generated samples. Irregular data structures such as graphs that involve dynamical memory management and “pointer chasing” are an important class of application and have attracted recent interest in the form of the Graph500 benchmark formulation. The generation of simulated sample network graphs and measurement of their properties can be accelerated using Graphical Processing Units (GPUs) and we discuss some algorithmic approaches using Compute Unified Device Architecture (CUDA). We particularly discuss recent support for dynamic memory allocation within CUDA GPU code and present some performance data for Watts’ α small-world