Efficient Situational Scheduling of Graph Workloads on Single-Chip Multicores and GPUs

Situational dynamic changes in graph analytic algorithm implementations give rise to efficiency challenges in concurrent hardware, such as GPUs and large-scale multicores. These performance variations stem from input dependence, such as the density and degree of the graph being processed. Consequently, concurrency control becomes challenging, because the complex data-dependent behavior in these workloads exhibits a range of plausible algorithmic and architectural choices. This article addresses the question of how to efficiently harness the multidimensional search space of such choices for graph analytic workloads in a real-time execution environment. A key insight is that architectural choices are sufficient to yield a concurrency control setting that is comparable to the optimal setup that optimizes both algorithmic and architectural choices. The authors propose a situationally adaptive scheduler (SAS) that learns the architectural choices offline using synthetically generated graphs. SAS-assisted execution in a real-time setup provides geometric performance gains of 40 percent for a large-scale GPU (Nvidia GTX-970), 35 percent for a smaller GPU (Nvidia GTX- 750Ti), and 30 percent for a large-scale multicore (Intel Xeon Phi).