Accelerating Large-Scale Single-Source Shortest Path on FPGA

Abstract

Many real-world problems can be represented as graphs and solved by graph traversal algorithms. Single-Source Shortest Path (SSSP) is a fundamental graph algorithm. Today, large-scale graphs involve millions or even billions of vertices, making efficient parallel graph processing challenging. In this paper, we propose a single-FPGA based design to accelerate SSSP for massive graphs. We adopt the well-known Bellman-Ford algorithm. In the proposed design, graph is stored in external memory, which is more realistic for processing large scale graphs. Using the available external memory bandwidth, our design achieves the maximum data parallelism to concurrently process multiple edges in each clock cycle, regardless of data dependencies. The performance of our design is independent of the graph structure as well. We propose a optimized data layout to enable efficient utilization of external memory bandwidth. We prototype our design using a state-of-the-art FPGA. Experimental results show that our design is capable of processing 1.6 billion edges per second (GTEPS) using a single FPGA, while simultaneously achieving high clock rate of over 200 MHz. This would place us in the 131st position of the Graph 500 benchmark list of supercomputing systems for data intensive applications. Our solution therefore provides comparable performance to state-of-the-art systems.