The growing use of graph in many fields has sparked a broad interest in developing high-level graph analytics programs. Existing\nGPU implementations have limited performance with compromising on productivity. HPGraph, our high-performance bulksynchronous\ngraph analytics framework based on the GPU, provides an abstraction focused on mapping vertex programs to\ngeneralized sparse matrix operations on GPU as the backend. HPGraph strikes a balance between performance and productivity\nby coupling high-performance GPU computing primitives and optimization strategies with a high-level programming model for\nusers to implement various graph algorithms with relatively little effort. We evaluate the performance of HPGraph for four graph\nprimitives (BFS, SSSP, PageRank, and TC). Our experiments show that HPGraph matches or even exceeds the performance of\nhigh-performance GPU graph libraries such as MapGraph, nvGraph, and Gunrock. HPGraph also runs significantly faster than\nadvanced CPU graph libraries.
Loading....