MT-lib: A Topology-aware Message Transfer Library for Graph500 on Supercomputers

TL;DR

MT-lib is a lightweight, topology-aware message transfer library designed to optimize communication in graph processing benchmarks like Graph500 on supercomputers, featuring novel non-blocking schemes and message merging techniques.

Contribution

Introduces MT-lib with innovative non-blocking communication, message merging, and intra-group message gathering for efficient large-scale graph processing.

Findings

High communication efficiency demonstrated on Tianhe supercomputers.

Achieved high throughput for BFS and SSSP operations.

Effective reduction of communication overhead in graph benchmarks.

Abstract

We present MT-lib, an efficient message transfer library for messages gather and scatter in benchmarks like Graph500 for Supercomputers. Our library includes MST version as well as new-MST version. The MT-lib is deliberately kept light-weight, efficient and friendly interfaces for massive graph traverse. MST provides (1) a novel non-blocking communication scheme with sending and receiving messages asynchronously to overlap calculation and communication;(2) merging messages according to the target process for reducing communication overhead;(3) a new communication mode of gathering intra-group messages before forwarding between groups for reducing communication traffic. In MT-lib, there are (1) one-sided message; (2) two-sided messages; and (3) two-sided messages with buffer, in which dynamic buffer expansion is built for messages delivery. We experimented with MST and then testing Graph500 with MST on Tianhe supercomputers. Experimental results show high communication efficiency and high throughputs for both BFS and SSSP communication operations.