Scaling Up Large-Scale Graph Processing for GPU-Accelerated Heterogeneous Systems

TL;DR

This paper introduces Seraph, a GPU-accelerated system that enhances large-scale graph processing on heterogeneous systems by improving transmission efficiency through subgraph iteration and predictive vertex updating, achieving significant performance gains.

Contribution

Seraph presents a novel approach with pipelined subgraph iterations and predictive vertex updating to improve GPU utilization and scalability in heterogeneous graph processing systems.

Findings

Seraph outperforms Graphie by 5.42x and Garaph by 3.05x in processing speed.

It effectively scales with increased computing resources for large graphs.

The system demonstrates significant performance improvements on various large graph datasets.

Abstract

Not only with the large host memory for supporting large scale graph processing, GPU-accelerated heterogeneous architecture can also provide a great potential for high-performance computing. However, few existing heterogeneous systems can exploit both hardware advantages to enable the scale-up performance for graph processing due to the limited CPU-GPU transmission efficiency. In this paper, we investigate the transmission inefficiency problem of heterogeneous graph systems. Our key insight is that the transmission efficiency for heterogeneous graph processing can be greatly improved by simply iterating each subgraph multiple times (rather than only once in prior work) in the GPU, further enabling to obtain the improvable efficiency of heterogeneous graph systems by enhancing GPU processing capability. We therefore present Seraph, with the highlights of {\em pipelined} subgraph iterations and {\em predictive} vertex updating, to cooperatively maximize the effective computations of GPU on graph processing. Our evaluation on a wide variety of large graph datasets shows that Seraph outperforms state-of-the-art heterogeneous graph systems by 5.42x (vs. Graphie) and 3.05x (vs. Garaph). Further, Seraph can be significantly scaled up over Graphie as fed with more computing power for large-scale graph processing.