David Tompkins

Exploring GPU Acceleration of Apache Spark

Apache Spark is one of the most active open-source cluster computing frameworks. However, there has been very limited research on improving Spark performance using GPUs. This paper explores the feasibility and benefits of off loading Spark core operations to GPUs. Experimental results from popular Spark applications show a performance improvement of up to 17X for a K-Means Clustering application. The results are used to suggest the type of applications that will benefit the most from off loading Spark workloads to GPUs.